Search

In the development of innovative and high-performance products, design expertise is a critical factor. Nevertheless, novel manufacturing processes often frequently lack an accessible comprehensive knowledge base for product developers. To tackle this deficiency in the context of emerging additive manufacturing processes, substantial design knowledge has already been established. However, novel additive manufacturing processes like continuous fiber-reinforced material extrusion have often been disregarded, complicating the process's wider dissemination. The importance of design knowledge availability is paramount, as well as the need for user-friendly design knowledge preparation, standardized structure, and methodological support for accessing the accumulated knowledge with precision. In this paper, we present an approach that provides formalized opportunistic and restrictive design knowledge, ensuring both the comprehensive exploitation of process-specific potentials and the consideration of restrictive limitations in the construction of components. Opportunistic knowledge, presented as principle cards, is systematically derived, prepared, and made accessible. Moreover, an access system is developed to ensure the comprehensive utilization of process-specific potentials throughout the development process. Furthermore, we propose linking these principles through a synergy and conflict matrix, aiming to consider synergistic principles and identify potential conflicts at an early stage. Additionally, an approach to provide restrictive design knowledge in the form of a design rule catalog is proposed. The application of the knowledge system is demonstrated exemplarily using a weight-optimized component. [ABSTRACT FROM AUTHOR]

Owing to the advantages of monolithic structure and little need for assembling, compliant guiding mechanisms appear to be an effective solution for decoupling multi-freedom precision motions but are still prone to geometric nonlinearities of parasitic error and stiffening effect for large strokes. This paper proposes a coiled L-shape compliant guiding mechanism featuring millimeter-scale strokes with a compact structure, constant stiffness, and minimized parasitic error. The coiled compliant guiding mechanism is formed by convolving L-shape flexure beams in a zigzag configuration with decoupled XY motions achieved. Its geometrically nonlinear parasitic error, variation in stiffness, and primary vibration are captured by using a dynamic beam constraint model (DBCM). It is theoretically, numerically, and experimentally found, by comparing with double parallel guiding mechanisms, that the kinetostatic and dynamic behaviors of the coiled L-shape compliant mechanism are nearly independent on the applied force within intermediate-deformation ranges. Such a weak geometric nonlinearity with the minimized influence of axially loaded stiffening and kinematics-arching effects is much different from the double parallel guiding mechanisms. The obtained results indicate that large strokes with constant stiffness and invariable resonance frequency can be realized, which also allows small parasitic errors. [ABSTRACT FROM AUTHOR]

In the early stages of the design process, designers explore opportunities by discovering unmet needs and developing innovative concepts as potential solutions. From a human-centered design perspective, designers must develop empathy with people to truly understand their experiences and needs. However, developing empathy is a complex and subjective process that relies heavily on the designer's empathic capability, and is often subject to the experiences of a small group of people. Therefore, the development of empathic understanding is intuitive, and the discovery of underlying needs can be serendipitous and unrepresentative. This paper aims to provide insights from artificial intelligence research to indicate the future direction of AI-driven human-centered design, considering the essential role of empathy. Specifically, we conduct an interdisciplinary investigation of research areas such as data-driven user research, empathic design, and artificial empathy. Based on this foundation, we discuss the role that artificial empathy can play in human-centered design and propose an artificial empathy framework for human-centered design. Building on the mechanisms behind empathy and insights from empathic design research, the framework aims to break down the rather complex and subjective process of developing empathic understanding into modules and components that can potentially be modeled computationally. Furthermore, we discuss the expected benefits of developing such systems and identify research opportunities to suggest future research efforts. [ABSTRACT FROM AUTHOR]

Sequential sampling methods have gained significant attention due to their ability to iteratively construct surrogate models by sequentially inserting new samples based on existing ones. However, efficiently and accurately creating surrogate models for high-dimensional, nonlinear, and multimodal problems is still a challenging task. This paper proposes a new sequential sampling method for surrogate modeling based on a hybrid metric, specifically making the following three contributions: (1) a hybrid metric is developed by integrating the leave-one-out cross-validation error, the local nonlinearity, and the relative size of Voronoi regions using the entropy weights, which well considers both the global exploration and local exploitation of existing samples; (2) a Pareto-TOPSIS strategy is proposed to first filter out unnecessary regions and then efficiently identify the sensitive region within the remaining regions, thereby improving the efficiency of sensitive region identification; and (3) a prediction-error-and-variance (PE&V) learning function is proposed based on the prediction error and variance of the intermediate surrogate models to identify the new sample to be inserted in the sensitive region, ultimately improving the efficiency of the sequential sampling process and the accuracy of the final surrogate model. The proposed sequential sampling method is compared with four state-of-the-art sequential sampling methods for creating Kriging surrogate models in seven numerical cases and one real-world engineering case of a cutterhead of a tunnel boring machine. The results show that compared with the other four methods, the proposed sequential sampling method can more quickly and robustly create an accurate surrogate model using a smaller number of samples. [ABSTRACT FROM AUTHOR]

The moment method is commonly used in reliability analysis, in which the maximum entropy method (MEM) and polynomial fitting (PF) have been widely used due to their advantages in accuracy and efficiency, respectively. In this paper, we propose a novel reliability analysis method by combining MEM and PF. The probability density function is preliminarily estimated using the fractional moment maximum entropy method (FM-MEM), based on which PF is then used to further improve the accuracy. The proposed method can avoid the phenomenon of the negative probability density and function oscillations in PF effectively. Moreover, the order of the exponential polynomial in the FM-MEM is adaptively selected in the preliminary solution calculation process. An iterative process for the number of exponential polynomial terms is also proposed, using the integral of the moment error function and the integrals of the local and global negative probability density as the convergence criteria. Four numerical examples and one engineering example are tested, and the results are compared with those of the Monte Carlo simulation and the classical FM-MEM results, respectively, demonstrating the good performance of the proposed method. [ABSTRACT FROM AUTHOR]

Bayesian optimization (BO) is a sequential optimization strategy that is increasingly employed in a wide range of areas such as materials design. In real-world applications, acquiring high-fidelity (HF) data through physical experiments or HF simulations is the major cost component of BO. To alleviate this bottleneck, multi-fidelity (MF) methods are used to forgo the sole reliance on the expensive HF data and reduce the sampling costs by querying inexpensive low-fidelity (LF) sources whose data are correlated with HF samples. However, existing multi-fidelity BO (MFBO) methods operate under the following two assumptions that rarely hold in practical applications: (1) LF sources provide data that are well correlated with the HF data on a global scale, and (2) a single random process can model the noise in the MF data. These assumptions dramatically reduce the performance of MFBO when LF sources are only locally correlated with the HF source or when the noise variance varies across the data sources. In this paper, we view these two limitations and uncertainty sources and address them by building an emulator that more accurately quantifies uncertainties. Specifically, our emulator (1) learns a separate noise model for each data source, and (2) leverages strictly proper scoring rules in regularizing itself. We illustrate the performance of our method through analytical examples and engineering problems in materials design. The comparative studies indicate that our MFBO method outperforms existing technologies, provides interpretable results, and can leverage LF sources which are only locally correlated with the HF source. [ABSTRACT FROM AUTHOR]

