Search

Highlights: [•] Input Variable Selection (IVS) helps when processing system inputs is computationally heavy. [•] A framework to accommodate high level perspective of different approaches to IVS is provided. [•] Sensitivity analysis (SA) helps IVS in heterogeneous input variables with time constraint. [•] Event-based SA proves fit by its application in an industrial drilling disaster prevention problem. [Copyright &y& Elsevier]

In the rapidly changeable market, product innovation is critical for enterprises to improve their product competitiveness. Product innovation can be described as an evolutionary process of technical systems where the relationship between technologies follows the evolution from parasitism to symbiosis in technological parasitism theory. The existing research on the technological parasitism theory mainly focuses on explaining and verifying the evolution law of product systems from parasitism to symbiosis in the product innovation process. However, these research activities are a post-hoc summary, which limits the guidance for enterprises to proactively realize the evolution of products from parasitism to symbiosis in an ex-ante perspective. For the development of innovative products in the engineering field, enterprises lack an effective ex-ante design method to proactively find the appropriate parasitic technology, and integrate it with the host technology for the product system evolving towards a symbiotic state. To fill this gap, this paper proposes a product innovation design process based on the recombination of host and target genes under the technological parasitism framework. Product scenario analysis is used to explore the potential function needs to determine the search direction of parasitic technologies. The min-complement distance measure method is introduced to identify the appropriate parasitic technology. Based on four recombination operations, the construction process of new product genome through the recombination of host and target genes is proposed. The concept of new product is formed through the transcription of the product genome. The final scheme is developed objectively by using the coefficient variation method and Dempster combination rule. The proposed method is applied in the ex-ante design of a Chinese medicine dispensing machine for its feasibility and effectiveness. [ABSTRACT FROM AUTHOR]

• Interaction feature pair (IFP) is introduced as carriers of interaction intents. • A product information model is established for interaction intent transmission. • Behaviors of cognizing interaction structures are achieved based on IFP matching. • Parts are endowed with the cognition behavior to mate with each other autonomously. Interactions of a part with other parts in an assembly constitute the behavior of the part. However, currently parts interact with each other lifelessly in assembly environment due to their incapability of cognizing interaction structures between them, making the assembly modeling of complex products suffer from considerable manual interventions. An intelligent assembly modeling method is proposed for complex products in this paper, by endowing parts with the ability of cognizing interaction structures between them. In this method, the concept of interaction feature pair (IFP) and the corresponding automatic construction algorithms are developed to explicitly describe interaction intent (i.e., how a part will mate with other parts) in designer's mind, providing carriers for part cognition behaviors and dynamical interaction intent in the assembly modeling process. On this basis, an object-oriented product information model considering IFP is established to facilitate the complete capture of interaction intent at part modeling stage and the consistent transmission of it to assembly modeling stage, endowing parts with the cognition ability of foreseeing how to mate with other parts before and after loading into assembly modeling environment. Then, IFP matching algorithms are designed to support the part cognition behaviors of actively cognizing interaction structures, perceiving potential mating parts and mating with other parts with high efficiency. Assembly modeling case studies of a reducer and a Mecanum wheel with few manual interventions indicate the feasibility of the proposed approach. [ABSTRACT FROM AUTHOR]

Roll forming is a cost-effective, efficient, and flexible plastic processing technique that involves the gradual transverse bending of metal strips using sequentially arranged forming dies. It is an important technological approach in response to lightweight, energy efficiency, and safety in various sectors, including new energy vehicles, aerospace, and rail transportation. However, the complexity of the process, diverse data types, and the effects of coupling and nonlinearity have led to challenges in process stability and quality control. The unclear impact mechanism of heterogeneous time-series data from multiple sources on product quality significantly hinders the development and widespread adoption of roll forming in industries. To facilitate the study of its mechanisms and optimize the control of forming quality, this paper introduces a digital twin (DT) model tailored for the roll forming field. It also presents a product-oriented feature data management framework based on the DT model. This framework facilitates feature-based data categorization across the complete lifecycle, enabling advanced data analysis in the roll forming domain. The feasibility and advantages of the proposed model and framework are validated through application to produce hat-shaped components. It is hoped that the work can provide valuable insights to the digitalization and intelligent transformation of roll forming field. [ABSTRACT FROM AUTHOR]

• Inheritance of organisms is introduced into innovation design. • Computer digital coding technology is introduced into intelligent innovative design process. • Histogram similarity algorithm intelligently identifies functional genes. The inheritance and variation of functional knowledge is an important way to achieve product innovation. Analogous biological genetic inheritance can solve the problems with the inheritance and variation of functional knowledge. However, the different expressions of functional knowledge in different domains lead designers to consuming a lot of time for functional knowledge characterization and identification, which reduces the efficiency of functional knowledge application. Therefore, in order to solve the problem of inefficient application of functional knowledge in the genetic process caused by irregular expression of functional knowledge, the paper proposes a digital characterization and identification process model of functional genes for product intelligent innovative design. The process model enables product intelligent innovative design through digital characterization of functional genes and rapid identification of functional genes using computer assistance. The process model consists of four following steps. First, extract functional knowledge from patents and perform preliminary functional gene characterization. Second, characterize functional genes digitally by using computerized digital coding techniques. Third, identify the required functional genes by using image similarity matching algorithm. It assists designers to quickly identify the functional genes required for the target system. Fourth, obtain the target product design scheme. By "transcribing" and "translating" the required functional genes and using TRIZ tools to solve the translated scheme, the product innovative design scheme is finally obtained. The feasibility and effectiveness of the model are verified by the intelligent innovative design of shared bicycle parking management device. [ABSTRACT FROM AUTHOR]

Urban areas in the US and around the globe are facing increasingly complex resilience challenges. Among the components of the "urban system," transportation networks are among the most critical facilitators that support the lives, interactions, and dynamics of urban dwellers. They are essential to the well-being of the society not only under business-as-usual conditions, but also during times of disaster for the entire response and recovery timeline. This paper introduces CRAFT (Comprehensive Resilience Assessment Framework for Transportation Systems in Urban Areas), which is designed to achieve holistic analyses of transportation disruptions by addressing the many shortcomings and research gaps in this domain. The framework couples a novel structure-specific modeling methodology with a high-fidelity metropolis-scale travel demand model based on real socioeconomic data, and produces results, which, in turn, serve as input for a state-of-the-art socioeconomic impact analysis methodology that is based on computable general equilibrium (CGE) analysis. By the virtues of its data-intensive, model-based, and cross-disciplinary nature, CRAFT aims to capture and incorporate many details that are usually neglected in traditional approaches, and generates resilience insights at 3 levels: (1) system component level (e.g., damages to bridges, tunnels and information on component recovery), (2) system level (e.g., road network disruptions, reconfiguration of traffic and network level functionality) and (3) regional economic level (e.g., impacts on regional GDP, employment, economic resilience). The objective of this paper is to introduce CRAFT and to demonstrate the workings of its first coupling between the hazard and transportation modules through a case study on the Greater Los Angeles Area. [ABSTRACT FROM AUTHOR]

• A digital twin-driven (DTD) framework and model are developed for predicting degraded lifting capacity (LC) of aging tower cranes. • A DTD model predicted the degraded LC of a scaled-down prototype, achieving a mean-square error (MSE) of 0.2253 and a coefficient of determination (R2) of 0.9973. • A DTD model is validated using k-5 cross-validation with a prediction accuracy of 0.97 (R2). • Degraded load charts assist operators in placing safe loads and preventing unexpected failures. Aging tower cranes face an elevated risk of failure, primarily due to structural fatigue and deterioration. Surprisingly, the degradation of aging-induced lifting capacity (LC) remains an unexplored domain. In response to this research gap, this paper introduces a digital twin-driven (DTD) framework and model to predict the degraded LC of aging tower cranes. This framework combines theoretical and numerical analysis of fatigue and degradation behavior in tower cranes with real-time vibration data obtained during cyclic load scenarios on the actual cranes. Machine learning (ML) techniques are employed to develop a model that accurately predicts the degraded LC caused by aging. A scaled-down tower crane prototype is adopted as a demonstrative case to illustrate the feasibility and effectiveness of the DTD framework. The DTD model predicts the degraded LC of the prototype with high accuracy, achieving a mean-square error (MSE) of 0.2253 and a coefficient of determination (R2) of 0.9973. The predicted degraded load charts of the tested tower crane for each decade of usage from 0 to 70 years are also presented to assist crane operators in applying safe loads, preventing unexpected failures and damages, and enhancing workplace monitoring and safety. This study helps monitor the safety conditions of tower cranes that are aging and susceptible to structural fatigue and deterioration, facilitates the prediction of the deterioration of complex machines and systems in the construction industry with real-time data, and highlights the potential of DTD approaches in improving efficiency, safety, and decision-making. [ABSTRACT FROM AUTHOR]

