Search

This paper assesses the effectiveness of different unsupervised Bayesian changepoint detection (BCPD) methods for identifying soil layers, using data from cone penetration tests (CPT). It compares four types of BCPD methods: a previously utilised offline univariate method for detecting clay layers through undrained shear strength data, a newly developed online univariate method, and an offline and an online multivariate method designed to simultaneously analyse multiple data series from CPT. The performance of these BCPD methods was tested using real CPT data from a study area with layers of sandy and clayey soil, and the results were verified against ground-truth data from adjacent borehole investigations. The findings suggest that some BCPD methods are more suitable than others in providing a robust, quick, and automated approach for the unsupervised detection of soil layering, which is critical for geotechnical engineering design.

The manufacturing industry must maintain high-quality standards while meeting customer demands for customization, reduced carbon footprint, and competitive pricing. To address these challenges, companies are constantly improving their production processes using quality management tools. A crucial aspect of this improvement is the root cause analysis of manufacturing defects. In recent years, there has been a shift from traditional knowledge-driven approaches to data-driven approaches. However, there is a gap in the literature regarding a systematic overview of both methodological types, their overlaps, and the challenges they pose. To fill this gap, this study conducts a scoping literature review of root cause analysis in manufacturing, focusing on both data-driven and knowledge-driven approaches. For this, articles from IEEE Xplore, Scopus, and Web of Science are examined. This review finds that data-driven approaches have become dominant in recent years, with explainable artificial intelligence emerging as a particularly strong approach. Additionally, hybrid variants of root cause analysis, which combine expert knowledge and data-driven approaches, are also prevalent, leveraging the strengths of both worlds. Major challenges identified include dependence on expert knowledge, data availability, and management issues, as well as methodological difficulties. This article also evaluates the potential of artificial intelligence and hybrid approaches for the future, highlighting their promises in advancing root cause analysis in manufacturing.

Background: The blood supply chain (BSC) is crucial for providing safe and sufficient blood, but it faces numerous challenges and needs to be robust and resilient. This study provides a comprehensive model for managing and optimizing the BSC in real-world scenarios, including emergency and routine circumstances and with consideration of health equity concepts. Method: Classic time-series models are applied to predict future supply chain circumstances, addressing uncertainty in blood demand and the need for timely supply. A structured framework and medical preferences are prioritized to optimize distribution, minimize blood shortages, minimize wastage due to expiry, and maximize blood freshness. Genetic algorithms (GA) and particle swarm optimization (PSO) are used to solve mathematical models quickly and efficiently, ensuring reliable operation. Result: The model’s outcomes can effectively meet the daily needs of the BSC and assist decision-makers managing blood inventory and distribution, improving robustness and resilience. Conclusions: Utilizing weights allows for the effective management of each objective function to convert the model into a single-objective mixed-integer linear programming (SO-MILP) based on unique conditions, enabling the system to self-adjust for optimal performance, boosting the sustainability of the blood supply chain, and promoting the principle of health equity under diverse real-world settings.

The degree of rock mass discontinuity is crucial for evaluating surrounding rock quality, yet its accurate and rapid measurement at construction sites remains challenging. This study utilizes fractal dimension to characterize the geometric characteristics of rock mass discontinuity and develops a data-driven surrounding rock classification (SRC) model integrating machine learning algorithms. Initially, the box-counting method was introduced to calculate the fractal dimension of discontinuity from the excavation face image. Subsequently, crucial parameters affecting surrounding rock quality were analyzed and selected, including rock strength, the fractal dimension of discontinuity, the discontinuity condition, the in-situ stress condition, the groundwater condition, and excavation orientation. This study compiled a database containing 246 railway and highway tunnel cases based on these parameters. Then, four SRC models were constructed, integrating Bayesian optimization (BO) with support vector machine (SVM), random forest (RF), adaptive boosting (AdaBoost), and gradient boosting decision tree (GBDT) algorithms. Evaluation indicators, including 5-fold cross-validation, precision, recall, F1-score, micro-F1-score, macro-F1-score, accuracy, and the receiver operating characteristic curve, demonstrated the GBDT-BO model’s superior robustness in learning and generalization compared to other models. Furthermore, four additional excavation face cases validated the intelligent SRC approach’s practicality. Finally, the synthetic minority over-sampling technique was employed to balance the training set. Subsequent retraining and evaluation confirmed that the imbalanced dataset does not adversely affect SRC model performance. The proposed GBDT-BO model shows promise for predicting surrounding rock quality and guiding dynamic tunnel excavation and support.

An accurate assessment of the state of charge (SOC) of electric vehicle batteries is critical for implementing frequency regulation and peak shaving. This study proposes mechanism- and data-driven SOC fusion calculation methods. First, a second-order Thevenin battery model is developed to obtain the physical parameters of the battery. Second, data from the Thevenin battery model and data from four standard cycling conditions in the electric vehicle industry are added to the dataset of the feed-forward neural network data-driven model to construct the test and training sets of the data-driven model. Finally, the error of the mechanism and data-driven fusion modeling method is quantitatively analyzed by comparing the estimation error of the method for the battery SOC at different temperatures with the accuracy of the data-driven SOC estimation method. The simulation results show that the root mean square error, the mean age absolute error, and the maximum error of mechanism and data-driven method for the estimation error of battery SOC are lower than those of the data-driven method by 0.9%, 0.65%, and 1.3%, respectively. The results show that the mechanism and data-driven fusion SOC estimation method has better generalization performance and higher SOC estimation accuracy.

The conceptual design of unmanned aerial vehicles (UAVs) presents significant multidisciplinary challenges requiring the optimization of aerodynamic and structural performance, stealth, and propulsion efficiency. This work addresses these challenges by integrating deep neural networks with a multiobjective genetic algorithm to optimize UAV configurations. The proposed framework enables a comprehensive evaluation of design alternatives by estimating key performance metrics required for different operational requirements. The design process resulted in a significant improvement in computational time over traditional methods by more than three orders of magnitude. The findings illustrate the framework’s capability to optimize UAV designs for a variety of mission scenarios, including specialized tasks such as intelligence, surveillance, and reconnaissance (ISR), combat air patrol (CAP), and Suppression of Enemy Air Defenses (SEAD). This flexibility and adaptability was demonstrated through a case study, showcasing the method’s effectiveness in tailoring UAV configurations to meet specific operational requirements while balancing trade-offs between aerodynamic efficiency, stealth, and structural weight. Additionally, these results underscore the transformative impact of integrating AI into the early stages of the design process, facilitating rapid prototyping and innovation in aerospace engineering. Consequently, the current work demonstrates the potential of AI-driven optimization to revolutionize UAV design by providing a robust and effective tool for solving complex engineering problems.