In many design automation applications, accurate segmentation and classification of 3D surfaces and extraction of geometric insight from 3D models can be pivotal. This paper primarily introduces a machine earning-based scheme that leverages graph neural networks for handling 3D geometries, specifically for surface classification. Our model demonstrates superior performance against two state-of-the-art models, PointNet + + and PointMLP, in terms of surface classification accuracy, beating both models. Central to our contribution is the novel incorporation of conformal predictions, a method that offers robust uncertainty quantification and handling with marginal statistical guarantees. Unlike traditional approaches, conformal predictions enable our model to ensure precision, especially in challenging scenarios where mistakes can be highly costly. This robustness proves invaluable in design applications, and as a case in point, we showcase its utility in automating the computational fluid dynamics meshing process for aircraft models based on expert guidance. Our results reveal that our automatically generated mesh, guided by the proposed rules by experts enabled through the segmentation model, is not only efficient but matches the quality of expert-generated meshes, leading to accurate simulations. [ABSTRACT FROM AUTHOR]

Engineering design often involves representation in at least two levels of abstraction: the system-level, represented by lumped parameter models (LPMs), and the geometric-level, represented by distributed parameter models (DPMs). Functional design innovation commonly occurs at the system-level, followed by a geometric-level realization of functional LPM components. However, comparing these two levels in terms of behavioral outcomes can be challenging and time-consuming, leading to delays in design translations between system and mechanical engineers. In this paper, we propose a simulation-free scheme that compares LPMs and spatially discretized DPMs based on their model specifications and behaviors of interest, regardless of modeling languages and numerical methods. We adopt a model order reduction (MOR) technique that a priori guarantees accuracy, stability, and convergence to improve the computational efficiency of large-scale models. Our approach is demonstrated through the model consistency analysis of several mechanical designs, showing its validity, efficiency, and generality. Our method provides a systematic way to compare system-level and geometric-level designs, improving reliability and facilitating design translation. [ABSTRACT FROM AUTHOR]

Machine learning is gaining prominence in mechanical design, offering cost-effective surrogate models to replace computationally expensive models. Nevertheless, concerns persist regarding the accuracy of these models, especially when applied to safety-critical products. To address this challenge, this study investigates methods to account for model prediction errors by incorporating epistemic uncertainty within surrogate models while managing aleatory uncertainty in input variables. The paper clarifies key aspects of modeling coupled epistemic and aleatory uncertainty when using surrogate models derived from noise-free training data. Specifically, the study concentrates on quantifying the impacts of coupled uncertainty in mechanical design through the development of numerical methods based on the concept of the most probable point. This method is particularly relevant for mechanical component design, where failure prevention holds paramount importance, and the probability of failure is low. It is applicable to design problems characterized by probability distributions governing aleatory and epistemic uncertainties in model inputs and predictions. The proposed method is demonstrated using shaft and beam designs as two illustrative examples. The results demonstrate the method's effectiveness in quantifying and mitigating the influence of coupled uncertainty in the design process. [ABSTRACT FROM AUTHOR]

In recent years, the field of structural DNA nanotechnology has advanced rapidly due to transformative design tools. Although these tools have been revolutionary, they still bear one overall limitation of requiring users to fully conceptualize their designs before designing. Recently, a simple computational casting technique was developed using generative optimization strategies to automate the DNA origami nanostructure design. This approach employs a shape annealing algorithm, which creates a formal language of honeycomb nanostructures with shape grammars and drives designs from the language toward a desired configuration using simulated annealing. This initial demonstration of the approach can generate novel scaffold routing schemes for creating solid or hollow structures constrained by the boundaries of polyhedral meshes. The results from the initial approach, particularly from the hollow structures, reveal a challenging design space. This simple technique generates novel scaffold routing schemes that do not replicate the overall polyhedral mesh shape and are limited in their ability to control scaffold path exploration in the design space. This paper demonstrates an approach for achieving different levels of consistent effective wall thicknesses and improving the quality of mesh coverage for hollow structures that can be tuned and optimized by introducing a more refined computational casting technique. We achieve these improvements through changes in the simulated annealing algorithm by adding a Hustin move set algorithm that dynamically adjusts the performance of the overall design and redefining how these hollow designs are articulated. This work illustrates how the technique can navigate a challenging design space to generate effective hollow designs. [ABSTRACT FROM AUTHOR]

Global Sensitivity Analysis (GSA) is the study of the influence of any given input on the outputs of a model. In the context of engineering design, GSA has been widely used to understand both individual and collective contributions of design variables on the design objectives. So far, global sensitivity studies have often been limited to design spaces with only quantitative (numerical) design variables. However, many engineering systems also contain, if not only, qualitative (categorical) design variables in addition to quantitative design variables. In this paper, we integrate Latent Variable Gaussian Process (LVGP) with Sobol' analysis to develop the first metamodel-based mixed-variable GSA method. Through numerical case studies, we validate and demonstrate the effectiveness of our proposed method for mixed-variable problems. Furthermore, while the proposed GSA method is general enough to benefit various engineering design applications, we integrate it with multi-objective Bayesian optimization (BO) to create a sensitivity-aware design framework in accelerating the Pareto front design exploration for metal-organic framework (MOF) materials with many-level combinatorial design spaces. Although MOFs are constructed only from qualitative variables that are notoriously difficult to design, our method can utilize sensitivity analysis to navigate the optimization in the many-level large combinatorial design space, greatly expediting the exploration of novel MOF candidates. [ABSTRACT FROM AUTHOR]

The concept of integrated sustainable product design has recently emerged, aiming to incorporate downstream life cycle performance into the initial product design to enhance sustainability. Various sustainable product design tools based on life cycle assessment or quality function deployment have been established while the impact of reliability on circular practices has received limited attention. Recognizing the critical role of product reliability in post-design performance, this paper develops a product design optimization model that considers the warranty performance and the effect of end-of-use options. The model takes into account the effect of uncertain operating conditions on product reliability. Two optimization goals including the minimization of expected unit life cycle cost and environmental impact are achieved by the model. To demonstrate the benefits of the integrated approach, the model is applied to an electric motor design problem. The results highlight that integrating end-of-use options in the early design phase leads to adjustments in component selection and reliability design. Moreover, the circular utilization of used products enables cost savings throughout the product's life cycle and contributes to environmental impact reduction. Lastly, the study analyzes the effects of operating conditions, warranty policies, and take-back prices for used products on design decisions, providing valuable insights for product designers. [ABSTRACT FROM AUTHOR]