The rapid development of information and communication technologies (ICT) has enabled the prevailing digital transformation (i.e. digitalization), where physical products can be readily digitized in the virtual space and seamlessly interconnected. Meanwhile, industries are ever increasingly adopting service business models (i.e. servitization), so as to offer not only physical products but also services as a solution bundle to meet individual customer needs. Such convergence of both digitalization and servitization (i.e. digital servitization) has triggered an emerging IT-driven business paradigm, smart product-service systems (Smart PSS). As a novel paradigm coined in 2014, to the authors' knowledge, only 2 conference papers have provided some literature review to date, and many issues remain uncovered or not comprehensively investigated. Aiming to fill this gap, this paper has conducted a systematic review of Smart PSS or related papers published ever since its first brought up to date (30/06/2019), and selected 97 representative items together with other 37 supplementary works to summarize the tendency towards Smart PSS, its business and technical aspects, current challenges, and future perspectives. From the survey, it is found that several hybrid concerns are the key challenges faced, and self-adaptiveness with sustainability, advanced IT infrastructure, human-centric perspectives, and circular lifecycle management are the core future perspectives to explore. It is hoped that this work can attract more open discussions and provide useful insights to both academics and industries in their exploration and implementation of Smart PSS. [ABSTRACT FROM AUTHOR]

• A data-model fusion driven design method for modeling of UG systems is proposed. • Digital models of hydrodynamic shape and pressure hull are established. • Mechanism models for rapid accurate performance analysis of UGs are established. • The feasibility and correctness of the data-model fusion method is verified. Underwater glider (UG) is one of the most promising ocean observation platforms, which involves multiple disciplines. Currently, the system design of UGs greatly relies on the time-consuming calculations of high-dimensional multidisciplinary design parameters, which cannot satisfy the requirements of the increasingly diversified ocean observation missions. In this paper, a data-model fusion driven method is established to realize the intelligent rapid response design of UG systems. First, the data involved in system design are collected with multidisciplinary platforms to establish the data models by machine learning, and the mechanism models are established to analyze the motion performance of UG systems. Then, a framework of the data-model fusion driven intelligent rapid response design is proposed based on the data models and mechanism models, and a case study is performed to analyze the motion performance of the UG system designed with the proposed method. Finally, an engineering prototype is designed, assembled, and tested, and a sea trial is carried out to fully verify the data-model fusion driven method. The design method proposed in this paper can greatly shorten the design cycle of UG systems and promote their industrialization development. [ABSTRACT FROM AUTHOR]

[Display omitted] • The progressive damage principle and cohesive contact model were used to simulate the stress field results of composite bolted joints. • The reconstruction of high-fidelity stress field distribution is achieved through the acquisition of a physical interpolation law within the proposed GAN-based model, transitioning from approximate solutions to high-fidelity representations. • Compared with finite element analysis and experimental testing, this proposed method has lower cost and higher efficiency. Predicting the stress fields induced by composite bolted joints constitutes a valuable research endeavor aimed at enhancing the structural integrity of equipment in the aerospace and maritime fields. The stress field characteristics of composite bolted joints may undergo changes due to potential mechanical behaviors, such as damage, constitutive relationships and so on, which exhibit complexity and pose challenges for prediction. Nevertheless, modeling the intricate stress field distribution directly from experimental data poses a formidable challenge, necessitating a substantial investment in materials and resources. Traditional finite element numerical methods have the capability to model the distribution of the stress fields. However, to obtain a high-fidelity solution of this distribution, it is imperative to generate a fine-grid mesh and allocate the significant computational resources. The incorporation of computational techniques in coarse −grid would enhance the efficiency of computations, but these approaches compromise the accuracy of the calculations. In this paper, an innovative deep learning framework is introduced. The network named as the SR-M−GAN is drew inspiration from the conditional generative adversarial network (cGAN) used in the image super-resolution. The primary aim of SR-M−GAN is to mitigate the intrinsic trade-off between result fidelity and computational complexity. The model proposed in this paper effectively reconstructs high-fidelity stress field data from calculations on coarse grids and exhibits excellent reconstruction metrics. Simultaneously, the model only incurs additional computational costs during the deployment of the network model and training. When compared to experimental data, the model continues to demonstrate superior performance in both accuracy and computational efficiency. Therefore, this method offers a high-fidelity data augmentation approach for stress analysis in composite bolted joints, laying the groundwork for large-scale analysis of stress field characteristics in composite bolted joints. [ABSTRACT FROM AUTHOR]

This paper addresses the significant challenge of predicting the Remaining Useful Life (RUL) of mechanical equipment, a critical aspect of predictive maintenance and reliability engineering. Traditional deep learning methods in RUL prediction have been hindered by key challenges, including the scarcity of comprehensive lifecycle data, the prevalence of high-frequency noise in sensor readings, and a heavy reliance on supervised learning. To overcome these challenges, we propose a novel methodology that synergizes self-supervised and supervised learning. Our approach uniquely leverages non-full lifecycle data abundant in industrial settings, thereby bypassing the limitations posed by data scarcity. The model undergoes a two-stage training process, initially learning from vast quantities of non-full lifecycle data in a self-supervised manner, followed by fine-tuning in a supervised phase with available full lifecycle data. We employ Contrastive Predictive Coding (CPC) for the encoder and a Transformer-based decoder, a combination adept at extracting low-frequency, significant features from the sensor data and effectively predicting RUL. The paper demonstrates the efficacy of our approach through comprehensive experiments testing on both bearing datasets from experimental setup and wheelset datasets from urban rail train, showing superior or comparable performance against state-of-the-art methods. Our results, supported by ablation studies, suggest the potential robustness and innovative aspects of our model, indicating it could contribute meaningfully to the field of predictive maintenance. • Novel Hybrid Model: Hybrid model boosts RUL prediction accuracy with self-supervised learning and Transformers. • Uses Non-Full Lifecycle Data: Uses partial lifecycle data for broader time-series insight extraction. • Mitigating High-Frequency Noise: Network focuses on low-frequency features, reducing high-frequency noise. • Superior Performance Across Domains: Model outperforms others in diverse industries, showing great generalization. [ABSTRACT FROM AUTHOR]

The global outbreak of COVID-19 has had a substantial impact on various sectors worldwide, including the economy, healthcare, entertainment, policy formulation, and international relations, with the transportation industry being particularly hard-hit. To curb the widespread transmission of the virus, many regions globally have implemented policies and measures to restrict transportation. These actions not only directly affect the transportation industry but also further impose a severe impact on the economy and societal development of various areas. In this context, the Transportation Revitalization Index (TRI) becomes particularly important. It can evaluate the degree of recovery of city traffic conditions after the pandemic, and accurate prediction of TRI can help governments and decision-makers respond more precisely to the challenges that the pandemic brings to the transportation industry. However, existing research primarily focuses on the direct correlation between TRI change data and COVID-19 pandemic data, without fully considering the dynamic spatial correlation features and time dependency features that affect the nonlinear changes of TRI. In light of the above situation, this study proposes a Deep Spatial-Temporal prediction model based on the Attention Mechanism (DeepST-AM). The DeepST-AM deeply integrates historical TRI data with multivariate pandemic information and uses a spatial–temporal attention mechanism to capture the deep and complex spatial–temporal information of urban data. To more accurately capture the long-term complex features of TRI data, this paper designs a Gaussian temporal convolution model dedicated to TRI data. To validate the effectiveness of DeepST-AM, researchers used real data from 29 core cities in China as samples and compared the performance of DeepST-AM with existing multiple methods on TRI prediction tasks. The experimental results showed that compared to other methods, the DeepST-AM proposed in this paper has a significant advantage in the long-term prediction tasks of TRI in terms of performance evaluation, indicator prediction, etc. In summary, this research provides a more accurate and comprehensive prediction model for the traffic recovery status after the pandemic, hoping to provide strong support for future decisions. [ABSTRACT FROM AUTHOR]