Aerodynamic contour dimensional accuracy is very important for the stable and safe flight of aerospace vehicles. Nevertheless, due to the influence of various factors such as material properties, machining and manufacturing deviations, and assembly and installation deviations, key structural geometric dimensions are frequently exceeded. Therefore, this paper investigates a data-driven combined vector loop method (VLM)–Skin Model Shapes (SMS) method to realize aerospace vehicle structural geometric accuracy analysis; assembly optimization targeting contour deviation is also achieved. Tests are carried out on a typical aerospace vehicle’s underconstrained structural workpieces to validate the effectiveness of the proposed method.

Large underground spaces are complex and huge, with problems such as fragmented data that cannot be shared, outdated management methods, and high operation and maintenance costs. The digitization of building information and the use of digital twin technology can effectively improve the efficiency of building operation and maintenance. Using information technology to build a digital-twin-based operation and maintenance management system, the huge and discrete data and equipment system information are effectively integrated and explored for application. First, we analyze the shortcomings of the traditional delivery and operation and maintenance methods and introduce the necessity of a new method of operation and maintenance management based on digital twin; then, we divide the operation and maintenance information of the construction project into four major categories of spatial information and eight major categories of equipment information and complete the coding work, and the categorized data serve as the data basis for operation and maintenance; second, we develop a digital twin operation and maintenance management platform based on the operation and maintenance data of BIM; finally, we carry out case validation for the three major constructions. Finally, case validation is carried out for three major buildings and a large underground space and the practical application shows that the operation and maintenance management system based on digital twin technology provides technical guarantee for decentralized information and system integration management and the information management quality and efficiency of the operation and maintenance process are effectively improved. Through the practice of summarizing the experience, which is worth learning, we aim to create a large underground space operation and maintenance management method to provide a reference.

This paper presents convergence analysis of a novel data-driven feedback control algorithm designed for generating online controls based on partial noisy observational data. The algorithm comprises a particle filter-enabled state estimation component, estimating the controlled system’s state via indirect observations, alongside an efficient stochastic maximum principle-type optimal control solver. By integrating weak convergence techniques for the particle filter with convergence analysis for the stochastic maximum principle control solver, we derive a weak convergence result for the optimization procedure in search of optimal data-driven feedback control. Numerical experiments are performed to validate the theoretical findings.

Nonlinear optimization (NOPT) is a meaningful tool for solving complex tasks in fields like engineering, economics, and operations research, among others. However, NOPT has problems when it comes to dealing with data variability and noisy input measurements that lead to incorrect solutions. Furthermore, nonlinear constraints may result in outcomes that are either infeasible or suboptimal, such as nonconvex optimization. This paper introduces a novel regularized physics-informed neural network (RPINN) framework as a new NOPT tool for both supervised and unsupervised data-driven scenarios. Our RPINN is threefold: By using custom activation functions and regularization penalties in an artificial neural network (ANN), RPINN can handle data variability and noisy inputs. Furthermore, it employs physics principles to construct the network architecture, computing the optimization variables based on network weights and learned features. In addition, it uses automatic differentiation training to make the system scalable and cut down on computation time through batch-based back-propagation. The test results for both supervised and unsupervised NOPT tasks show that our RPINN can provide solutions that are competitive compared to state-of-the-art solvers. In turn, the robustness of RPINN against noisy input measurements makes it particularly valuable in environments with fluctuating information. Specifically, we test a uniform mixture model and a gas-powered system as NOPT scenarios. Overall, with RPINN, its ANN-based foundation offers significant flexibility and scalability.

With the advent of large-scale data, the demand for information is increasing, which makes signal sampling technology and digital processing methods particularly important. The utilization of 1-bit compressive sensing in sparse recovery has garnered significant attention due to its cost-effectiveness in hardware implementation and storage. In this paper, we first leverage the minimax concave penalty equipped with the least squares to recover a high-dimensional true signal x∈Rp with k-sparse from n-dimensional 1-bit measurements and discuss the regularization by combing the nonconvex sparsity-inducing penalties. Moreover, we give an analysis of the complexity of the method with minimax concave penalty in certain conditions and derive the general theory for the model equipped with the family of sparsity-inducing nonconvex functions. Then, our approach employs a data-driven Newton-type method with stagewise steps to solve the proposed method. Numerical experiments on the synthesized and real data verify the competitiveness of the proposed method.

The charging behavior of electric vehicle users is highly stochastic, which makes the short-term prediction of charging load at electric vehicle charging stations difficult. In this paper, a data-driven hybrid model optimized by the improved dung beetle optimization algorithm (IDBO) is proposed to address the problem of the low accuracy of short-term prediction. Firstly, the charging station data are preprocessed to obtain clear and organized load data, and the input feature matrix is constructed using factors such as temperature, date type, and holidays. Secondly, the optimal CNN-BiLSTM model is constructed using convolutional neural network (CNN) and Bi-directional Long Short-Term Memory (BiLSTM), which realizes the feature extraction of the input matrix and better captures the hidden patterns and regularities in it. Then, methods such as Bernoulli mapping are used to improve the DBO algorithm and its hyperparameters; for example, hidden neurons of the hybrid model are tuned to further improve the model prediction accuracy. Finally, a simulation experiment platform is established based on MATLAB R2023a to validate the example calculations on the historical data of EV charging stations in the public dataset of ANN-DATA, and comparative analyses are carried out. The results show that compared with the traditional models such as CNN, BiLSTM and PSO-CNN-BiLSTM, the coefficient of determination of the model exceeds 0.8921 and the root mean square error is maintained at about 4.413 on both the training and test sets, which proves its effectiveness and stability.

With the rapid development of artificial intelligence technology, data-driven advanced models have provided new ideas and means for airfoil aerodynamic optimization. As the advanced models update and iterate, many useful explorations and attempts have been made by researchers on the integrated application of artificial intelligence and airfoil aerodynamic optimization. In this paper, many critical aerodynamic optimization steps where data-driven advanced models are employed are reviewed. These steps include geometric parameterization, aerodynamic solving and performance evaluation, and model optimization. In this way, the improvements in the airfoil aerodynamic optimization area led by data-driven advanced models are introduced. These improvements involve more accurate global description of airfoil, faster prediction of aerodynamic performance, and more intelligent optimization modeling. Finally, the challenges and prospect of applying data-driven advanced models to aerodynamic optimization are discussed.