Unmanned engineering systems that execute various operations are becoming increasingly complex relying on a large number of components and their interactions. The reliability, maintainability, and performance optimization of these systems are critical due to their intricate nature and inaccessibility during operations. This paper introduces a new reliability-based optimization framework for planning operational profiles for unmanned systems. The proposed method employs deep learning techniques for subsystem health monitoring, dynamic Bayesian networks for system reliability analysis, and multi-objective optimization schemes for optimizing system performance. The proposed framework systematically integrates these schemes to enable their application to a wide range of tasks, including offline reliability-based optimization of system operational profiles. This framework is the first in the literature that incorporates health monitoring of multi-component systems with causal relationships. Using this hybrid scheme on unmanned systems can improve their reliability, extend their lifespan, and enable them to execute more challenging missions. The proposed framework is implemented and executed using a simulation model for the engine cooling and control system of an unmanned surface vessel. [ABSTRACT FROM AUTHOR]

Deployable polyhedral grippers have attracted increasing attention for their priority in noncontact capturing missions. Enrichment of these grippers may benefit the conduction of various capturing tasks. In this paper, novel deployable polyhedral grippers are presented. A design flow is proposed for the structural designs of diverse grippers. The core problem during the construction is reducible to the structural designs and combination of multiple synchronously deployable modules. Each module, containing three faces connected by two revolute joints, can realize one-degree-of-freedom deployment. Type synthesis of synchronously deployable modules adopting different layouts of revolute joints is conducted. The mobility and kinematics of these modules are analyzed to verify the achieved motion. As examples, four deployable polyhedral grippers based on different polyhedrons and deployment diagrams are presented. The deployment performance of the prototype proves the validity of the proposed design method and exhibits the potential of these deployable polyhedral grippers for diverse capturing missions. [ABSTRACT FROM AUTHOR]

Solving a multiple-criteria optimization problem with severe constraints remains a significant issue in multi-objective evolutionary algorithms. The problem primarily stems from the need for a suitable constraint handling technique. One potential approach is balancing the search in feasible and infeasible regions to find the Pareto front efficiently. The justification for such a strategy is that the infeasible region also provides valuable information, especially in problems with a small percentage of feasibility areas. To that end, this paper investigates the potential of the infeasibility-driven principle based on multiple constraint ranking-based techniques to solve a multi-objective problem with a small feasibility ratio. By analyzing the results from intensive experiments on a set of test problems, including the realistic multi-objective car structure design and actuator design problem, it is shown that there is a significant improvement gained in terms of convergence by utilizing the generalized version of the multiple constraint ranking techniques. [ABSTRACT FROM AUTHOR]

Continuous constraint satisfaction is prevalent in many science and engineering fields. When solving continuous constraint satisfaction problems, it is more advantageous for practitioners to derive all feasible regions (i.e., the solution space) rather than a limited number of solution points, since these feasible regions facilitate design concept generation and design tradeoff evaluation. Several central processing unit (CPU)-based branch-and-prune methods and geometric approximation methods have been proposed in prior research to derive feasible regions for continuous constraint satisfaction problems. However, these methods have not been extensively adopted in practice, mainly because of their high computational expense. To overcome the computational bottleneck of extant CPU-based methods, this paper introduces a GPU-based parallel region classification method to derive feasible regions for continuous constraint satisfaction problems in a reasonable computational time. Using interval arithmetic, coupled with the computational power of GPU, this method iteratively partitions the design space into many subregions and classifies these subregions as feasible, infeasible, and indeterminate regions. To visualize these classified regions in the design space, a planar visualization approach that projects all classified regions into one figure is also proposed. The GPU-based parallel region classification method and the planar visualization approach are validated through two case studies about the bird function and the welded beam design. These case studies show that the method and the approach can solve the continuous constraint satisfaction problems and visualize the results effectively and efficiently. A four-step procedure for implementing the method and the approach in practice is also outlined. [ABSTRACT FROM AUTHOR]

This paper discusses a framework to design elements of the plant and control systems for floating offshore wind turbines in an integrated manner using linear parameter-varying models. Multiple linearized models derived from aero-elastic simulation software in different operating regions characterized by the incoming wind speed are combined to construct an approximate low-fidelity model of the system. The combined model is then used to generate open-loop, optimal control trajectories as part of a nested control co-design strategy that explores the system's power production and stability using the platform pitch tilt as a proxy in the context of crucial plant and control design decisions. The radial distance between the central and outer columns and the diameter of the outer columns of the semisubmersible platform are the plant design variables. The platform stability and power production are studied for different plant design decisions. The effect of plant decisions on subsequent power production and stability response of the floating wind turbine is quantified in terms of the levelized cost of energy. The results show that the inner-loop constraints and the plant design decisions affect the turbine's power and, subsequently, the cost of the system. [ABSTRACT FROM AUTHOR]

Geometric Design and Tolerancing (GD&T) is the language that specifies several design features and, in this paper, is used to deal with the tolerances of Translational Parallel Manipulators (TPMs). TPMs intend to make a platform have only translational motion with respect to the frame (base), but, in practice, TPMs' platforms present undesirable rotation motions due to unavoidable geometric errors in links' sizes. During the machine-element design, geometric errors can be limited by imposing given tolerances on links' sizes and the tighter tolerances are the higher manufacturing costs are. Therefore, dealing with tolerances is the key for designing a TPM with assigned requirements in terms of platform's rotation limits. In this context, this paper moves from the fact that machining processes generate link sizes with values distributed according to Gaussian distributions, whose mean values are the nominal sizes and whose standard deviations depend on the machining process accuracy, to build a novel method that makes a designer able to satisfy an assigned maximum orientation error on the TPM platform. The proposed method consists of two main phases: (a) identification of the geometric parameters that affect platform's position and orientation, and (b) an analysis, based on numerical simulations, that relates the tolerances assigned to the identified parameters and the positioning precision of the platform. The method can be adapted to other types of lower-mobility robots (LMRs). A case study is also discussed to better illustrate the method. [ABSTRACT FROM AUTHOR]

Two-wheeled self-balancing robot (TWSBR) is a mobile robot with a wide application in security, rescue, entertainment, and other fields. To make the robot obtain a larger range of the controllable inclination angle, a reconfigurable mechanism of the moment of inertia is designed for the TWSBR, and the energy consumption of the reconfigurable mechanism is reduced by a gravity compensation mechanism. This paper constructs a virtual equivalent parallel mechanism (VEPM) to model the robot-ground system combining the robot and the ground. The kinematics, dynamic model, and performance indexes of the VEPM are solved based on the vector method, the Lagrangian dynamics, and the screw theory. Then, the dimensions of the mechanism are optimized based on the comprehensive performance analysis. Finally, the effectiveness of the optimization algorithm and gravity compensation mechanism is verified through simulation and motion experiments. The reconfigurable mechanism enables the TWSBR to stand up, step up, and surmount obstacles. The performance analysis and optimal design approaches proposed in this paper have positive significance for the systematic modeling and optimal design of two-wheeled and two-legged robots. [ABSTRACT FROM AUTHOR]