Particle swarm optimization (PSO) is one of the most classical metaheuristic algorithms that has gained significant attention since its inception. It has some inherent advantages, such as easy implementation, rapid convergence, low computational complexity and so on. However, the drawbacks of being prone to local optimization and insufficient diversity cannot be ignored. Therefore, a new multiple adaptive co-evolved particle swarm algorithm (ACEPSO) with adaptive population grouping strategy, pros-cons coevolution mechanism, new co-evolved mechanism and adaptive mutation strategy is proposed in this paper. Firstly, ACEPSO partitions the overall population into two distinct subpopulations: elite population and common population. The size of the subpopulations undergoes variations at different stages. Secondly, the introduced pros-cons coevolution mechanism effectively improves the exploration ability of PSO. Meanwhile, a new co-evolved mechanism is proposed here aiming to enhance population diversity and balance the exploration and exploitation ability. This mechanism can better transfer information between individuals and promote effective collaboration. Finally, an adaptive mutation strategy is introduced. It improves the population diversity and prevents the algorithm from falling into local optimality productively. To validate the outstanding performance of ACEPSO, this paper compares it with various state-of-the-art metaheuristic algorithms as well as their variants on CEC2017 and CEC2022 test sets. The results exhibit that ACEPSO has a standout comprehensive performance. In addition, ACEPSO is utilized to tackle a set of twelve engineering optimization problems as well as 2D robot path planning problems. On all these complex optimisation problems, ACEPSO obtains the relatively best results. All the above results manifest that ACEPSO has great advantages and competitiveness in solving some of the optimization problems. [ABSTRACT FROM AUTHOR]

The high performance precision assembly (HPPA) of complex products such as aerospace, aircraft and high-end machine tool has demanding requirements for assembly accuracy. Achieving the accurate prediction of assembly accuracy for these complex products before assembling is the premise of improving the assembly quality and performance, and also has always been a challenge. Existing assembly accuracy prediction methods focus on acquiring the assembly deviation based on CAD model and manufacturing errors of parts, but rarely involve the multidimensional error coupling of parts and the influencing factors in the assembly process, which inevitably cause a certain gap between the prediction result and the actual condition, affecting the reliability of the prediction result. To address the above problems, this paper presents a digital twin (DT)-driven assembly accuracy prediction method for the HPPA of complex products. Firstly, this paper introduces the methodology overview and proposes an overall framework for DT-driven assembly accuracy prediction. Secondly, three key enabling technologies realizing the DT-driven assembly accuracy prediction, including the construction of part digital twin model, the generation of DT-based assembly process model, and assembly deviation propagation and accuracy analysis are introduced in detail. Finally, an application implementation of a prototype system and a case study involving a simplified satellite structure panel assembly process are used to verify the effectiveness and feasibility of the proposed method. [ABSTRACT FROM AUTHOR]

• This study constructed a multi domain feature dynamic weighted fusion health indicator: DEWMQE. • A new RUL hybrid prediction model, BGTLLM, has been developed. This model describes the non Gaussian, LRD, and multifractal characteristics of the degradation process of mechanical systems. • BGTLLM overcomes the limitations of traditional stochastic process models by using BGRU and transfer learning strategies to replace traditional degradation functions. • The proposed RUL prediction framework is validated using gear degradation data from a heavy truck drive middle bridge test bench and PHM2012 bearing data. The accurate prediction of remaining useful life (RUL) for rotating machinery with gears and bearings at its core plays a crucial role in ensuring equipment's safe operation and preventing catastrophic accidents. Therefore, this paper focuses on the RUL issue of rotating machinery, proposing a novel RUL prediction framework. Initially, leveraging multi-domain feature extraction and self-organizing map (SOM) networks, this paper constructs the dynamic entropy weighted minimum quantization error (DEWMQE) as the initial health indicator (HI). Subsequently, employing windowed inertia smoothing and scale correction mechanisms, this paper filters anomalies in HI, ensuring trend smoothing and scale consistency. Considering the degradation process and characteristics of rotating machinery systems, this study utilizes linear multi-fractional Lévy stable motion (LMLSM) to build a degradation model. Building upon this, to effectively utilize historical data and overcome the shortcomings of random process theory requiring predefined degradation paths, this study further integrates bidirectional gated recurrent units (BGRU) and similarity transfer learning methods to devise the BGTLLM hybrid model, enabling adaptive fitting of the degradation trend. Finally, the Monte Carlo (MC) method is employed to evaluate the uncertainty in RUL prediction. The effectiveness and accuracy of the proposed hybrid prediction model in RUL forecasting are validated using heavy-duty truck axle data and the PHM2012 dataset. [ABSTRACT FROM AUTHOR]

Increasing the generalizability of intelligent diagnostic models amidst data distribution shifts is receiving growing attention. Nevertheless, current domain generalization methods primarily enhance fault diagnosis in variable working conditions or machines. Due to the lack of prior knowledge to determine which features are task-unrelated and which features are task-related, existing methods typically learn coupled features. Facing industrial diagnosis scenarios across bearings and artificial-to-real faults, coupled features induce false correlations that limit the model's generalizability. To address this challenge, this paper proposes a decoupled interpretable robust domain generalization network (DIRNet) to enhance model generalizability by interpretably transferring fault-related components. First, this paper constructs a neural basis function decoupling module to disentangle the signal into fault-related and fault-unrelated basis functions. Second, a dynamic Shapley pruning network is proposed to dynamically prune the fault-unrelated neural basis functions, achieving the generalization of fault-related basis functions. Third, we introduce a loss function that relies on interpretable basis function selection to enhance the expressive capability of the basis function decoupling module. Experiments on a self-collected industrial distributed fault bearing case and two laboratory cases are carried out. The results demonstrate that DIRNet can obtain generalizable fault-related components to effectively deal with industrial across bearings and artificial-to-real fault diagnosis scenarios compared to the previous methods. [ABSTRACT FROM AUTHOR]

One of the most significant sources of information from customers is customer complaints. Successful and effective complaint management can end complaint crises and ensure client loyalty, which is a sign of great service performance. In this paper, we proposed a novel customer temperament-centered and e-CCH system-based data collection and data mining method titled "3D" model for customer complaint data analysis. Three phases are (1) Development and launch of e-Customer Complaint Handling system, (2) Data collection and transfer of learning by e-Customer Complaint Handling system, and (3) Data mining by e-Customer Complaint Handling system. An advanced e lectronic C ustomer C omplaint H andling System called the e-CCH system was then developed and launched. This system adapts the seasonal associations model based on Hippocrates's customer temperament theory to the whole stages of customer complaint reporting and handling. With this system, we conducted a dataset collection work from restaurant chains of two brands over four years. As a result, we collect thousands of real-world temperament-centred customer complaint cases by four years to form the one-of-a-kind CCH dataset. This one-of-a-kind CCH dataset was open-sourced with detailed customer complaint attributes and heuristic decision-making for valuable industrial handling manner. After further analysis of this dataset, we found that customers with different temperament types tend to have different types of complaints. In addition, adapting the temperament theory to the e-CCH system can classify customer types better and provide personalized solutions. To our best knowledge, this rich and the one-of-a-kind CCH dataset reported in this paper is the first comprehensive study of customer complaint handling in an industrial service management context. Meanwhile, data mining with cross analysis and correspondence analysis and an ChatGPT experiment for transfer of learning based on this yearly and one-of-a-kind industrial customer complaint dataset was analyzed and discussed. In addition, how this dataset may contribute to more realistic complaint-handling theoretic studies for better service failure recovery and interactive marketing is discussed in-depth. [ABSTRACT FROM AUTHOR]