In order to solve the problems of traditional mental stress detection in college students that are time-consuming, random, and subjective, this paper proposes an intelligent perception-driven mental stress assessment method for college students. First, we analyze the factors in SRQ and SCL-90, which can be measured by intelligent sensing methods, including sleep, exercise, social interaction, and environment, and then perform feature extraction. Secondly, we use machine learning methods to build a mental stress assessment model. The Shapley additive explanations (SHAP) model is used to explain the training results. Experimental results show that the model proposed in this article can effectively assess the mental stress state of college students. This means that the collection of intelligent perception data based on the mental stress scale can effectively evaluate the mental stress state of college students and provide a new research idea for further developing a non-intrusive and real-time mental stress assessment for college students.

In hydro turbines, the draft tube vortex rope is one of the most crucial impact factors causing pressure pulsation and vibration. It is affected by operating conditions due to differences in the flow rate and state and can be symmetric or asymmetric along the rotational direction. It may influence the stability of draft tube flow. To achieve a better understanding, in this work, dynamic mode decomposition is used in a draft tube case study of a simplification of a vortex rope. As the flow rate increases, the shape of the vortex rope becomes clear, and the flow rotation becomes more significant as the inlet flow rate increases. Dynamic mode decomposition was used to determine the relative frequencies, which were 0 (averaged), 0.7 times, and 1.4 times the features of the reference frequency. As the inlet flow rate increases, the order of high-energy modes and their influence on the vortex rope gradually increase, and this characteristic is exhibited further downstream of the draft tube. When the inlet flow rate is low, the impact of mode noise is greater. As the flow velocity increases, the noise weakens and the rotation mode becomes more apparent. Identifying the mode of the vortex flow helps extract characteristics of the vortex rope flow under different operating conditions, providing a richer data-driven basis for an in-depth analysis of the impact of operating conditions on the flow stability of a draft tube.

The escalating demand for power load is increasingly prone to triggering power quality (PQ) issues, leading to severe economic losses. Aiming at reducing the economic losses, this paper focuses on the coordinated relationship between PQ and economic costs. Firstly, a multilayer multiple linear stepwise regression method is employed to screen PQ indicators, identifying harmonic and voltage deviation as the primary influencing factors of PQ. Secondly, a gradient descent optimization algorithm based on the Least Absolute Shrinkage and Selection Operator (LASSO) is proposed, enabling rapid computation of the minimum PQ cost. Finally, through validations of two case studies, the results confirm that the proposed method can rapidly calculate the minimum PQ cost based on real-time load demands, enabling the dynamic adjustment of PQ cost to meet the evolving needs of power system development.

This study introduces a data-driven and machine-learning approach to design a personalized tourist recommendation system for Nepal. It examines key tourist attributes, such as demographics, behaviors, preferences, and satisfaction, to develop four sub-models for data collection and machine learning. A structured survey is conducted with 2400 international and domestic tourists, featuring 28 major questions and 125 variables. The data are preprocessed, and significant features are extracted to enhance the accuracy and efficiency of the machine-learning models. These models are evaluated using metrics such as accuracy, precision, recall, F-score, ROC, and lift curves. A comprehensive database for Pokhara City, Nepal, is developed from various sources that includes attributes such as location, cost, popularity, rating, ranking, and trend. The machine-learning models provide intermediate categorical recommendations, which are further mapped using a personalized recommender algorithm. This algorithm makes decisions based on weights assigned to each decision attribute to make the final recommendations. The system’s performance is compared with other popular recommender systems implemented by TripAdvisor, Google Maps, the Nepal tourism website, and others. It is found that the proposed system surpasses existing ones, offering more accurate and optimized recommendations to visitors in Pokhara. This study is a pioneering one and holds significant implications for the tourism industry and the governing sector of Nepal in enhancing the overall tourism business.

In the era of burgeoning electric vehicle (EV) popularity, understanding the patterns of EV users’ behavior is imperative. This paper examines the trends in household charging sessions’ timing, duration, and energy consumption by analyzing real-world residential charging data. By leveraging the information collected from each session, a novel framework is introduced for the efficient, real-time prediction of important charging characteristics. Utilizing historical data and user-specific features, machine learning models are trained to predict the connection duration, charging duration, charging demand, and time until the next session. These models enhance the understanding of EV users’ behavior and provide practical tools for optimizing the EV charging infrastructure and effectively managing the charging demand. As the transportation sector becomes increasingly electrified, this work aims to empower stakeholders with insights and reliable models, enabling them to anticipate the localized demand and contribute to the sustainable integration of electric vehicles into the grid.

Arctic navigation faces numerous challenges, including uncertain ice conditions, rapid weather changes, limited communication capabilities, and lack of search and rescue infrastructure, all of which increase the risks involved. According to an Arctic Council statistical report, a remarkable 2638 maritime accidents were recorded in Arctic waters between 2005 and 2017, showing a fluctuating upward trend. This study collected and analyzed ship accident data in Arctic waters to identify the various accident scenarios and primary risk factors that impact Arctic navigation safety. By utilizing data-driven algorithms, a model for predicting ship navigation accidents in Arctic waters was constructed, providing an in-depth understanding of the risk factors that make accidents more likely. The research findings are of practical significance for enhancing quantitative risk assessment, specifically focusing on the navigational risks in Arctic waters. The results of this study can assist maritime authorities and shipping companies in conducting risk analysis and implementing accident prevention measures for safe navigation in Arctic waters.

This paper introduces a comprehensive framework that elucidates the microfoundations of data-driven antimicrobial stewardship programs (ASPs), specifically focusing on resource-constrained settings. Such settings necessitate the utilization of available resources and engagement among multiple stakeholders. The microfoundations are conceptualized as interlinked components: input, process, output, and outcome. Collectively, these components provide a comprehensive framework for understanding the development and implementation of data-driven ASPs in resource-constrained settings. It underscores the importance of considering both the social and material dimensions when evaluating microbiological, clinical, and social impacts. By harmonizing technology, practices, values, and behaviors, this framework offers valuable insights for the development, implementation, and assessment of ASPs tailored to resource-constrained environments.