This paper proposes a general method to generate spherical conjugated curves based on their contact path. The main objective of generating conjugated curves is to use them as gearing tooth profiles. The derivation is based on the prescribed spherical contact path, the equation of meshing, and the rigid body motion between two bodies. This paper demonstrates the method by assigning great circle and small circle contact paths in circular pitch pair transmission to generate conjugated curves. With the great circle contact path, the conjugated curves are exact spherical involute, and with the small circle contact path, the conjugated curves are spherical cycloid. The contact properties of the conjugated curves, such as induced curvature and the sliding ratio, are also provided with mathematical equations. Based on the results, the procedures and the geometries between the planar and spherical contact path methods have corresponding relationships. In contrast to the Camus theorem, the exact spherical involute could be generated from a similar procedure of planar involute cases. The ultimate goal of this research topic is to propose a general approach to generating conjugated profiles in planar, spherical, and spatial cases. The successful derivation of the spherical cases in this paper paves the way for spatial cases in the future. [ABSTRACT FROM AUTHOR]

Generative adversarial networks (GANs) have shown remarkable success in various generative design tasks, from topology optimization to material design, and shape parametrization. However, most generative design approaches based on GANs lack evaluation mechanisms to ensure the generation of diverse samples. In addition, no GAN-based generative design model incorporates user sentiments in the loss function to generate samples with high desirability from the aggregate perspectives of users. Motivated by these knowledge gaps, this paper builds and validates a novel GAN-based generative design model with an offline design evaluation function to generate samples that are not only realistic but also diverse and desirable. A multimodal data-driven design evaluation (DDE) model is developed to guide the generative process by automatically predicting user sentiments for the generated samples based on large-scale user reviews of previous designs. This paper incorporates DDE into the StyleGAN structure, a state-of-the-art GAN model, to enable data-driven generative processes that are innovative and user-centered. The results of experiments conducted on a large dataset of footwear products demonstrate the effectiveness of the proposed DDE-GAN in generating high-quality, diverse, and desirable concepts. [ABSTRACT FROM AUTHOR]

This paper proposes a novel framework for building semantic networks from a seed design statement using Recursive Object Modeling (ROM), Word2Vec language modeling, and vector semantic-based method. Semantic Scholar API was used to retrieve abstracts of scientific papers to build ROM-based Semantic Networks to address the design problem implied in the seed design statement, following Environment Analysis from Environment-Based Design (EBD) methodology. The proposed framework was applied to construct the semantic network for a project to design aircraft braking systems, which demonstrates the framework's efficiency. The presented research makes two major contributions: a ROM-based phrase extractor and a domain-specific language model, which is trained on the automatically collected literature abstracts. Using a manually created and assessed truth set containing 100 pairs of abstract-key phrases, the phrase extractor was evaluated by benchmarking it with two existing off-the-shelf key phrase extraction algorithms: TextRank and Rake. The ROM-based phrase extractor extracted most key phrases from target domains and showed higher precision, recall, and F-1 scores than other methods. Meanwhile, the trained project-specific language model was evaluated using the NASA thesaurus. We randomly sampled 457 pairs of connected domain-specific terms related to aircraft braking and landing knowledge. Our Skip-gram model was compared with Google's pre-trained word2vec model and a baseline word2vec model. The results demonstrated that our language model could detect the most pairs of concepts from the NASA thesaurus. The generated semantic network can be applied to design information retrieval, computer-aided design idea generation, cross-domain communication support system, and designer training tool. [ABSTRACT FROM AUTHOR]

Identifying new problems and providing solutions are necessary tasks for design engineers at early-stage product design and development. A new problem fosters innovative and inventive solutions. Hence, it is expected that engineering design pedagogy and practice should equally focus on engineering design problem-exploring (EDPE)--a process of identifying or coming up with a new problem or need at the early-stage of design, and engineering design problem-solving (EDPS)--a process of developing engineering design solutions to a given problem. However, studies suggest that EDPE is scarcely practiced or given attention to in academia and industry, unlike EDPS. The aim of this paper is to investigate the EDPE process for any information relating to its scarce practice in academia and industry. This is to explore how emerging technologies could support the process. Natural models and phenomena that explain the EDPE process are investigated, including the "rational" and "garbage can" models, and associated challenges identified. A computational framework that mimics the natural EDPE process is presented. The framework is based on Markovian model and computational technologies, including machine learning. A case study is conducted with a sample size of 43 participants drawn worldwide from the engineering design community in academia and industry. The case study result shows that the first-of-its-kind computational EDPE framework presented in this paper supports both novice and experienced design engineers in EDPE. [ABSTRACT FROM AUTHOR]

Conceptual design is the foundational stage of a design process that translates ill-defined design problems into low-fidelity design concepts and prototypes through design search, creation, and integration. In this stage, product shape design is one of the most paramount aspects. When applying deep learning-based methods to product shape design, two major challenges exist: (1) design data exhibit in multiple modalities and (2) an increasing demand for creativity. With recent advances in deep learning of cross-modal tasks (DLCMTs), which can transfer one design modality to another, we see opportunities to develop artificial intelligence (AI) to assist the design of product shapes in a new paradigm. In this paper, we conduct a systematic review of the retrieval, generation, and manipulation methods for DLCMT that involve three cross-modal types: text-to-3D shape, text-to-sketch, and sketch-to-3D shape. The review identifies 50 articles from a pool of 1341 papers in the fields of computer graphics, computer vision, and engineering design. We review (1) state-of-the-art DLCMT methods that can be applied to product shape design and (2) identify the key challenges, such as lack of consideration of engineering performance in the early design phase that need to be addressed when applying DLCMT methods. In the end, we discuss the potential solutions to these challenges and propose a list of research questions that point to future directions of data-driven conceptual design. [ABSTRACT FROM AUTHOR]

Design representations play a pivotal role in the design process. In particular, design representations enable the formation of a shared understanding between team members, enhancing team performance. This paper explores the relationship between design representation modality (low-fidelity prototypes and sketches) and shared understanding among designers during communicative acts between design dyads. A mixed-methods study with 44 participants was conducted to investigate if representation modality affects shared understanding and identifies the factors that shape shared understanding during communication. Quantitative results suggest that low-fidelity prototypes and sketches did not significantly differ in terms of the shared understanding they facilitated within dyads. Qualitative analysis identified four factors at the representation- and actor-level that influence how shared understanding is built between individuals during design communication. This research extends our understanding of the utility of design representations given the needs of communicative contexts; specifically, this work demonstrates that designers must understand the perspectives of listeners during communication to create representations that accurately represent the information that a listener seeks to gain. [ABSTRACT FROM AUTHOR]