• This paper proposes an online fault diagnosis method for rotating machinery. • A novel multi-level information fusion method is proposed for multi-sensor signals. • Sample and class incremental learning capability are developed for rapid updates. • Two datasets of key components are employed to validate the superiority. Intelligent Fault Diagnosis (IFD) models are all trained in one-time learning way, lacking the incremental learning capability for continually incoming samples and newly occurring faults. Although Online Fault Diagnosis (OFD) models with incremental learning capability have begun to attract sustaining attention and extensive research, they are just suitable for a single-sensor signal, limiting their diagnostic performance on machinery operating under complex environment. To solve these problems, this paper proposes a multi-sensor fused incremental broad learning with D-S theory for online fault diagnosis of rotating machinery. Firstly, a feature fusion method based on mutual attention mechanism is designed to sufficiently explore the similarity relationship of the multi-sensor data after fast Fourier transform (FFT). After that, the fused feature matrices are inputted to broad learning system for training and the outputs are fused based on D-S evidence theory, achieving multi-level information fusion to ensure adequate fusion of the multi-sensor signals. Additionally, the sample and class incremental learning are developed to rapidly update subsequent models without retraining. Finally, two experiment datasets concerning the key components of rotating machinery are employed to verify the effectiveness and superiority of the proposed method. Benefiting from the advantages of sample incremental learning, the model can be updated in approximately 6 s and 0.15 s, respectively, which is less than the initial model. Meanwhile, the testing accuracy of subsequent models is still maintained at 100% as more and more samples are employed for model updates. Besides, it can be updated in 13 s and 1 s respectively to accommodate new faults, while still has excellent accuracy after fusion. Consequently, the proposed method is an effective online fault diagnosis method because it represents significant advantages in reducing time consumption and improving the accuracy and reliability of diagnostic results. [ABSTRACT FROM AUTHOR]

Manufacturing systems envisioned for factories of the future will promote human-centricity for close collaboration in a shared working environment towards better overall productivity within the context of Industry 5.0. Robust and accurate recognition and prediction of human intentions are crucial to reliable and safe collaborative operations between humans and robots. For this purpose, this paper proposed a safety-aware human-centric collaborative assembly approach driven by function blocks, human action recognition for intention detection, and collision avoidance for safe robot control. Within the context, a deep learning-based recognition system is developed for high-accuracy human intention recognition and prediction, and an assembly feature-based approach driven by function blocks is presented for assembly execution and control. Thus, assembly features and human behaviours during assembly are formulated to support safe assembly actions. Skeleton-based human behaviours are defined as control inputs to an adaptive safety-aware scheme. The scheme includes collaborative and parallel mode-based pre-warning and obstacle avoidance approaches for a human-centric collaborative assembly system. The former is to monitor and regulate robot control modes when working in parallel with humans, and the latter uses a position-based approach to control robot actions by adaptively adjusting obstacle avoidance trajectories in a dynamic collaborative environment. The findings of this paper reveal the effectiveness of the developed system, as experimentally validated through an engine-assembly case study. [ABSTRACT FROM AUTHOR]

With the promotion of emerging technologies in the era of big data, there has been a diversification in user participation in product requirement development. This has resulted in many complex, diverse, and rapidly iterated user requirements, greatly reducing the applicability of traditional requirement development methods. In this paper, to address the complex and ever-changing relationships among users, requirements, products, and requirement development teams in the product development process, a multilayer dynamic heterogeneous network node influence analysis method is constructed for product requirement development. This method establishes a product requirement development framework based on a multilayer dynamic heterogeneous network consisting of a user layer, requirement layer, component layer, and expert layer in terms of three dimensions: requirement development, requirement evaluation, and time. Based on this framework, indicators such as comprehensive node significance, layer significance, and node influence are designed. To address the issues encountered in small sample data testing, three measurement models are further designed in this paper, effectively improving the sampling efficiency of the multilayer dynamic heterogeneous network. Additionally, calculation models for the comprehensive node influence and comprehensive node influence variation rate are improved and constructed, and corresponding algorithms are designed. This method is applied in an experimental study of product requirement development for new energy vehicles, providing high-quality recommendations for new energy vehicle requirement developers, including functional requirements and product components that need close and timely attention. Moreover, accuracy tests show that the proposed algorithm achieves an average accuracy rate of 0.8611, which is significantly higher than those of other network node centrality measurement methods. This demonstrates the advanced nature and applicability of the proposed method in the field of product requirement development, providing a new way for requirement developers to improve work efficiency. [ABSTRACT FROM AUTHOR]

In this paper, we address the following question: How can self-organizing system designers steer the system towards expected global behaviors that satisfy multiple conflicting performance indicators? Self-organizing systems (SOS) have advantages in performing tasks in exploratory and hazardous domains that are not suitable for humans. The design of the SOS is however difficult because negative emergence with unwanted behaviors is likely to happen and multiple conflicting performance indicators need to be considered. To address this challenge, in this paper, we propose an SOS design method using surrogate models and the compromise Decision Support Problem (cDSP) construct. Surrogate models are used to capture the relationship between low-level rules or parameters and high-level emerging system performance. And the cDSP construct is used to explore "good enough" solutions (characterized by rule adoption rates) while managing the trade-offs among conflicting performance indicators. The efficacy of the proposed method is illustrated using a multi-agent box-pushing problem in the Webots simulation environment. It is shown in the results that our method leads to a 6.9% improvement in time efficiency, an 8.4% improvement in energy efficiency, and 26.2% in system reliability. [ABSTRACT FROM AUTHOR]

In online markets, consumers rely on reputation systems to make purchases decisions. However, traditional accumulative-score type online reputation systems bring disadvantages to new sellers since they do not have sufficient transactions. In this paper, we investigate how do consumer decision making as well as seller competition change after introducing buyer protection mechanisms, such as escrow services and money-back guarantee. Do consumers rely less on online reputation systems after launching buyer protection mechanisms? Does introducing buyer protection mechanisms alleviate the competition pressure among sellers? Does a new seller benefit more than an existing seller? This paper proposes a theoretical model to discuss how online reputation systems affect sellers and consumers in the presence of buyer protection mechanisms. Contrary to the conventional wisdom that buyer protection mechanisms enhance buyer experiences and give low-reputation sellers advantages, we find that such scenarios occur only in the short term. In the long run, consumers rely more on online reputation systems as the effectiveness of buyer protection mechanisms increase. Both consumers and low-reputation sellers can be worse off. We also empirically assess these theoretical predictions. [ABSTRACT FROM AUTHOR]

Effective safety management significantly influences the success of construction projects. Comprehensive standards are developed to ensure a fundamental safety level. However, improving the standard system requires an effective evaluation method to assess its coverage of construction risks. This challenge arises due to the intricate relationships between risks and standards. Addressing this issue, this paper introduces a dual-layer network analytical framework for evaluating standard systems in construction safety management. By utilizing various property metrics and four dedicated node metrics, the framework allows quantifying the extent to which a standard system addresses project-specific risk factors. The efficacy of the analytical framework is validated through a case study, revealing that the management mechanism of a standard system primarily manifests in the overall management of specific risks and associated risks with triggering relationships. It is observed that key standards often encompass a wider array of risks. Based on the findings, this paper offers suggestions for revising construction standards. [ABSTRACT FROM AUTHOR]

The proliferation of high-immersion technologies might change the way virtual prototypes are used in the design process. This paper investigates the effect of immersion on reviews – critical design situations where many decisions are made. More specifically, the paper analyses the effect of immersion on spatial (intrinsic or extrinsic) and design space (problem or solution) aspects of the review. The effects have been tested in an experimental study comparing low- (computer screen) and high- (head-mounted display) immersion collaborative virtual environments (CVEs). In the experiment, four-member distributed teams conducted early-phase reviews with virtual prototypes represented in one of the two environments. Results show that the high-immersion CVE did not significantly affect the number of feedback items. Next, there was a non-significant but medium effect on the number of extrinsic feedback items, i.e., items that consider relations between the design and surroundings (e.g., users, environment). Finally, there was a significantly higher number and proportion of problem-related feedback items. Therefore, a high-immersion CVE might be more suitable if designers would like to get more problem-related or extrinsic feedback – essential aspects for the early design phases. These findings suggest that low-immersion and high-immersion CVEs are not substitutable but rather complementary technologies. [ABSTRACT FROM AUTHOR]