The state of Victoria, Australia, implemented one of the world’s most prolonged cumulative lockdowns in 2020 and 2021. Although lockdowns have proven effective in managing COVID-19 worldwide, this approach faced challenges in containing the rising infection in Victoria. This study evaluates the effects of short-term (less than 60 days) and long-term (more than 60 days) lockdowns on public mobility and the effectiveness of various social restriction measures within these periods. The aim is to understand the complexities of pandemic management by examining various measures over different lockdown durations, thereby contributing to more effective COVID-19 containment methods. Using restriction policy, community mobility, and COVID-19 data, a machine-learning-based simulation model was proposed, incorporating analysis of correlation, infection doubling time, and effective lockdown date. The model result highlights the significant impact of public event cancellations in preventing COVID-19 infection during short- and long-term lockdowns and the importance of international travel controls in long-term lockdowns. The effectiveness of social restriction was found to decrease significantly with the transition from short to long lockdowns, characterised by increased visits to public places and increased use of public transport, which may be associated with an increase in the effective reproduction number (Rt) and infected cases.

Fault detection is crucial in maintaining reliability, safety, and consistent product quality in chemical engineering processes. Accurate fault detection allows for identifying anomalies, signaling deviations from the system’s nominal behavior, ensuring the system operates within desired performance parameters, and minimizing potential losses. This paper presents a novel semi-supervised data-based monitoring technique for fault detection in multivariate processes. To this end, the proposed approach merges the capabilities of Principal Component Analysis (PCA) for dimensionality reduction and feature extraction with the Kolmogorov–Smirnov (KS)-based scheme for fault detection. The KS indicator is computed between the two distributions in a moving window of fixed length, allowing it to capture sensitive details that enhance the detection of faults. Moreover, no labeling is required when using this fault detection approach, making it flexible in practice. The performance of the proposed PCA–KS strategy is assessed for different sensor faults on benchmark processes, specifically the Plug Flow Reactor (PFR) process and the benchmark Tennessee Eastman (TE) process. Different sensor faults, including bias, intermittent, and aging faults, are considered in this study to evaluate the proposed fault detection scheme. The results demonstrate that the proposed approach surpasses traditional PCA-based methods. Specifically, when applied to PFR data, it achieves a high average detection rate of 98.31% and a low false alarm rate of 0.25%. Similarly, when applied to the TE process, it provides a good average detection rate of 97.27% and a false alarm rate of 6.32%. These results underscore the efficacy of the proposed PCA–KS approach in enhancing the fault detection of high-dimensional processes.

The prediction and optimization of the rate of penetration (ROP) for horizontal wells are more complicated than for vertical wells, but most of the current ROP prediction studies are for vertical wells, which cannot be adapted to the complex drilling characteristics of horizontal wells. To this end, this paper proposes a data knowledge dual-driven horizontal well ROP prediction method. Firstly, the drilling characteristics of horizontal wells are analyzed, showing that the horizontal wells ROP prediction model cannot be modeled using surface measurement data; secondly, based on the analysis of horizontal well drilling characteristics, a physical model-based horizontal well ROP modeling data pre-processing method is proposed by introducing the drag and torque model. Finally, a data knowledge dual-driven horizontal well ROP prediction method is proposed in conjunction with data-driven algorithms. The proposed horizontal well ROP prediction method is applied to the A1~A4 wells in the Sichuan area. Compared with the conventional data-driven ROP prediction method, the prediction accuracy of this method is improved by 30%. The proposed method can provide a basis for the intelligent optimization and management of ROP during the drilling of horizontal wells.

Battery degradation is a complex nonlinear problem, and it is crucial to accurately predict the cycle life of lithium-ion batteries to optimize the usage of battery systems. However, diverse chemistries, designs, and degradation mechanisms, as well as dynamic cycle conditions, have remained significant challenges. We created 53 features from discharge voltage curves, 18 of which were newly developed. The maximum relevance minimum redundancy (MRMR) algorithm was used for feature selection. Robust linear regression (RLR) and Gaussian process regression (GPR) algorithms were deployed on three different datasets to estimate battery cycle life. The RLR and GPR algorithms achieved high performance, with a root-mean-square error of 6.90% and 6.33% in the worst case, respectively. This work highlights the potential of combining feature engineering and machine learning modeling based only on discharge voltage curves to estimate battery degradation and could be applied to onboard applications that require efficient estimation of battery cycle life in real time.

Among several approaches to analyzing crash research, the use of machine learning and econometric analysis has found potential in the analysis. This study aims to empirically examine factors influencing the single-vehicle crash for personal cars and trucks using decision trees (DT) and mixed binary logit with heterogeneity in means and variances (RPBLHMV) and compare model accuracy. The data in this study were obtained from the Department of Highway during 2011–2017, and the results indicated that the RPBLHMV was superior due to its higher overall prediction accuracy, sensitivity, and specificity values when compared to the DT model. According to the RPBLHMV results, car models showed that injury severity was associated with driver gender, seat belt, mount the island, defect equipment, and safety equipment. For the truck model, it was found that crashes located at intersections or medians, mounts on the island, and safety equipment have a significant influence on injury severity. DT results also showed that running off-road and hitting safety equipment can reduce the risk of death for car and truck drivers. This finding can illustrate the difference causing the dependent variable in each model. The RPBLHMV showed the ability to capture random parameters and unobserved heterogeneity. But DT can be easily used to provide variable importance and show which factor has the most significance by sequencing. Each model has advantages and disadvantages. The study findings can give relevant authorities choices for measures and policy improvement based on two analysis methods in accordance with their policy design. Therefore, whether advocating road safety or improving policy measures, the use of appropriate methods can increase operational efficiency.

A data-driven fault diagnosis method is proposed in this study to address the challenge of handling a large volume of pressure data in the air brake pipe of high-speed trains. The suggested method utilizes a BP (back propagation) neural network to transform the time series pressure data into model elements in the model space, ensuring simplicity and stability. Various fitting functions, including Fourier basis, Gaussian basis, polynomial basis, sine basis, and others, are employed to accurately fit the pressure curve of the air brake pipe. The fault diagnosis process involves two steps: classifying the fault based on an optimal approximation equation and diagnosing it by analyzing the topological relationship of the model elements in the model space. The proposed method achieves an average fault diagnosis accuracy of 89.8%, with high accuracy rates for different fault states: 98% for normal state, 88% for blockage state, 84% for leakage state, and 96% for compressor fault state. Compared to the hidden Markov model method, the proposed method improves the average diagnostic accuracy by 2% for known working conditions and 4.87% for all working conditions, demonstrating its effectiveness and reliability. The fault diagnosis of the air brake tube in high-speed trains is of great significance, which aims to realize accurate fault diagnosis and prediction through sensor data monitoring and signal processing technology, so as to ensure the safe operation of high-speed trains. These studies provide an important theoretical and practical basis for the improvement and application of fault diagnosis methods.