In the commercial freight industry, tire retreading decisions are often conservative due to limited knowledge of a tire's remaining service life. This practice leads to increased costs and material waste. This paper proposes a machine learning-based approach for estimating tire casing life and retreadability, focusing on usage data rather than wear information. This approach could extend the tire's lifespan and reduce landfill waste. Data integration from diverse tire casing measurement sources presents challenges, including imbalanced removal data. Our methodology addresses these challenges by using historical inspection, telematics, and finite element modeling (FEM) datasets. We introduce "Tire Casing Energy" as a comprehensive usage input and apply a Variance-Reduction Synthetic Minority Oversampling Technique (VR-SMOTE) for data imbalance rectification. A random forest model is used to estimate the state of the tire casing and the casing removal probability, with Bayesian optimization applied for hyperparameter tuning, enhancing model accuracy. The proposed prediction framework is able to differentiate different truck fleets and tire locations based on their usage parameters. With the aid of this machine learning model, the importance and sensitivity of different tire usage parameters can be obtained, which is beneficial to maximize tire life. [ABSTRACT FROM AUTHOR]

Designing mechatronic products requires interdisciplinary skills and as products become more complex, the design of mechatronic systems plays a critical role. To minimize waste production and pollution, a shift toward a circular economy is necessary, with mechatronic products being particularly impacted by such policies. Repairing plays a key part in achieving a circular economy. Through repairability, the product lifespan can be extended, and combined with maintenance the rate of product replacement can be reduced. Within this context, the goal of this paper is to propose a design methodology (based on the EN 45554:2020 standard) for generating and implementing eco-design rules for disassembly and repair. The methodology has four phases, the first one is the identification of target components (those that are more likely to fail during the lifespan). The second phase encompasses the experimental disassembly analysis which can be manual or virtual. The third phase is the assessment of the disassemblability index which includes the analysis of parameters that affect the disassembly phase. The last phase is the implementation of the eco-design methodology for all the components that do not meet the minimum repairability requirements. A case study of electro-mechanical ovens is presented, targeting replaceable components. The results show that the use of this framework and the eco-design actions derived from it are successful in improving the repairability of the product and increasing the disassemblability index (30% on average) through a virtual analysis. A sensitivity analysis has been conducted to study the impact of parameter weight modification. This research contributes to advancing repairability and supporting the circular economy paradigm in mechatronic product design. [ABSTRACT FROM AUTHOR]

Developable mechanisms provide unparalleled compactness and deployability. This paper explores the kinematic behavior of developable mechanisms that conform to regular cylindrical surfaces. Design considerations that aid in the dimensional synthesis of these mechanisms are developed and demonstrated through case studies. The design implications, limitations, and opportunities associated with regular cylindrical developable mechanisms are discussed through the lens of both an analytical and graphical methods. [ABSTRACT FROM AUTHOR]

To optimize structures and monitor their health, it is essential to build an accurate dynamic analysis model. However, traditional modeling methods based solely on physical information or data-driven techniques may not suffice for many engineering applications. While physical models can accurately simulate complex equipment, they may also incur high computational time. On the other hand, data-driven models may improve computational efficiency but are subject to significant deviations due to the influence of training data. To address these challenges, the Physics-Informed Neural Network (PINN) has gained popularity for imposing physical constraints during the training process, leading to better generalization capabilities with fewer data samples. This paper proposes a physics-informed hybrid modeling (PIHM) approach that combines a reduced-order model, kernel functions, and dynamic equations to predict dynamic output with limited training data and physical information. The method integrates prior physics information into function approximation by incorporating the reduced dynamic equation into a surrogate modeling framework. The loss function considers inertial and damping effects, ensuring physical plausibility. Unlike traditional PINN applications, the proposed modeling method is more explainable, as the trained model can be expressed in function form with engineering interpretation. The approach is verified with a real-world engineering example (telehandler boom) under complex load conditions, demonstrating accuracy, efficiency, and physical plausibility. Overall, the proposed method offers promising capabilities in solving problems where high-fidelity simulation is challenging. [ABSTRACT FROM AUTHOR]

As additive manufacturing (AM) usage increases, designers who wish to maximize AM's potential must reconsider the traditional manufacturing (TM) axioms they may be more familiar with. While research has previously investigated the potential influences that can affect the designs produced in concept generation, little research has been done explicitly targeting the manufacturability of early-stage concepts and how previous experience and the presenting of priming content in manufacturing affect these concepts. The research in this paper addresses this gap in knowledge, specifically targeting differences in concept generation due to designer experience and presenting design for traditional manufacturing (DFTM) and design for additive manufacturing (DFAM) axioms. To understand how designers approach design creation early in the design process and investigate potential influential factors, participants in this study were asked to complete a design challenge centered on concept generation. Before this design challenge, a randomized subset of these participants received priming content on DFTM and DFAM considerations. These participants' final designs were evaluated for both traditional manufacturability and additive manufacturability and compared against the final designs produced by participants who did not receive the priming content. Results show that students with low manufacturing experience levels create designs that are more naturally suited for TM. Additionally, as designers' manufacturing experience levels increase, there is an increase in the number of designs more naturally suited for AM. This correlates with a higher self-reported use of DFAM axioms in the evaluation of these designs. These results suggest that students with high manufacturing experience levels rely on their previous experience when it comes to creating a design for either manufacturing process. Lastly, while the manufacturing priming content significantly influenced the traditional manufacturability of the designs, the priming content did not increase the number of self-reported design for manufacturing (DFM) axioms in the designs. [ABSTRACT FROM AUTHOR]

This paper presents a 3D material mask overlay topology optimization approach using truncated octahedron elements and spheroidal masks. Truncated octahedron elements provide face connectivity between two juxtaposed elements, thus eliminating singular solutions inherently. A novel meshing scheme with Tetra-Kai-Decaheral or TKD (generic case of truncated octahedron) elements is proposed. The scheme is extended to parameterized generic-shaped domains. Various benefits of implementing the elements are also highlighted, and the corresponding finite element is introduced. Spheroidal negative masks are employed to determine the material within the elements. Seven design variables define each mask. A material density formulation is proposed, and sensitivity analysis for gradient-based optimization is developed. fminconMATLAB matlab function is used for the optimization. The efficacy and success of the approach are demonstrated by solving structures and compliant mechanism design problems. Compliance is minimized for the former, whereas a multi-criteria arising due to flexibility and stiffness measures is extremized for optimizing the mechanisms. Convergence of the optimization is smooth. The volume constraint is satisfied and remains active at the end of the optimization. [ABSTRACT FROM AUTHOR]