The digital twin (DT) represents a powerful tool for advancing construction industry to provide a cyber–physical integration that enables real-time monitoring of assets and activities and facilitates decision-making. Due to the inherent characteristics of the construction industry and the diverse possibilities with DT, proliferation of building digital twin (BDT) necessitates a comprehensive comprehension of its evolution and the creation of roadmaps. This paper aims to contribute to the formalization and standardization of BDT. It designs a novel assessment framework for the overall maturity measurement of existing BDT projects. The developed BDT maturity model incorporates a collective opinion generation paradigm based on a fairness-aware multiobjective optimization model to provide an expert-based evaluation system for evaluating the maturity of BDT projects. The effectiveness and feasibility of the proposed framework have been validated through a case study of an experimental BDT initiative. This paper establishes a generalizable framework for BDT maturity assessment that can offer insights into BDT maturity standards to construction practitioners to create effective strategies for the diffusion, development, and maturation of BDT. [ABSTRACT FROM AUTHOR]

It is well accepted that domain ontologies can support requirement analysis activities, particularly in detecting inconsistencies and incompleteness of requirement models. These benefits critically depend on the provision of a suitable ontology. We observe the context of supporting requirement analysis provides both opportunities and restrictions when choosing the most appropriate ontology retrieval mechanisms. Requirement models are the basis for retrieving the most influential ontologies and are not the typical retrieval domain ontologies. For instance, a retrieval ontology derived from the requirement is not expected only to be a hierarchical taxonomy, nor is it limited to the boundaries of a single domain, nor does it cover any particular domain completely. Hence, retrieval methods cannot be based on classes only and computational constraints do not necessarily apply as the retrieval process is expected to run only once at the outset of the analysis phase. It is also important to assume that the retrieval in this context is targeting multiple ontologies describing multiple but related domains. In this paper, we deduce that avoiding structural based retrieval mechanisms in fact benefits to the requirement models. Instead, we formulate a new retrieval method based on the PageRank algorithm that takes into account the indirect influences of various concepts within plausible supporting ontologies. This paper provides an empirical analysis that evidences the strength of our retrieval algorithm in supporting the identification of ontologies to support requirement analysis. [ABSTRACT FROM AUTHOR]

The paper proposes a deep learning-based multi-object real-time detection model for concrete cracks and structural deformations. The model improves the single-stage object detection framework, You Only Look Once version 7 (YOLOv7), by incorporating convolutional block attention mechanisms and global attention mechanisms into its backbone and neck networks, respectively. It also establishes dual output branches for cracks and deformations within the output module to enable multi-object detection capabilities. Utilizing transfer learning strategies, the model effectively detects concrete cracks and structural deformations with a limited dataset. The results demonstrate that the improved YOLOv7 model significantly improves the detection of non-continuous cracks and reduces noise in complex environments, indicating strong generalization and robustness. The improved model exhibits a 4.53% increase in crack detection accuracy over the original and achieves low peak relative errors for deflection deformation in concrete beams and in-plane deformation in concrete slabs at just 0.22% and 3.05%, respectively. [ABSTRACT FROM AUTHOR]

• An efficient data-driven structure with scalable time sequences and kernel sizes is developed. • A novel model-based regression model is formulated to provide adjustable capabilities. • A hybrid PHM framework that integrates data-driven RUL and model-based TTF is proposed. • We comprehensively improve hybrid PHM frameworks to adapt to various system hierarchies. With the rapid development of sensor technology and mechatronics integration, there are emerging demands for achieving prognostic and health management (PHM) within a general framework across multi-level engineering systems. However, current PHM frameworks are mainly supported either by field data or degradation models, which are always limited in inadequate robustness to systematically increase operational availability and reduce maintenance costs. For extending the scalability and flexibility of PHM services, this paper proposes a novel hybrid framework that integrates the scalable convolution neural network (SCNN) with the adjustable functional regression model (AFRM) through a modified linear filter. This proposed framework first establishes a data-driven SCNN with scalable time sequences and kernel sizes to enhance the remaining useful life (RUL) generalization. Then, enabled by an adjustable semi-parametric degradation process model, AFRM with flexible lifetime distributions is designed to evaluate time-to-failure (TTF) in real time. Finally, a modified Kalman filter has been explored to coordinate data-driven RUL results with model-based TTF values to schedule predictive maintenance (PdM). High-accuracy prediction, multi-level systems, high-flexibility evaluation are thus encompassed within the hybrid progressive modification. The proposed framework has been practically validated through multi-level studies including the component-level bearings, subsystem-level engines, and system-level machines. Results demonstrate that our hybrid PHM framework achieves significant improvements in prediction accuracy, evaluation adaptability, and scheduling effectiveness. [ABSTRACT FROM AUTHOR]

Digital Engineering (DE) must be able to maximize efficiency and update dynamically in order to keep up with the wave of global interconnection. The evolution of the Digital Twin (DT) plays a significant role in DE as it enables autonomous optimization and an iterative cycle. However, the intricacy of real-world settings renders conventional evolutionary investigations of a solitary DT inadequate in tackling intricate systems at a comprehensive lifecycle magnitude. To address this, this paper presents the Co-evolutionary DTs (CoEDT), which has several key characteristics. (1) CoEDT study the evolutionary behavior of interconnected multi-DT. (2) CoEDT use a co-evolutionary distributed system architecture and is a DT technology that integrate MBSE. (3) CoEDT offers detailed dynamic models for the complex interactions and co-evolution among multi-DT throughout the lifecycle. It also supports real time measurement of multi-DT behavior to detect system anomalies. The significance of CoEDT lies in providing a more comprehensive insight for future product development by constructing a parallel world that simulates the lifecycle. In the CoEDT, we tackle the behavioral identification and structure of these evolving multi-DT throughout product lifecycle through the following approaches. Initially, drawing inspiration from biological cytology, we have conceived a concept of Collective DTs (CollDTs) to observing a collective behavioral of multi-DT. Subsequently, we further developed CoEDT to depict co-evolutionary behavior patterns and established a co-evolution architecture for all DT throughout the lifecycle by fusing Model-Based Systems Engineering (MBSE). Then, dynamic expressions and algorithm that can measure the co-evolution of every DT are inferred using information theory. Finally, the viability of the proposed CoEDT framework is demonstrated through the development of a solid rocket engine, which promotes the application of DT in the DE. [ABSTRACT FROM AUTHOR]

• Organizing a data matrix of PCI, RDI, RQI, and SRI from highway network in Guizhou. • Forming the method of establishing a multi-output neural network prediction model. • Establishing a LSTM model of network-level semi-rigid asphalt pavement performance. • Combining the Bayesian optimization algorithm to optimize the hyperparameters. • Adopting SHAP to conduct post-hoc causal analysis through set-valued mapping. With the dense and huge highway network in China, the highway maintenance management system has become the most concerned issue for Chinese highway managers in recent years. Therefore, based on the highway network in Guizhou Province of China, this paper established the semi-rigid asphalt pavement performance multi-output Long Short-Term Memory (LSTM) prediction model with regional applicability, including Pavement Surface Condition Index (PCI), Pavement Rutting Depth Index (RDI), Pavement Riding Quality Index (RQI) and Pavement Skidding Resistance Index (SRI) and the hyperparameters of the model were optimized by Bayesian optimization algorithm and the casual analysis of the model was conducted based on SHapley Additive exPlanations (SHAP), providing a reference for China's highway network-level preventive maintenance decision-making. The results prove that the established model can effectively predict the performance of the following year through the data of the previous two years. The established model has a better comprehensive prediction effect in comparison to similar multi-output models. The average coefficient of determination (R2) of the four prediction indexes can reach 0.823. Besides, the prediction effect among the indexes is stable and multiple pavement performance indexes can be effectively and reliably predicted at the same time. In addition, the contribution of input feature variables to output is quantified based on SHAP. According to quantified the contribution, the association relationship of the neural network model is set-valued mapped to the causality relationship in the post hoc. The input feature variables with the main contribution are extracted for causal analysis. The causal analysis shows that the degradation of the four pavement performances all have obvious time memory characteristics and have significant differences, but their pavement performance degradation is the result of nonlinear changes caused by the coupling effects of traffic load, road age, climate, and pavement structure. [ABSTRACT FROM AUTHOR]