Fault detection and diagnosis (FDD) is of utmost importance in ensuring the safety and reliability of electric vehicles (EVs). The EV’s power train and energy storage, namely the electric motor drive and battery system, are critical components that are susceptible to different types of faults. Failure to detect and address these faults in a timely manner can lead to EV malfunctions and potentially catastrophic accidents. In the realm of EV applications, Permanent Magnet Synchronous Motors (PMSMs) and lithium-ion battery packs have garnered significant attention. Consequently, fault detection methods for PMSMs and their drives, as well as for lithium-ion battery packs, have become a prominent area of research. An effective FDD approach must possess qualities such as accuracy, speed, sensitivity, and cost-effectiveness. Traditional FDD techniques include model-based and signal-based methods. However, data-driven approaches, including machine learning-based methods, have recently gained traction due to their promising capabilities in fault detection. This paper aims to provide a comprehensive overview of potential faults in EV motor drives and battery systems, while also reviewing the latest state-of-the-art research in EV fault detection. The information presented herein can serve as a valuable reference for future endeavors in this field.

Frequency-diverse radar imaging is an emerging field that combines computational imaging with frequency-diverse techniques to interrogate the high-quality images of objects. Despite the success of deep reconstruction networks in improving scene image reconstruction from noisy or under-sampled frequency-diverse measurements, their reliance on large amounts of high-quality training data and the inherent uninterpretable features pose significant challenges in the design and optimization of imaging networks, particularly in the face of dynamic variations in radar operating frequency bands. Here, aiming at reducing the latency and processing burden involved in scene image reconstruction, we propose an adaptive sampling iterative soft-thresholding deep unfolding network (ASISTA-Net). Specifically, we embed an adaptively sampling module into the iterative soft-thresholding (ISTA) unfolding network, which contains multiple measurement matrices with different compressed sampling ratios. The outputs of the convolutional layers are then passed through a series of ISTA layers that perform a sparse coding step followed by a thresholding step. The proposed method requires no need for heavy matrix operations and massive amount of training scene targets and measurements datasets. Unlike recent work using matrix-inversion-based and data-driven deep reconstruction networks, our generic approach is directly adapted to multi-compressed sampling ratios and multi-scene target image reconstruction, and no restrictions on the types of imageable scenes are imposed. Multiple measurement matrices with different scene compressed sampling ratios are trained in parallel, which enables the frequency-diverse radar to select operation frequency bands flexibly. In general, the application of the proposed approach paves the way for the widespread deployment of computational microwave and millimeter wave frequency-diverse radar imagers to achieve real-time imaging. Extensive imaging simulations demonstrate the effectiveness of our proposed method.

Building energy consumption prediction has a significant effect on energy control, design optimization, retrofit evaluation, energy price guidance, and prevention and control of COVID-19 in buildings, providing a guarantee for energy efficiency and carbon neutrality. This study reviews 116 research papers on data-driven building energy prediction from the perspective of data and machine learning algorithms and discusses feasible techniques for prediction across time scales, building levels, and energy consumption types in the context of the factors affecting data-driven building energy prediction. The review results revealed that the outdoor dry-bulb temperature is a vital factor affecting building energy consumption. In data-driven building energy consumption prediction, data preprocessing enables prediction across time scales, energy consumption feature extraction enables prediction across energy consumption types, and hyperparameter optimization enables prediction across time scales and building layers.

Availability of reliable and extended datasets of recorded power output from renewables is nowadays seen as one of the key drivers to improve the design and control of smart energy systems. In particular, these datasets are needed to train artificial intelligence methods. Very often, however, datasets can be corrupted due to lack of records connected to failures of the acquisition system, maintenance downtime periods, etc. Several recovery (imputation) methods have been used to guess and replace missing data. In this paper, we exploit the matrix completion approach. The available measures of several variables referring to a real onshore wind farm are organized into a matrix in a daily range and the Singular Value Thresholding method is used to carry out the matrix completion process. Numerical results show that matrix completion is a reliable and parameter-free tuning tool to impute missing data in these applications.

The tire/road peak friction coefficient (TRPFC) is the core parameter of vehicle stability control, and its estimation accuracy significantly affects the control effect of active vehicle safety. To estimate the peak adhesion coefficient accurately, a new method for the comprehensive adhesion coefficient of three-dimensional pavement based on a dimensionless data-driven tire model is proposed. Firstly, in order to accurately describe the contact state between the three-dimensional road surface and the tire during driving, stress distribution and multi-point contact are introduced into the vertical dynamic model and a new tire model driven by dimensionless data is established based on the normalization method. Secondly, the real-time assessment of lateral and longitudinal adhesion coefficients of three-dimensional pavement is realized with the unscented Kalman filter (UKF). Finally, according to the coupling relationship between the longitudinal tire adhesion coefficient and the lateral tire adhesion coefficient, a fuzzy reasoning strategy of fusing the longitudinal tire adhesion coefficient and the lateral tire adhesion coefficient is designed. The results of vehicle tests prove that the method proposed in this paper can estimate the peak adhesion coefficient of pavement quickly and accurately.

We are part of the digital transformation of society and industry. The digital transformation of industry is based on new technologies brought about by the fourth industrial revolution. The Internet of Things (IoT), Cloud Computing, Cyber–Physical Systems (CPS) and Big Data provide the digital link between machines and individuals in processes. This completely new system is based on efficient data collection, data analysis and immediate interventions in organizational processes based on the results of the analysis. Smart organizations are driven by data and not by models. By working efficiently with the vast amounts of data available, the smart organizations of the future can ensure business sustainability, increase competitiveness through process optimization and reduce costs. In general, the aim of this paper was to identify the means to achieve a paradigm shift from traditional organizations to smart organizations through the use of data in the context of integrating Industry 4.0 technologies. The aim of the research was to determine the extent to which different Industry 4.0 technologies are applied in the effective use of data from specific activities/processes in industrial organizations to bring about a paradigm shift from traditional organizations to smart organizations. The first part of the paper describes the theoretical background of the transition from traditional to smart organizations using selected Industry 4.0 technologies. The second part of the paper characterizes the research objective, the methods used in the paper and the basic statistics used to determine the research questions and hypotheses. The next section evaluates the research questions and hypotheses that were used to meet the research objective. The last part of the paper is a summary of the obtained results, based on which we conclude that the primary challenge for organizations in the Slovak Republic is to learn how to work with the collected data, the need for their appropriate structuring and subsequent archiving, which is manifested by the need for training and application of data analysts in a broader context.