Can we provide evidence-based guidance to instructors to improve the delivery of the course based on students' reflection on doing? Over three years at the University of Oklahoma, Norman, USA, we have collected about 18,000 Take-aways from almost 400 students who participated in an undergraduate design, build, and test course. In this paper, we illustrate the efficacy of using the Latent Dirichlet Algorithm to respond to the question posed above. We describe a method to analyze the Take-aways using a Latent Dirichlet Allocation (LDA) algorithm to extract topics from the Take-away data and then relate the extracted topics to instructors' expectations using text similarity. The advantage of the LDA algorithm is anchored in that it provides a means for summarizing large amount of take-away data into several key topics so that instructors can eliminate the labor-intensive evaluation of it. By connecting and comparing what students learned (embodied in Take-aways) and what instructors expected the students to learn (embodied in stated Principles of Engineering Design), we provide evidence-based guidance to instructors on how to improve the delivery of AME4163: Principles of Engineering Design. Our objective in this paper is to introduce a method for quantifying text data to facilitate an instructor to modify the content and delivery of the next version of the course. The proposed method can be extended to other courses patterned after AME4163 to generate similar data sets covering student learning and instructor expectations, and the LDA algorithm can be used for dealing with the large amount of textual data embodied in students' Take-aways. [ABSTRACT FROM AUTHOR]

This paper presents a novel deployable antenna mechanism for synthetic aperture radar (SAR) satellites. First, the topological structure of the new deployable mechanism is designed based on the five conditions expected to be satisfied. Then, the kinematic model of the new mechanism is fully established based on vector equations and structural symmetry. Third, the deployed/folded ratio and interference of the new mechanism are analyzed. Finally, a typical numerical example is used to illustrate the effectiveness of the theoretical analysis, and a physical prototype is developed to show the fabrication feasibility of the new deployable mechanism. Compared with the latest counterpart for SAR satellites in the existing literature, the new deployable mechanism of this paper has a simpler driving system, simpler deployment movement, and no prismatic pairs with cold welding problems. With these characteristics, the presented new mechanism has a good application prospect in SAR satellites. [ABSTRACT FROM AUTHOR]

Designers are challenged to create sustainable products that succeed in the marketplace, often relying on life cycle analyses to identify engineered sustainable features while neglecting perceived-as-sustainable (PAS) features. PAS features may not contribute to engineered sustainability but are identified by customers as sustainable. In previous papers, we proposed methods for extracting PAS features from online reviews using machine learning techniques and validating them using collage placement techniques. We demonstrated our methods using French presses (and other products). In this paper, we combined design and marketing approaches to test previously extracted PAS features in terms of purchasing products that include PAS features, as compared to others that do not. We built a simulated Amazon shopping experience using incentive alignment and constructed a within-subject, fractional factorial design with a variety of product features and physical appearances. We collected data on purchase intent, willingness to pay, and sustainability rating. We found that participants opted to purchase products with PAS features more often than products with features that are not PAS, termed "dummy" features. Participants also indicated they were willing to pay more for products with PAS features and rated those products as more sustainable, despite the features not contributing to engineered sustainability. Our findings demonstrate the potential value of identifying and including PAS features in sustainable products and a new application for shopping simulation experiments in design research. We recommend that sustainable designers include both engineered and PAS features in sustainable products to align with customer needs, drive purchasing decisions, and potentially increase profitability. [ABSTRACT FROM AUTHOR]

Origami patterns have been used in the design of deployable arrays. In engineering applications, paper creases are often replaced with surrogate folds by providing a hinge-like function to enable motion. Overconstraint observed in multivertex origami patterns combined with imperfect manufacturing may cause the resulting mechanisms to bind. The removal of redundant constraints decreases the likelihood of binding, may simplify the overall system, and may decrease the actuation force by reducing friction and other resistance to motion. This paper introduces a visual and iterative approach to eliminating redundant constraints in origami-based mechanisms through joint removal. Several techniques for joint removal are outlined and illustrated to reduce overconstraints in origami arrays. [ABSTRACT FROM AUTHOR]

Delta-like architectures are widely used for fast pick-and-place applications. When rotational degrees-of-freedom are required to perform a task, one or more UPU kinematic chains are usually added to transmit the torques from motors located on the base to the platform, in order to actuate a wrist. Packaging applications usually require five degrees-of-freedom, and two UPU chains are then used to actuate two rotational degrees-of-freedom (DOFs) on the end-effector. However, the UPU chain induces significant limitations for industrial use: it significantly constrains the workspace along the vertical direction and implies a backlash in the universal joints degrading the accuracy of the robot. In this paper, we investigate an alternative to the UPU kinematic chain for designing delta-like robots with five DOFs. Indeed, the actuation of a two-DOFs wrist is performed through the use of a kinematic chain based on a succession of parallelograms associated with a delta-like leg. After a description of the kinematic models of the modified leg and an analysis of its singularities, a design optimization procedure is presented in order to define suitable geometric parameters for a given industrial application. Finally, a prototype is presented and its performances are evaluated. [ABSTRACT FROM AUTHOR]

Recently, online user-generated data have emerged as a valuable source for consumer product research. However, most studies have neglected the brand effect, although it is a significant factor in conventional market research. This paper demonstrates the importance of brands in data-driven design using online reviews. Specifically, this study utilizes game theory and suggests a game setting representing market competition. Elements of the game are determined based on online data analysis. The proposed approach consists of four stages. The first stage divides online customers into different segments and analyzes them to extract the feature importance of each brand in each segment. The importance is based on the positive term frequency of features, and it becomes the customer's partial utility for each feature. The second stage defines the specification of product candidates and calculates their costs. This study refers to real market datasets (bill of materials) available online. At this point, the game is all set. The third stage finds the Nash equilibrium of the designed game, and the final stage compares the optimal strategy for a product portfolio with and without brand consideration. The suggested approach was tested on smartphone reviews from Amazon. The result shows that the lack of brand consideration leads a company to choose a non-optimal product strategy, illustrating the significance of the brand factor. [ABSTRACT FROM AUTHOR]

Power-split hybrid transmissions are the core components of power-split hybrid electric vehicles (HEVs), and the quest for a more energy-efficient and higher-performing power-split hybrid transmission has long been the focus of study. In contrast to previously published methodologies, this paper proposes a novel approach for directly synthesizing power-split hybrid transmissions that makes use of the results of previously synthesized planetary gear trains (PGTs) rather than necessitating a resynthesis of their PGTs. A new topological graph that can construct a bridge between the PGTs and power-split hybrid transmission has been developed, reducing the computational complexity in the synthesis process. The new topological graph is obtained by adding topological characteristics of the power-split hybrid transmission to the PGT graph. A standard structure matrix is proposed to further screen out all the isomorphic configurations. The present method can generate various types of multi-PGT hybrid transmissions while avoiding mechanical structural interference. The design process of configurations for power-split hybrid transmission with three-column PGTs (3-PGT) is used as an example to prove the rationality of the method. [ABSTRACT FROM AUTHOR]