Learning building information modeling (BIM) systems has always been a challenge for BIM adoption. Although groundbreaking performances of large language models (LLMs) have inspired many researchers to consider an LLM as a potential BIM control method using natural language, a specific method of utilizing LLMs for automated BIM model detailing has not yet been proposed. This paper proposes an LLM-BIM chaining framework to enable architectural design detailing using natural language, instead of using menu-based user interfaces, named "Natural-language-based Architectural Detailing through Interaction with AI (NADIA)". The NADIA framework is based on three main approaches: 1) separating the specification of the wall layers from the creation of the wall layers; 2) appropriate instruction prompting to guide the LLM to minimize irrational responses and produce engineering rational details; and 3) LLM-BIM chaining to seamlessly link a BIM authoring tool and an LLM. The effectiveness of NADIA was validated based on two main aspects: its accuracy in generating details that adhere to specified design requirements from users—as a design assistant—and its compliance with general engineering requirements—as a design consultant. The validation was achieved through tasks that involved generating 240 and 1,920 exterior wall details, respectively. NADIA achieved an average accuracy of 83.33% in generating logically coherent details in line with the required design conditions. For thermal performance requirements, it demonstrated a mean accuracy of 98.54% in complying with the American Society of Heating, Refrigerating, and Air-Conditioning Engineers (ASHRAE) 20.1–2019 standard. Despite being in its early stages, NADIA's potential for developing and refining architectural details through natural language-based interactions between architects and machines is promising. [ABSTRACT FROM AUTHOR]

Deep learning-based methods demonstrate acceptable performance on few-sample surface defect recognition, which is a pivotal instrument for quality control in intelligent manufacturing systems. However, deep learning models often experience overfitting to the limited training data and struggle with generalizing to unseen test data due to the discrepancy between the feature distributions. Moreover, the high intra-class variation of defect samples makes it challenging to extract discriminative features. To address the issue of few-sample defect recognition, this paper proposes an Adaptive Classifier with Attention-wise Transformation (ACAT). Firstly, a novel Adaptive Attention Transformation is proposed to integrate into the transformer encoder module for augmenting features which improve the generalization ability. Secondly, a novel Adaptive Classifier is proposed to reduce intra-class variation for obtaining discriminative features. The effectiveness of the proposed ACAT method in addressing the challenge of recognizing defects with few-sample is demonstrated through experimentation on publicly defect datasets X-SDD and GC10, as well as real-world engineering datasets containing printed circuit board (PCB) defects obtained from operational manufacturing facilities. The proposed ACAT method enhances accuracies of 2.82%, 6.15%, and 9.89% contrasted with the most successful method on the X-SDD, GC10, and PCB datasets, respectively, using only five samples per class for training. [ABSTRACT FROM AUTHOR]

In recent years, electroencephalography (EEG) emotion recognition has achieved excellent progress. However, the applied shallow convolutional neural networks (CNNs) cannot characterize the spatial relations between different features well, which affects the performance of these models. In addition, because the amount of EEG sample data is small, it is challenging to collect and annotate enough EEG signals for emotion recognition. Extracting more distinguishing features from small sample data is one of the problems faced by EEG emotion recognition. To solve these problems, this paper proposes a light-weight residual convolution-based capsule network (LResCapsule) for EEG emotion recognition. The LResCapsule consists of a Light-ResNet based feature extractor and a capsule-based classifier. Because of the low EEG training data, we propose a low-parameter Light-ResNet to automatically extract deep emotion features from the raw EEG signal. Then the Capsule-based classifier is applied to identify the positional relations between local features and global features in the spatial domain, which can further improve the performance of EEG emotion recognition. Compared with ResNet18, the number of parameters of our proposed Light-ResNet is reduced by 84.5%. The experimental results on the DEAP and DREAMER datasets show that the proposed LResCapsule can outperform state-of-the-art methods in both subject-dependent and subject-independent experiments. [ABSTRACT FROM AUTHOR]

Data-driven fault diagnosis techniques for rotating machinery have exhibited highly promising results. However, these methods heavily rely on sufficient faulty data and presuppose that the source (model training) and target domains (model diagnosis) share a matching data distribution. In practical industrial settings, acquiring target domain data can be quite challenging, and the distribution between the source and target domains is expected to differ due to various working condition of mechanical equipment. In order to surmount these challenges and address state monitoring under unknown working conditions, this paper presents a novel fault diagnosis method designed for rotating machinery in the absence of target domain data. Firstly, this method involves constructing local fault state semantic attributes using source samples from limited known working conditions of the rotating equipment. Secondly, a dual embedding module is employed to map the relation between fault features and fault state semantic attributes in a high-dimensional embedding space. Thirdly, an improved loss function is designed to optimize the dual embedding module by balancing inter-class and out-of-class distances of fault samples. Finally, to prevent overfitting result from limited known working conditions, samples of an additional third working condition are introduced during the training of the dual embedding module. Experimental evaluations conducted on two bearing datasets and an automobile transmission fault dataset from First Auto Work demonstrate the effectiveness of the proposed method in accurately identifying faults under unknown working condition. The fault diagnosis recognition accuracy under unknown working conditions exceeds 99.2%, 96.1% and 88.2%, and the proposed approach can effectively address the issue of diagnosing with no target domain data in engineering problems. [ABSTRACT FROM AUTHOR]

Nowadays offline transfer learning (TL) is the mainstream research for cross-domain machinery fault diagnosis (MFD). However, the target data is usually collected online by edge devices in real-world applications, causing practicality issue of offline TL. To address this issue, a new and practical online TL scenario test-time adaptation (TTA) is considered in this paper. In TTA, the labeled source data is inaccessible for privacy, and only a pre-trained source model is provided for online model adaptation with the online unlabeled target data. To enable TTA for MFD, a dynamic data division strategy is proposed to divide each mini-batch of the online target data into the certain-aware and uncertain-aware sets based on the spectral entropy and prediction confidence for the subsequent fine-grained online model adaptation. Delving into underlying data properties, a customized contrastive learning (CL) framework is proposed, consisting of specifically designed CL strategies for the different divided sets, respectively. Specifically, prototypical CL based on the representative class-wise prototypes is proposed to boost the feature discriminability of certain-aware set, while neighborhood CL based on the local neighborhood structure is proposed to refine the numerous noise of uncertain-aware set. Meanwhile, smooth entropy minimization is devised for reliable model uncertainty reduction. The cloud-edge TTA implementation framework is further considered in the scenario of cloud manufacturing and edge computing for practical real-world applications. Specifically, the pre-trained source model is directly deployed from cloud to edge for local TTA. A simple source model pruning strategy is proposed to obtain the lightweight pre-trained source model for efficient deployment on resource-limited edge devices. Practical experiments on two edge devices Raspberry Pi and NVIDIA Jetson Nano verify the effectiveness and efficiency. [ABSTRACT FROM AUTHOR]

The emergence of "Digital Twin" has raised higher demands for the health management of industrial equipment. Sliding bearings, as crucial supporting components in rotating machinery, may wear under radial loads, posing potential risks to the safety and stability of the system. However, The wear profile is usually challenging to measure online, making it difficult to present the real-time wear status of the bearing. To address this issue, this paper proposes a novel framework of digital twin by combining physics-driven with data-driven model in parallel. Within this framework, we establish a parallel hybrid model of finite element and deep neural network (PFENN), used for monitoring and visualizing the real-time wear profile of sliding bearing. In the offline phase, PFENN gets the wear profile through numerical calculations of finite element model and constructs the space of bearing wear states; during the online phase, PFENN captures the bearing's vibration signal and obtains the maximum wear depth through deep neural network. Subsequently, mapping the wear profile in the wear data space based on the maximum wear depth and visually presenting. Additionally, we employ relevance vector regression with a sliding window to fit the bearing degradation curve for predicting the remaining useful life. Experimental validation confirmed PFENN's 93% profile accuracy and the capability for real-time monitoring and prediction, meeting the demands for high-fidelity digital twinning and real-time performance. This research also introduces new methodologies and perspectives for industrial equipment health management. [ABSTRACT FROM AUTHOR]