This article presents an approach for spellchecking and autocorrection using web data for morphologically complex languages (in the case of Kazakh language), which can be considered an end-to-end approach that does not require any manually annotated word–error pairs. A sizable web of noisy data is crawled and used as a base to infer the knowledge of misspellings with their correct forms. Using the extracted corpus, a sub-string error model with a context model for morphologically complex languages are trained separately, then these two models are integrated with a regularization parameter. A sub-string alignment model is applied to extract symmetric and non-symmetric patterns in two sequences of word–error pairs. The model calculates the probability for symmetric and non-symmetric patterns of a given misspelling and its candidates to obtain a suggestion list. Based on the proposed method, a Kazakh Spellchecking and Autocorrection system is developed, which we refer to as QazSpell. Several experiments are conducted to evaluate the proposed approach from different angles. The results show that the proposed approach achieves a good outcome when only using the error model, and the performance is boosted after integrating the context model. In addition, the developed system, QazSpell, outperforms the commercial analogs in terms of overall accuracy.

The main gearbox is very important for the operation safety of helicopters, and the oil temperature reflects the health degree of the gearbox; therefore establishing an accurate oil temperature forecasting model is an important step for reliable fault detection. Firstly, in order to achieve accurate gearbox oil temperature forecasting, an improved deep deterministic policy gradient algorithm with a CNN–LSTM basic learner is proposed, which can excavate the complex relationship between oil temperature and working condition. Secondly, a reward incentive function is designed to accelerate the training time costs and to stabilize the model. Further, a variable variance exploration strategy is proposed to enable the agents of the model to fully explore the state space in the early training stage and to gradually converge in the training later stage. Thirdly, a multi-critics network structure is adopted to solve the problem of inaccurate Q-value estimation, which is the key to improving the prediction accuracy of the model. Finally, KDE is introduced to determine the fault threshold to judge whether the residual error is abnormal after EWMA processing. The experimental results show that the proposed model achieves higher prediction accuracy and shorter fault detection time costs.

Social relationships refer to the connections that exist between people and indicate how people interact in society. The effective recognition of social relationships is conducive to further understanding human behavioral patterns and thus can be vital for more complex social intelligent systems, such as interactive robots and health self-management systems. The existing works about social relation recognition (SRR) focus on extracting features on different scales but lack a comprehensive mechanism to orchestrate various features which show different degrees of importance. In this paper, we propose a new SRR framework, namely Multi-level Transformer-Based Social Relation Recognition (MT-SRR), for better orchestrating features on different scales. Specifically, a vision transformer (ViT) is firstly employed as a feature extraction module for its advantage in exploiting global features. An intra-relation transformer (Intra-TRM) is then introduced to dynamically fuse the extracted features to generate more rational social relation representations. Next, an inter-relation transformer (Inter-TRM) is adopted to further enhance the social relation representations by attentionally utilizing the logical constraints among relationships. In addition, a new margin related to inter-class similarity and a sample number are added to alleviate the challenges of a data imbalance. Extensive experiments demonstrate that MT-SRR can better fuse features on different scales as well as ameliorate the bad effect caused by a data imbalance. The results on the benchmark datasets show that our proposed model outperforms the state-of-the-art methods with significant improvement.

In the extremely competitive environment of shipping, minimizing shipping cost is the key factor for the survival and growth of shipping companies. However, stricter rules and regulations that aim at the reduction of greenhouse gas emissions published by the International Maritime Organization, force shipping companies to increase the operational efficiency of their fleet. The prediction of a ship speed in actual seas with a given power by its engine is the most important performance indicator and thus makes it the “holy grail” in pursuing better efficiency. Traditionally, tank model tests and semi-empirical formulas were the preferred solution for the aforementioned prediction and are still widely applied. However, currently, with the increased computational power that is widely available, novel and more sophisticated methods taking into consideration computational fluid dynamics (CFD) and machine learning (ML) algorithms are emerging. In this paper, we briefly present the different approaches in the prediction of a ship’s speed but focus on ML methods comparing a representative number of the latest data-driven models used in papers, to provide guidelines, discover trends and identify the challenges to be faced by researchers. From this comparison, we can distinguish that artificial neural networks (ANN), being used in 73.3% of the reviewed papers, dominate as the algorithm of choice. Researchers mostly rely on physical laws governing the phenomena in the crucial part of data preprocessing tasks. Lastly, most researchers rely on data acquisition systems installed at ships in order to achieve usable results.

As the core component of an electric vehicle, the health of the traction battery closely affects the safety performance of the electric vehicle. If the sub-health state cannot be identified and dealt with in time, it may cause traction battery failure, pose a safety hazard, and cause property damage to the driver and passengers. This study used data-driven methods to identify the two typical types of sub-health state. For the first type of sub-health state, the interclass correlation coefficient (ICC) method was used to determine whether there was an inconsistency between the voltage of a single battery and the overall voltage of the battery pack. In order to determine the threshold, the ICC value of each vehicle under different working conditions was analyzed using box plots, and a statistical ICC threshold of 0.805 was used as the standard to determine the first sub-health type. For the second type of sub-health state, the Z-score and the differential area method were combined to determine whether the single cell voltage deviated from the overall battery pack voltage. A battery whose voltage differential area exceeds the range of u ± 3σ is regarded as having a sub-health state. The results show that both methods can accurately judge the sub-health state type of a single battery. Furthermore, combined with the one-month operation data of the vehicle, we could calculate the sub-health state frequency of each single battery and take single batteries with a high frequency as the key object of attention in future vehicle operations.

The ever-increasing travel demand has brought great challenges to the organization, operation, and management of the subway system. An accurate estimation of passenger flow distribution can help subway operators design corresponding operation plans and strategies scientifically. Although some literature has studied the problem of passenger flow distribution by analyzing the passengers’ path choice behaviors based on AFC (automated fare collection) data, few studies focus on the passenger flow distribution while considering the passenger–train matching probability, which is the key problem of passenger flow distribution. Specifically, the existing methods have not been applied to practical large-scale subway networks due to the computational complexity. To fill this research gap, this paper analyzes the relationship between passenger travel behavior and train operation in the space and time dimension and formulates the passenger–train matching probability by using multi-source data including AFC, train timetables, and network topology. Then, a reverse derivation method, which can reduce the scale of possible train combinations for passengers, is proposed to improve the computational efficiency. Simultaneously, an estimation method of passenger flow distribution is presented based on the passenger–train matching probability. Finally, two sets of experiments, including an accuracy verification experiment based on synthetic data and a comparison experiment based on real data from the Beijing subway, are conducted to verify the effectiveness of the proposed method. The calculation results show that the proposed method has a good accuracy and computational efficiency for a large-scale subway network.