Design heuristics are traditionally used as qualitative principles to guide the design process, but they have also been used to improve the efficiency of design optimization. Using design heuristics as soft constraints or search operators has been shown for some problems to reduce the number of function evaluations needed to achieve a certain level of convergence. However, in other cases, enforcing heuristics can reduce diversity and slow down convergence. This paper studies the question of when and how a given set of design heuristics represented in different forms (soft constraints, repair operators, and biased sampling) can be utilized in an automated way to improve efficiency for a given design problem. An approach is presented for identifying promising heuristics for a given problem by estimating the overall impact of a heuristic based on an exploratory screening study. Two impact indices are formulated: weighted influence index and hypervolume difference index. Using this approach, the promising heuristics for four design problems are identified and the efficacy of selectively enforcing only these promising heuristics over both enforcement of all available heuristics and not enforcing any heuristics is benchmarked. In all problems, it is found that enforcing only the promising heuristics as repair operators enables finding good designs faster than by enforcing all available heuristics or not enforcing any heuristics. Enforcing heuristics as soft constraints or biased sampling functions results in improvements in efficiency for some of the problems. Based on these results, guidelines for designers to leverage heuristics effectively in design optimization are presented. [ABSTRACT FROM AUTHOR]

Design researchers have struggled to produce quantitative predictions for exactly why and when diversity might help or hinder design search efforts. This paper addresses that problem by studying one ubiquitously used search strategy--Bayesian optimization (BO)--on a 2D test problem with modifiable convexity and difficulty. Specifically, we test how providing diverse versus non-diverse initial samples to BO affects its performance during search and introduce a fast ranked-determinantal point process method for computing diverse sets, which we need to detect sets of highly diverse or non-diverse initial samples. We initially found, to our surprise, that diversity did not appear to affect BO, neither helping nor hurting the optimizer's convergence. However, follow-on experiments illuminated a key trade-off. Non-diverse initial samples hastened posterior convergence for the underlying model hyper-parameters--a model building advantage. In contrast, diverse initial samples accelerated exploring the function itself--a space exploration advantage. Both advantages help BO, but in different ways, and the initial sample diversity directly modulates how BO trades those advantages. Indeed, we show that fixing the BO hyper-parameters removes the model building advantage, causing diverse initial samples to always outperform models trained with non-diverse samples. These findings shed light on why, at least for BO-type optimizers, the use of diversity has mixed effects and cautions against the ubiquitous use of space-filling initializations in BO. To the extent that humans use explore-exploit search strategies similar to BO, our results provide a testable conjecture for why and when diversity may affect human-subject or design team experiments. [ABSTRACT FROM AUTHOR]

Generative design (GD) techniques have been proposed to generate numerous designs at early design stages for ideation and exploration purposes. Previous research on GD using deep neural networks required tedious iterations between the neural network and design optimization, as well as post-processing to generate functional designs. Additionally, design constraints such as volume fraction could not be enforced. In this paper, a two-stage non-iterative formulation is proposed to overcome these limitations. In the first stage, a conditional generative adversarial network (cGAN) is utilized to control design parameters. In the second stage, topology optimization (TO) is embedded into cGAN (cGAN + TO) to ensure that desired functionality is achieved. Tests on different combinations of loss terms and different parameter settings within topology optimization demonstrated the diversity of generated designs. Further study showed that cGAN + TO can be extended to different load and boundary conditions by modifying these parameters in the second stage of training without having to retrain the first stage. Results demonstrate that GD can be realized efficiently and robustly by cGAN+TO. [ABSTRACT FROM AUTHOR]

A key part of an engineer's purpose is to create products and services that benefit society, or, in other words, to create products with a positive social impact. While engineers have many predictive models to aid in making design decisions about the functional performance or safety of a product, very few models exist for estimating or planning for the wide range of social impacts an engineered product can have. To model social impact, a model must contain representations of both the product and society. Agent-based modeling is a tool that can model society and incorporate social impact factors. In this paper, we investigate factors that have historically limited the usefulness of product adoption agent-based models and predictive social impact models through a systematic literature review. Common themes of limiting factors are identified, steps are presented to improve the usefulness of agent-based product adoption models and predictive social impact models, and a general process for the creation of agent-based social impact models is presented. Improving the usefulness of these predictive models can aid engineers in making better design decisions. Predictive social impact models can help identify areas in the design space to improve the social impact of products. When coupled with existing design methods, agent-based predictive social impact models can help increase the probability that a product achieves positive social impact. [ABSTRACT FROM AUTHOR]

G-Lattices (proposed by Armanfar and Gunpinar) are a group of novel periodic and strut-based lattice structures for additive manufacturing. It has been demonstrated that these structures have superior mechanical properties under compression compared to conventional lattice structures. This paper introduces an extension of G-Lattices (i.e., reinforced G-Lattices) that also have better mechanical performance under inclined (compression) loading conditions. For different inclined loads, separate reinforced G-Lattices are first optimized, and a G-Lattice library is formed. For a part under loading, displacement vectors in each unit cell (cubic domains within the inner region of the part) are then extracted. Based on these vectors, (pre-optimized) reinforced G-Lattices are selected from the G-Lattice library and utilized (as infills) in the unit cells. This process is called G-Puzzling. As a proof of concept, parts under three different inclined loading conditions are infilled using reinforced G-Lattices and investigated based on stiffness-over-volume ratios. According to these experiments, the resulting parts, on average, exhibit more than 30% better mechanical performance compared to FBCCZ (a conventional lattice structure). [ABSTRACT FROM AUTHOR]

Accurate analysis of rare failure events with an affordable computational cost is often challenging in many engineering applications, particularly for problems with high-dimensional system inputs. The extremely low probabilities of occurrence often lead to large probability estimation errors and low computational efficiency. Thus, it is vital to develop advanced probability analysis methods that are capable of providing robust estimations of rare event probabilities with narrow confidence bounds. The general method of determining confidence intervals of an estimator using the central limit theorem faces the critical obstacle of low computational efficiency. This is a side effect of the widely used Monte Carlo method, which often requires a large number of simulation samples to derive a reasonably narrow confidence interval. In this paper, a new probability analysis approach is developed which can be used to derive the estimates of rare event probabilities efficiently with narrow estimation bounds simultaneously for high-dimensional problems and complex engineering systems. The asymptotic behavior of the developed estimator is proven theoretically without imposing strong assumptions. An asymptotic confidence interval is established for the developed estimator. The presented study offers important insights into the robust estimations of the probability of occurrences for rare events. The accuracy and computational efficiency of the developed technique are assessed with numerical and engineering case studies. Case study results have demonstrated that narrow bounds can be obtained efficiently using the developed approach with the true values consistently located within the estimation bounds. [ABSTRACT FROM AUTHOR]