Computational form-finding methods hold great potential concerning resource-efficient structural design. The Combinatorial Equilibrium Modeling (CEM), an equilibrium-based form-finding method based on graphic statics and graph theory, allows the design of cross-typological tension–compression structures starting from an input topology diagram in the form of a graph. This paper presents a novel Logic-Informed Graph Neural Network (LIGNN) that integrates the validity conditions of CEM topology diagrams into the learning process through semantic loss terms. A Primary-LIGNN (P-LIGNN) and a Modification-LIGNN (M-LIGNN) are introduced and incorporated together with the CEM into a general form-finding-based computational structural design workflow that transforms input topologies into parametric models of equilibrium structures. An implementation of this computational design workflow for the conceptual design of pedestrian bridge structures is made, and presented through a case study, for which a synthetic training dataset of topology diagrams for the LIGNNs has been developed. [Display omitted] • Logic-Informed Graph Neural Networks (LIGNN) implementing discrete logic-based rules • New synthetic dataset of graphs for Combinatorial Equilibrium Modeling (CEM) • Semantic loss function formalizing the CEM validity conditions for graph labeling • Machine Learning-assisted design workflow based on Structural Form-Finding • Case study of a human–machine collaborative design of a pedestrian bridge structure [ABSTRACT FROM AUTHOR]

• A collision detection strategy is developed for lift path planning in modular construction. • An optimized octree with a fast encoding method is built to divide the lifting space. • A novel AABB and OBB integrated method is developed for collision detection. • An adaptive variable-step strategy is proposed to ensure continuous collision detection. • The developed algorithm reduces planning time by about 95 % while ensuring accuracy. Crane-lift path planning (CLPP) ensures the safe and efficient installation of hefty modules in high-rise modular integrated construction (MiC). The implementation of CLPP requires effective collision detection strategies. However, existing collision detection strategies suffer from limitations in terms of computational intensity or insufficient accuracy. This paper aims to develop a fast and accurate collision detection strategy for CLPP in high-rise MiC projects using a single tower crane, thereby achieving safe and efficient module installation. It is executed with the assumptions that the geometry of the building remains unchanged, the positions and orientations of the lifted module and the tower crane are monitored, and no external loads act on the lifted module. Based on the research scope and assumptions, an octree and bounding box (Oct-Box) integrated strategy is developed. The strategy operates in two stages, the pre-execution and execution stages, supported by two critical technical components: (1) an optimized octree for lifting space division and encoding, and (2) an integrated bounding box algorithm for construction object collision detection. The strategy was evaluated using a real-life MiC project in Hong Kong. The results show that the developed strategy minimized the CLPP time by about 95 %, while ensuring continuous and accurate collision detection. In addition, the strategy was significantly affected by the depth of octree, the encoding method of octree, the bounding box algorithm and the configuration density. The developed Oct-Box strategy for CLPP is novel as it addresses temporal efficiency and spatial tightness in tandem, and marks a breakthrough for collision detection in modular construction. [ABSTRACT FROM AUTHOR]

• The mapping mechanism between medial axis transform (MAT) and NC machining is established to reveal the association between geometry and NC process. • Deeper NC process information hidden in 3D CAD models is mined to reflect the NC machining procedure practically. • A multi-objective optimization model considering both material removal amount and cutting consistency is constructed. • A hybrid ant colony algorithm (ACA) and simulated annealing (SA) approach is presented to search the Candidate Tools Graph (CTG) to obtain the optimal roughing tool sequence automatically. The appropriate and intelligent selection of roughing tool sequence for pocket features is essential to improve the efficiency of NC machining. However, there exist few researches exploring how to discover and utilize the valuable NC process information imbedded in 3D CAD models. In this paper, a NC process information mining based optimization method of roughing tool sequence selection for pocket features is presented. Firstly, the medial axis transform (MAT) is introduced to represent the tool paths of a pocket feature, and corresponding parameters of MAT are calculated. Secondly, considering the restrictions of tool movements during machining, the mapping mechanism between geometry and NC process is elaborated based on MAT to reveal the association of 3D CAD models and NC machining. The deeper information for NC process planning is mined to reflect the machining procedure feasibly. Then, the multi-objective optimization model is constructed by considering material removal amount and cutting consistency synthetically. Moreover, the precedence and distances between roughing tools are formulated in a Candidate Tools Graph (CTG). Finally, a hybrid ant colony algorithm (ACA) and simulated annealing (SA) approach based on CTG is proposed to generate the global optimal roughing tool sequence. In the experiment, various pocket features are conducted to illustrate the application effectiveness of the proposed method. The experimental results show that our method can achieve highly satisfactory results and outperforms other approaches. [ABSTRACT FROM AUTHOR]

Flex-route transit (FRT) service has become increasingly popular in low-density suburban areas as a shared transportation mode. Improving the service quality of FRT heavily relies on effective routing plans. To end of this, this paper addresses the FRT routing plan problem considering heterogeneous requests and time windows (FRTRPP-HRTW), which is formulated as a mixed-integer programming (MIP) model. The MIP model concerns on the objective of minimizing the average system costs. Due to the NP-hard nature of the considering problem, a niche-based modified ant colony optimization (NM-ACO) algorithm is developed to handle it efficiently for large-scale cases. In NM-ACO, a niche-based pheromone update technology is designed to increase the population diversity. Finally, as a case study, a real-world FRT service is employed to validate the effectiveness of NM-ACO. Computational results demonstrate that the NM-ACO can obtain high-quality solutions with small gap in much shorter time compared with the mature solver (i.e. CPLEX). Furthermore, compared with the well-known MMAS algorithm and a state-of-art ACO-DI algorithm, the NM-ACO expresses higher precision and stronger robustness. [ABSTRACT FROM AUTHOR]

Classification and size quantification of defects on both the internal and external surfaces of pipelines are critical to pipeline integrity assessment. However, defect classification is challenging because of the similarities of defect signals on the internal and external surfaces. In addition, most existing size quantification methods are not sufficiently accurate. To solve these problems, this paper proposes a classification and quantitative evaluation method based on an asymmetric student–teacher with a classifier network (ASTC-Net). First, a novel approach for expanding defect magnetic flux leakage (MFL) data is validated through experiments and simulations. Second, ASTC-Net is built to address the problem of defect classification and quantification. Finally, the superiority of the method is verified by experiments. The results show that this approach pioneers the accurate classification of defects on both internal and external surfaces by achieving an accuracy of 99.41%. Furthermore, a high-precision quantitative assessment of defect size is realized, with length, width, and depth errors of only 0.35 mm, 0.34 mm, and 0.41% of the wall thickness, respectively. These experimental results clearly demonstrate that this method has exceptionally high accuracy in defect classification and quantification, offering vast prospects for its application in pipeline MFL evaluation. [ABSTRACT FROM AUTHOR]

This paper introduces a novel group single-criteria decision-making algorithm that addresses the challenges from personal biases. The algorithm utilizes offset centroid-driven weight adaptation to enhance the fairness and reliability of decisions, providing robust decision-making. The core steps of the new algorithm include splitting the evaluation dataset, calculating the offset centroid, introducing dynamic adjustment coefficients, constructing a comparison matrix, and calculating the weighted mean. To empirically validate the effectiveness and applicability of the proposed algorithm, we conducted a case study involving five appearance design alternatives for automotive steering wheels, and the numerical results demonstrate the algorithm's substantial improvements on group decision-making outcomes. Remarkably, the algorithm not only facilitates the flourishing of a fair decision-making environment but also can effectively handles biased decision-making scenarios and mitigate the impact of unfairness. By utilizing this algorithm, decision-makers can alleviate individual biases and enable fairer and more reliable decision-making processes. Consequently, this algorithm introduces a novel approach for tackling complex decision problems and exhibits promising prospects for practical applications. Its versatility renders it highly valuable in diverse decision-making processes, empowering decision-makers to achieve fairness and precision in their choices. • A novel decision-making algorithm is proposed to mitigate individual biases. • Offset centroid-driven weight adaptation stands at the core of the algorithm. • A case study verifies the proposed algorithm in both fair and unfair environments. [ABSTRACT FROM AUTHOR]