A data-driven-based methodology for SHM in reinforced concrete structures using embedded fiber optic sensors and pattern recognition techniques is presented. A prototype of a reinforced concrete structure was built and instrumented in a novel fashion with FBGs bonded directly to the reinforcing steel bars, which, in turn, were embedded into the concrete structure. The structure was dynamically loaded using a shaker. Superficial positive damages were induced using bonded thin steel plates. Data for pristine and damaged states were acquired. Classifiers based on Mahalanobis’ distance of the covariance data matrix were developed for both supervised and unsupervised pattern recognition with an accuracy of up to 98%. It was demonstrated that the proposed sensing scheme in conjunction with the developed supervised and unsupervised pattern recognition techniques allows the detection of slight stiffness changes promoted by damages, even when strains are very small and the changes of these associated with the damage occurrence may seem negligible.

Data driven approaches are utilized for optimal sensor placement as well as for velocity prediction of wind turbine wakes. In this work, several methods are investigated for suitability in the clustering analysis and for predicting the time history of the flow field. The studies start by applying a proper orthogonal decomposition (POD) technique to extract the dynamics of the flow. This is followed by evaluations of different hyperparameters of the clustering and machine learning algorithms as well as their impacts on the prediction accuracy. Two test cases are considered: (1) the wake of a cylinder and (2) the wake of a rotating wind turbine rotor exposed to complex flow conditions. The training and test data for both cases are obtained from high fidelity CFD approaches. The studies reveal that the combination of a classification-based machine learning algorithm for optimal sensor placement and Bi-LSTM is sufficient for predicting periodic signals, but a more advanced technique is required for the highly complex data of the turbine near wake. This is done by exploiting the dynamics of the wake from the set of POD modes for flow field reconstruction. A satisfactory accuracy is achieved for an appropriately chosen prediction horizon of the Bi-LSTM networks. The obtained results show that data-driven approaches for wind turbine wake prediction can offer an alternative to conventional prediction approaches.

In order to study the multiple restricted factors and parameters of the eddy current loss of generator end structures, both the multi-layer perceptron (MLP) and support vector regression (SVR) are used to study and predict the mechanism of the synergistic effect of metal shield conductivity, relative permeability of clamping plates and structural characteristics of eddy current losses. Based on the eddy current losses of generator end structures under different metal shielding thicknesses and electromagnetic properties, the calculation accuracy of the MLP and SVR is compared. The prediction method gives an effective means for the complex design of the end region of the generator, which reduces the effort of the designers. It also promotes the design efficiency of the electrical generator.

Small intestinal bacterial overgrowth (SIBO) is characterized by abnormal and excessive amounts of bacteria in the small intestine. Since symptoms and lab tests are non-specific, the diagnosis of SIBO is highly dependent on breath testing. There is a lack of a universally accepted cut-off point for breath testing to diagnose SIBO, and the dilemma of defining “SIBO patients” has made it more difficult to explore the gold standard for SIBO diagnosis. How to validate the gold standard for breath testing without defining “SIBO patients” has become an imperious demand in clinic. Breath-testing datasets from 1071 patients were collected from Xiangya Hospital in the past 3 years and analyzed with an artificial intelligence method using cluster analysis. K-means and DBSCAN algorithms were applied to the dataset after the clustering tendency was confirmed with Hopkins Statistic. Satisfying the clustering effect was evaluated with a Silhouette score, and patterns of each group were described. Advantages of artificial intelligence application in adaptive breath-testing diagnosis criteria with SIBO were discussed from the aspects of high dimensional analysis, and data-driven and regional specific dietary influence. This research work implied a promising application of artificial intelligence for SIBO diagnosis, which would benefit clinical practice and scientific research.

Many complex turbulent flows in nature and engineering can be qualitatively regarded as being constituted of multiple simpler unit flows. The objective of this work is to characterize the coherent structures in such complex flows as a combination of constituent unitary flow structures for the purpose of reduced-order representation. While turbulence is clearly a non-linear phenomenon, we aim to establish the degree to which the optimally weighted superposition of unitary flow structures can represent the complex flow structures. The rationale for investigating such superposition stems from the fact that the large-scale coherent structures are generated by underlying flow instabilities that may be reasonably described using linear analysis. Clearly, the degree of validity of superposition will depend on the flow under consideration. In this work, we take the first step toward establishing a procedure for investigating superposition. Experimental data of single and triple tandem jets in crossflow are used to demonstrate the procedure. A composite triple tandem jet flow field is generated from optimal superposition of single jet data and compared against ‘true’ triple jet data. Direct comparisons between the true and composite fields are made for spatial, temporal, and kinetic energy content. The large-scale features (obtained from proper orthogonal decomposition or POD) of true and composite tandem jet wakes exhibit nearly 70% agreement in terms of modal eigenvector correlation. Corresponding eigenvalues reveal that the kinetic energy of the flow is also emulated with only a slight overprediction. Temporal frequency features are also examined in an effort to completely characterize POD modes. The proposed method serves as a foundation for more rigorous and robust dimensional reduction in complex flows based on unit flow modes.

Effectively transporting drilled cuttings to the surface is a vital part of the well construction process. Usually, mechanistic models are used to estimate the cuttings concentration during drilling. Based on the results from these model, operational parameters are adjusted to mitigate any nonproductive time events such as pack-off or lost circulation. However, these models do not capture the underlying complex physics completely and frequently require updating the input parameters, which is usually performed manually. To address this, in this study, a data-driven modeling approach is taken and evaluated together with widely used mechanistic models. Artificial neural networks are selected after several trials. The experimental data collected at The University of Tulsa–Drilling Research Projects (in the last 40 years) are used to train and validate the model, which includes a wide range of wellbore and pipe sizes, inclinations, rate-of-penetration values, pipe rotation speeds, flow rates, and fluid and cuttings properties. It is observed that, in many cases, the data-driven model significantly outperforms the mechanistic models, which provides a very promising direction for real-time drilling optimization and automation. After the neural network is proven to work effectively, an optimization attempt to estimate flow rate and pipe rotation speed is introduced using a genetic algorithm. The decision is made considering minimizing the required total energy for this process. This approach may be used as a design tool to identify the required flow rate and pipe rotation speed to acquire effective hole cleaning while consuming minimal energy.