In this paper, we present "BIKED," a dataset composed of 4500 individually designed bicycle models sourced from hundreds of designers. We expect BIKED to enable a variety of data-driven design applications for bicycles and support the development of data-driven design methods. The dataset is comprised of a variety of design information including assembly images, component images, numerical design parameters, and class labels. In this paper, we first discuss the processing of the dataset, and then highlight some prominent research questions that BIKED can help address. Of these questions, we further explore the following in detail: (1) How can we explore, understand, and visualize the current design space of bicycles and utilize this information? We apply unsupervised embedding methods to study the design space and identify key takeaways from this analysis. (2) When designing bikes using algorithms, under what conditions can machines understand the design of a given bike? We train a multitude of classifiers to understand designs, then examine the behavior of these classifiers through confusion matrices and permutation-based interpretability analysis. 3) Can machines learn to synthesize new bicycle designs by studying existing ones? We test Variational Autoencoders on random generation, interpolation, and extrapolation tasks after training on BIKED data. The dataset and code are available online. [ABSTRACT FROM AUTHOR]

Although artificial intelligence (AI) systems which support composition using predictive text are well established, there are no analogous technologies for mechanical design. Motivated by the vision of a predictive system that learns from previous designs and can interactively provide a list of established feature alternatives to the designer as design progresses, this paper describes the theory, implementation, and assessment of an intelligent system that learns from a family of previous designs and generates inferences using a form of spatial statistics. The formalism presented models 3D design activity as a "marked point process" that enables the probability of specific features being added at particular locations to be calculated. Because the resulting probabilities are updated every time a new feature is added, the predictions will become more accurate as a design develops. This approach allows the cursor position on a CAD model to implicitly define a spatial focus for every query made to the statistical model. The authors describe the mathematics underlying a statistical model that amalgamates the frequency of occurrence of the features in the existing designs of a product family. Having established the theoretical foundations of the work, a generic six-step implementation process is described. This process is then illustrated for circular hole features using a statistical model generated from a dataset of hydraulic valves. The paper describes how the positions of each design's extracted hole features can be homogenized through rotation and scaling. Results suggest that within generic part families (i.e., designs with common structure), a marked point process can be effective at predicting incremental steps in the development of new designs. [ABSTRACT FROM AUTHOR]

Design concept evaluation is a key process in the new product development process with a significant impact on the product's success and total cost over its life cycle. This paper is motivated by two limitations of the state-of-the-art in concept evaluation: (1) the amount and diversity of user feedback and insights utilized by existing concept evaluation methods such as quality function deployment are limited. (2) Subjective concept evaluation methods require significant manual effort which in turn may limit the number of concepts considered for evaluation. A deep multimodal design evaluation (DMDE) model is proposed in this paper to bridge these gaps by providing designers with an accurate and scalable prediction of new concepts' overall and attribute-level desirability based on large-scale user reviews on existing designs. The attribute-level sentiment intensities of users are first extracted and aggregated from online reviews. A multimodal deep regression model is then developed to predict the overall and attribute-level sentiment values based on the features extracted from orthographic product images via a fine-tuned ResNet-50 model and from product descriptions via a fine-tuned bidirectional encoder representations from transformer model and aggregated using a novel self-attention-based fusion model. The DMDE model adds a data-driven, user-centered loop within the concept development process to better inform the concept evaluation process. Numerical experiments on a large dataset from an online footwear store indicate a promising performance by the DMDE model with 0.001 MSE loss and over 99.1% accuracy. [ABSTRACT FROM AUTHOR]

Mind-mapping is useful for externalizing ideas and their relationships surrounding a central problem. However, balancing between the exploration of different aspects (breadth) of the problem with respect to the detailed exploration of each of its aspects (depth) can be challenging, especially for novices. The goal of this paper is to investigate the notion of "reflection-in-design" through a novel interactive digital mind-mapping workflow that we call "QCue." The idea behind this workflow is to incorporate the notion of reflective thinking through two mechanisms: (1) offering suggestions to promote depth exploration through user's queries (Q) and (2) asking questions (Cue) to promote reflection for breadth exploration. This paper is an extension of our prior work (Chen et al., 2020, "Qcue: Queries and Cues for Computer-Facilitated Mind-Mapping," Proceedings of Graphics Interface 2020, GI 2020, Canadian Human-Computer Communications Society/Société canadienne du Dialogue Human-Machine, pp. 125-136) where our focus was mainly on the algorithmic development and implementation of a cognitive support mechanism behind QCue enabled by ConceptNet (a graph-based rich ontology with "commonsense" knowledge). In this extended work, we first present a detailed summary of how QCue facilitated the breadth-depth balance in a mind-mapping task. Second, we present a comparison between QCue and conventional digital mind-mapping, i.e., without our algorithm through a between-subjects user study. Third, we present new detailed analysis on the usage of different cognitive mechanisms provided by QCue. We further consolidate our prior quantitative analysis and build a connection with our observational analysis. Finally, we discuss in detail the different cognitive mechanisms provided by QCue to stimulate reflection in design. [ABSTRACT FROM AUTHOR]

Metamodel technology provides an efficient method to approximate complex engineering design problems. However, the approximation for high-dimensional problems usually requires a large number of samples for most traditional metamodeling methods, which leads to the difficulty of "curse of dimensionality." To address the aforementioned issue, this paper presents the Net-high dimension model representation (HDMR) method based on the Cut-HDMR framework. Compared with traditional HDMR modeling, the Net-HDMR method incorporates two novel modeling approaches that improve the modeling efficiency of high-dimensional problems. The first approach enhances the modeling accuracy of HDMR by using the net function interpolation method to decompose the component functions into a series of one-dimensional net functions. The second approach adopts the CV-Voronoi sequence sampling method to effectively represent one-dimensional net functions with limited samples. Overall, the proposed method transforms complex high-dimensional problems into fitting finite one-dimensional splines, thereby increasing the modeling efficiency while ensuring approximate accuracy. Six numerical benchmark examples with different dimensions are examined to demonstrate the accuracy and efficiency of the proposed Net-HDMR. An engineering problem of thermal stress and deformation analysis for a jet engine turbine blade was introduced to verify the engineering feasibility of the proposed Net-HDMR. [ABSTRACT FROM AUTHOR]

Life-cycle reliability analysis can effectively estimate and present the changes in the state of safety for structures under dynamic uncertainties during their lifecycle. The first-crossing approach is an efficient way to evaluate time-variant reliability-based on the probabilistic characteristics of the first-crossing time point (FCTP). However, the FCTP model has a number of critical challenges, such as computational accuracy. This paper proposes an adaptive first-crossing approach for the time-varying reliability of structures over their whole lifecycle, which can provide a tool for cycle-life reliability analysis and design. The response surface of FCTP regarding input variables is first estimated by performing support vector regression. Furthermore, the adaptive learning algorithm for training support vector regression is developed by integrating the uniform design and the central moments of the surrogate model. Then, the convergence condition, which combines the raw moments and entropy of the first-crossing probability distribution function (PDF), is constructed to build the optimal first-crossing surrogate model. Finally, the first-crossing PDF is solved using the adaptive kernel density estimation to obtain the time-variant reliability trend during the whole lifecycle. Examples are demonstrated to specify the proposed method in applications. [ABSTRACT FROM AUTHOR]