Human-Cyber-Physical Systems (HCPS), as an emerging paradigm centered around humans, provide a promising direction for the advancement of various domains, such as intelligent manufacturing and aerospace. In contrast to Cyber-Physical Systems (CPS), the development of HCPS emphasizes the expansion of human capabilities. Humans no longer solely function as operators or agents working in collaboration with computers and machines but extend their roles to include system design and innovation management. This paper proposes a Multisensory Interaction Framework for HCPS (MS-HCPS) that leverages human senses to facilitate system creation and management. Additionally, the introduced Multisensory Graph Convolutional Network (MS-GCN) model calculates recommendation values for multiple senses, elucidating their relevance to system development. Furthermore, the effectiveness of the proposed framework and model is validated through three practical engineering scenarios. This study explores the research on multisensory interaction in HCPS from a human sensory perspective, aiming to facilitate the progress and development of HCPS across various domains. [ABSTRACT FROM AUTHOR]

• Creation of a parameterized circular intuitionistic fuzzy (C-IF) scoring mechanism. • Rational C-IF scoring outcomes through the proposed parameterized scoring rule. • Allowing customization of parameters to align with decision-makers' preferences. • C-IF assignment modeling through the parameterized C-IF scoring framework. • Demonstrating its advantages through practical applications and comparative study. The notion of circular intuitionistic fuzzy (C-IF) sets, which utilizes a malleable circle to depict uncertainties and encompasses membership and non-membership constituents at its core, constitutes a progressive advancement of standard intuitionistic fuzzy sets. This paper concerns the utilization of a C-IF assignment model along with a parameterized scoring rule for a methodology involving multiple criteria assessment. This study introduces a novel parameterized C-IF scoring function, addressing limitations in current scoring methodologies. The newly proposed scoring function incorporates datum and allocating parameters, offering enhanced adaptability and practicality. Unlike some existing C-IF scoring functions, this parameterized function effectively accounts for the radius of uncertainty, ensuring more accurate and reliable C-IF number comparisons. Comparative assessments with other scoring techniques demonstrate the superiority and stability of proposed function across various C-IF datasets. This newly introduced scoring function proves valuable in addressing multiple criteria assessment challenges within C-IF contexts, providing decision analysts with a dependable tool for complex decision-making scenarios. This research delves into real-world instances, including supplier assessment and healthcare waste disposal, illustrating a practical implementation of the model. Additionally, a comparison study and investigation have been done to emphasize the benefits of the parameterized C-IF scoring procedure employed in the postulated C-IF assignment methodology. This study offers substantial contributions, encompassing: (i) devotion to the establishment of a parameterized C-IF scoring methodology, (ii) assurance of consistent and rational C-IF scoring outcomes through the proposed parameterized scoring rule, (iii) the methodology's flexibility, allowing customization of parameters to align with decision-makers' preferences, (iv) improvement in the stability of C-IF assignment modeling through the parameterized C-IF scoring framework, and (v) demonstrated its practical viability through real-world applications in tackling challenges associated with multiple criteria assessment in C-IF contexts. [ABSTRACT FROM AUTHOR]

Conventional intelligent fault diagnosis studies require precise labels by default. However, label noise is inevitable in real industrial environments due to human errors, measurement biases, data transmission and storage errors. The performance of existing data-driven methods may be severely affected by mislabels. In this paper, we investigate the fault diagnosis issue of rotating machinery under noisy labels. A generalized framework contrastive regularization guided label refurbishment (CRLR) is proposed, which utilizes contrastive regularization function extracting class prototype to guide label refurbishment. The learned contrastive representations can suppress the misleading effect of noisy labels. The theoretical analysis from an information theoretic perspective also ensures the effectiveness of CRLR. Validation experiments have been conducted on public and private collected datasets using the ResNet-50 as the backbone network. The experiments demonstrate that our proposed framework outperforms the current state-of-the-art methods at different noise rates. [ABSTRACT FROM AUTHOR]

Abnormal conditions that arise during the fused magnesia smelting process (FMSP) can negatively impact product quality and increase energy consumption. However, due to the process's nonlinear and time-varying nature and the limited availability of abnormal condition data, researching effective self-healing control measures has been severely constrained. Therefore, this paper proposes a fused magnesium furnace (FMF) abnormal condition self-healing control method based on data augmentation and improved just-in-time learning (JITL). Firstly, data augmentation technology is used to generate virtual abnormal condition samples to expand the historical dataset. Then, an improved JITL model is constructed to solve the self-healing measures corresponding to abnormal conditions. Experimental results demonstrate that the proposed method can effectively restore the FMF to normal conditions and outperforms existing methods. [ABSTRACT FROM AUTHOR]

3-D mapping of buildings is crucial for urban renewal, but traditional LiDAR-based mapping methods are often less effective for buildings with narrow spaces and limited geometric features. Current methods attempt to overcome this by integrating additional sensors, such as cameras, which increases cost and complexity. This paper proposes a novel LiDAR-based mobile mapping framework using global principal planes (GPPs) to address this challenge without additional sensors. GPPs are defined as unlimited planes characterized by principal normal vectors (PNVs). GPPs can provide stronger constraints than traditional small planes extracted from one or certain LiDAR frames because they are little affected by the accumulative error from point cloud matching. A PNV estimation method is also proposed based on an inertial measurement unit and polar histogram, and PNVs are axes of the natural cartesian XYZ coordinate system. Point clouds are transformed into the PNVs coordinate system to extract robust edge and plane feature points and GPPs. The proposed framework is tested in various environments. It achieves about 3 cm accuracy in corridors and similar accuracy in stairwells. Compared to five state-of-the-art mapping methods (Cartographer, etc.), its accuracy improves by over 76%, increasing at least an order of magnitude. In the outdoor KITTI dataset, it shows a reduction in absolute pose errors by 4% to 20%. Extensive experiments demonstrate its accuracy, robustness, and generalizability. Ablation experiments further validate the efficacy of different components in the framework. [ABSTRACT FROM AUTHOR]

Fault diagnosis is important for isolating the root causes and supporting preventive maintenance of an equipment. However, the lack of labeled fault samples often limits the performance of fault diagnosis in practical situations. In this paper, we propose an information-guided signal multi-granularity contrastive feature learning (IMCFL) method with few labeled data to identify fault types. Unlike manual selection of data augmentation in traditional contrastive learning, IMCFL adaptively generates task-relevant augmented views for contrastive learning by differentiable automatic augmentation guided by information from few labeled (no more than 5%) data. Furthermore, a multi-granularity contrastive loss is constructed for the feature extractor to generate discriminative feature representation considering the characteristics of the signals. By exploring instance-level relationships and temporal relationships within the signal in multiple successive down-sampling operations, features of different granularities can be adequately extracted. After completing the contrastive learning, fault diagnosis is accomplished by a simple classifier without fine-tuning. Experiments on bearing and gear datasets demonstrate the diagnostic accuracy of the proposed method compared to other methods. Further transfer learning experiments show that the proposed method has the ability to be applied to different devices for fault diagnosis through knowledge transfer of its pre-trained powerful feature extractors. [ABSTRACT FROM AUTHOR]

The big data era enables automakers to mine users' affective (Kansei) requirements for the car design. However, existing literature mostly applies text mining with users' online comments, possibly leading to biased results since users without online comments were not considered. To fill in this gap, this paper proposes to jointly analyse users' online commenting and offline usage big data, and develops a novel framework to efficiently fuse these two datasets for the Kansei engineering of the intelligent connected vehicle (ICV) functions. A behaviour-enhanced large language model is proposed to process users' online comments; then, users' Kansei requirements are further jointly analysed with their offline in-cabin behaviour data, by the proposed NLP-MDCEV (natural language process — multiple discrete-continuous extreme value) model, to understand user's complex discrete and continuous choice decisions in the smart cockpit. In addition, the proposed framework aims to solve the problem of design tasks prioritization, where not all the Kansei requirements can be met if design resources are limited. The proposed framework is applied in the studied new energy vehicle company, with more than nine-months' online comments and six-months' offline usage data, where results suggest its merits of economic, efficient, and effective. • Online comments and offline behaviours are mined for Kansei design requirements. • Entropy is used to evaluate the cost-benefit of customized text mining models. • Behaviour-enhanced BERT model is proposed to achieve a 98% F1-score in text mining. • NLP-boost MDCEV model is developed to bridge online-offline data for Kansei analysis. • Applied in a new energy vehicle company with real data. [ABSTRACT FROM AUTHOR]