Simultaneous and timely assessment of growth and water status-related plant traits is critical for precision irrigation management in arid regions. Here, we used proximal hyperspectral sensing tools to estimate biomass fresh weight (BFW), biomass dry weight (BDW), canopy water content (CWC), and total tuber yield (TTY) of two potato varieties irrigated with 100%, 75%, and 50% of the estimated crop evapotranspiration (ETc). Plant traits were assessed remotely using published and newly constructed vegetation and water spectral reflectance indices (SRIs). We integrated genetic algorithm (GA) and adaptive neuro-fuzzy inference system (ANFIS) models to predict the measured traits based on all SRIs. The different plant traits and SRIs varied significantly (p < 0.05) between the three irrigation regimes for the two varieties. The values of plant traits and majority SRIs showed a continuous decrease from the 100% ETc to the 50% ETc. Water-SRIs performed better than vegetation-SRIs for estimating the four plant traits. Almost all indices of the two SRI types had a weak relationship with the four plant traits (R2 = 0.00–0.37) under each irrigation regime. However, the majority of vegetation-SRIs and all water-SRIs showed strong relationships with BFW, CWC, and TTY (R2 ≥ 0.65) and moderate relationships with BDW (R2 ≥ 0.40) when the data of all irrigation regimes and varieties were analyzed together for each growing season or the data of all irrigation regimes, varieties, and seasons were combined together. The ANFIS-GA model predicted plant traits with satisfactory accuracy in both calibration (R2 = 1.0) and testing (R2 = 0.72–0.97) modes. The results indicate that SRI-based ANFIS models can improve plant trait estimation. This analysis also confirmed the benefits of applying GA to ANFIS to estimate plant responses to different growth conditions.

Thermal hydraulics, in certain components of nuclear reactor systems, involve complex flow scenarios, such as flows assisted by free jets and stratified flows leading to turbulent mixing and thermal fluctuations. These complex flow patterns and thermal fluctuations can be extremely critical from a reactor safety standpoint. The component-level lumped approximations (0D) or one-dimensional approximations (1D) models for such components and subsystems in safety analysis codes cannot capture the physics accurately, and may introduce a large degree of modeling uncertainty. On the other hand, high-fidelity computational fluid dynamics codes, which provide numerical solutions to the Navier–Stokes equations, are accurate but computationally intensive, and thus cannot be used for system-wide analysis. An alternate way to improve reactor safety analysis is by building reduced-order emulators from computational fluid dynamics (CFD) codes to improve system scale models. One of the key challenges in developing a reduced-order emulator is to preserve turbulent mixing and thermal fluctuations across different-length scales or time-scales. This paper presents the development of a reduced-order, non-linear, “Markovian” statistical surrogate for turbulent mixing and scalar transport. The method and its implementation are demonstrated on a canonical problem of differentially heated channel flow, and high-resolution direct numerical simulations (DNS) data are used for emulator or surrogate development. This statistical surrogate model relies on Kramers–Moyal expansion and emulates the turbulent velocity signal with a high degree of accuracy.

This paper presents an optimization algorithm for tuning the interpolation parameters of computer numerical control (CNC) controllers; it operates by considering multiple objective functions, namely, contour errors, the machining time (MT), and vibrations. The position commands, position errors, and vibration signals from 1024 experiments were considered in the designed trajectory. The experimental data—the maximum contour error (MCoE), MT, and corner vibration (CVib)—were analyzed to compute the performance index. A backpropagation neural network (BPNN) with 20 hidden layers was applied to predict the performance index. The correlation coefficients for the predicted values and experimental results for the MCoE, MT, and CVib based on the validation data were 0.9984, 0.9998, and 0.9354, respectively. The high correlation coefficients highlight the accuracy of the model for designing the interpolation parameter. After the BPNN model was developed, a genetic algorithm (GA) was adopted to determine the optimized parameters of the interpolation under different weighting of the performance index. A weighted sum approach involving the objective function was employed to determine the optimized interpolation parameters in the GA. Thus, operators can judge the feasibility of the interpolation parameter for various weighting settings. Finally, a mixed path was selected to verify the proposed algorithm.

To date, the predominant tools for the evaluation of built environment quality and impact have been surveys, scorecards, or verbal comments—approaches that rely upon user-reported responses. The goal of this research project is to develop, test, and validate a data-driven approach for built environment quality evaluation/validation based upon measurement of real-time emotional responses to simulated environments. This paper presents an experiment that was conducted by combining an immersive virtual environment (virtual reality) and electroencephalogram (EEG) as a tool to evaluate Pre and Post Purple Line development. More precisely, the objective was to (a) develop a data-driven approach for built environment quality evaluation and (b) understand the correlation between the built environment characters and emotional state. The preliminary validation of the proposed evaluation method identified discrepancies between traditional evaluation results and emotion response indications through EEG signals. The validation and findings have laid a foundation for further investigation of relations between people’s general cognitive and emotional responses in evaluating built environment quality and characters.

This paper proposes a distributed model-free adaptive bipartite consensus tracking (DMFABCT) scheme. The proposed scheme is independent of a precise mathematical model, but can achieve both bipartite time-invariant and time-varying trajectory tracking for unknown dynamic discrete-time heterogeneous multi-agent systems (MASs) with switching topology and coopetition networks. The main innovation of this algorithm is to estimate an equivalent dynamic linearization data model by the pseudo partial derivative (PPD) approach, where only the input–output (I/O) data of each agent is required, and the cooperative interactions among agents are investigated. The rigorous proof of the convergent property is given for DMFABCT, which reveals that the trajectories error can be reduced. Finally, three simulations results show that the novel DMFABCT scheme is effective and robust for unknown heterogeneous discrete-time MASs with switching topologies to complete bipartite consensus tracking tasks.

There is great interest in data-driven modelling for the forecasting of building energy consumption while using machine learning (ML) modelling. However, little research considers classification-based ML models. This paper compares the regression and classification ML models for daily electricity and thermal load modelling in a large, mixed-use, university building. The independent feature variables of the model include outdoor temperature, historical energy consumption data sets, and several types of ‘agent schedules’ that provide proxy information that is based on broad classes of activity undertaken by the building’s inhabitants. The case study compares four different ML models testing three different feature sets with a genetic algorithm (GA) used to optimize the feature sets for those ML models without an embedded feature selection process. The results show that the regression models perform significantly better than classification models for the prediction of electricity demand and slightly better for the prediction of heat demand. The GA feature selection improves the performance of all models and demonstrates that historical heat demand, temperature, and the ‘agent schedules’, which derive from large occupancy fluctuations in the building, are the main factors influencing the heat demand prediction. For electricity demand prediction, feature selection picks almost all ‘agent schedule’ features that are available and the historical electricity demand. Historical heat demand is not picked as a feature for electricity demand prediction by the GA feature selection and vice versa. However, the exclusion of historical heat/electricity demand from the selected features significantly reduces the performance of the demand prediction.