Abstract 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.
{"title":"Design Considerations for the Dimensional Synthesis of Cylindrical Developable Mechanisms","authors":"Henry Vennard, Jacob Greenwood, Jared Butler","doi":"10.1115/1.4063405","DOIUrl":"https://doi.org/10.1115/1.4063405","url":null,"abstract":"Abstract 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.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135043602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract 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.
{"title":"Toward an Online Monitoring of Structural Performance Based on Physics-Informed Hybrid Modeling Method","authors":"Xiwang He, Kunpeng Li, Shuo Wang, Xiaonan Lai, Liangliang Yang, Ziyun Kan, Xueguan Song","doi":"10.1115/1.4063403","DOIUrl":"https://doi.org/10.1115/1.4063403","url":null,"abstract":"Abstract 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.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135303051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Many complex engineering systems can be represented in a topological form, such as graphs. This paper utilizes a machine learning technique called Geometric Deep Learning (GDL) to aid designers with challenging, graph-centric design problems. The strategy presented here is to take the graph data and apply GDL to seek the best realizable performing solution effectively and efficiently with lower computational costs. This case study used here is the synthesis of analog electrical circuits that attempt to match a specific frequency response within a particular frequency range. Previous studies utilized an enumeration technique to generate 43,249 unique undirected graphs presenting valid potential circuits. Unfortunately, determining the sizing and performance of many circuits can be too expensive. To reduce computational costs with a quantified trade-off in accuracy, the fraction of the circuit graphs and their performance are used as input data to a classification-focused GDL model. Then, the GDL model can be used to predict the remainder cheaply, thus, aiding decision-makers in the search for the best graph solutions. The results discussed in this paper show that additional graph-based features are useful, favorable total set classification accuracy of 80% in using only 10% of the graphs, and iteratively-built GDL models can further subdivide the graphs into targeted groups with medians significantly closer to the best and containing 88.2 of the top 100 best-performing graphs on average using 25% of the graphs.
{"title":"ON THE USE OF GEOMETRIC DEEP LEARNING FOR THE ITERATIVE CLASSIFICATION AND DOWN-SELECTION OF ANALOG ELECTRIC CIRCUITS","authors":"Anthony Sirico, Daniel R. Herber","doi":"10.1115/1.4063659","DOIUrl":"https://doi.org/10.1115/1.4063659","url":null,"abstract":"Abstract Many complex engineering systems can be represented in a topological form, such as graphs. This paper utilizes a machine learning technique called Geometric Deep Learning (GDL) to aid designers with challenging, graph-centric design problems. The strategy presented here is to take the graph data and apply GDL to seek the best realizable performing solution effectively and efficiently with lower computational costs. This case study used here is the synthesis of analog electrical circuits that attempt to match a specific frequency response within a particular frequency range. Previous studies utilized an enumeration technique to generate 43,249 unique undirected graphs presenting valid potential circuits. Unfortunately, determining the sizing and performance of many circuits can be too expensive. To reduce computational costs with a quantified trade-off in accuracy, the fraction of the circuit graphs and their performance are used as input data to a classification-focused GDL model. Then, the GDL model can be used to predict the remainder cheaply, thus, aiding decision-makers in the search for the best graph solutions. The results discussed in this paper show that additional graph-based features are useful, favorable total set classification accuracy of 80% in using only 10% of the graphs, and iteratively-built GDL models can further subdivide the graphs into targeted groups with medians significantly closer to the best and containing 88.2 of the top 100 best-performing graphs on average using 25% of the graphs.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134975089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Debrina Roy, Nicole Calpin, Kathy Cheng, Alison Olechowski, Andrea Arguelles, Nicolás F. Soria Zurita, Jessica Menold
Abstract The pace of technological advancements has been rapidly increasing in recent years, with the advent of artificial intelligence, virtual/augmented reality, and other emerging technologies fundamentally changing the way human beings work. The adoption and integration of these advanced technologies necessitates teams with diverse disciplinary expertise, to help teams remain agile to an ever-evolving technological landscape. Significant disciplinary diversity amongst teams however can be detrimental to team communication and performance. Additionally, accelerated by the COVID-19 Pandemic, the adoption and use of technologies that enable design teams to collaborate across significant geographical distances has become the norm in today's work environments, further complicating communication, and performance issues. Little is known about the way in which technology mediated communication affects the collaborative processes of design. As a first step towards filling this gap, the current work explores the fundamental ways experts from distinct disciplinary backgrounds collaborate in virtual design environments. Specifically, we explore the conversational dynamics between experts from two distinct fields: Non-Destructive Evaluation (NDE) and Design for Additive Manufacturing (DfAM). Using Markov Modeling, the study identified distinct communicative patterns that emerged during collaborative design efforts. Our findings suggest that traditional assumptions regarding communication patterns and design outcomes may not be applicable to expert design teams working in virtual environments.
{"title":"Designing Together: Exploring Collaborative Dynamics of Multi-Objective Design Problems in Virtual Environments","authors":"Debrina Roy, Nicole Calpin, Kathy Cheng, Alison Olechowski, Andrea Arguelles, Nicolás F. Soria Zurita, Jessica Menold","doi":"10.1115/1.4063658","DOIUrl":"https://doi.org/10.1115/1.4063658","url":null,"abstract":"Abstract The pace of technological advancements has been rapidly increasing in recent years, with the advent of artificial intelligence, virtual/augmented reality, and other emerging technologies fundamentally changing the way human beings work. The adoption and integration of these advanced technologies necessitates teams with diverse disciplinary expertise, to help teams remain agile to an ever-evolving technological landscape. Significant disciplinary diversity amongst teams however can be detrimental to team communication and performance. Additionally, accelerated by the COVID-19 Pandemic, the adoption and use of technologies that enable design teams to collaborate across significant geographical distances has become the norm in today's work environments, further complicating communication, and performance issues. Little is known about the way in which technology mediated communication affects the collaborative processes of design. As a first step towards filling this gap, the current work explores the fundamental ways experts from distinct disciplinary backgrounds collaborate in virtual design environments. Specifically, we explore the conversational dynamics between experts from two distinct fields: Non-Destructive Evaluation (NDE) and Design for Additive Manufacturing (DfAM). Using Markov Modeling, the study identified distinct communicative patterns that emerged during collaborative design efforts. Our findings suggest that traditional assumptions regarding communication patterns and design outcomes may not be applicable to expert design teams working in virtual environments.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134976045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mohammad Behtash, Xinyang Liu, Matthew Davied, Todd Thompson, Roger Burjes, Michael Lee, Pingfeng Wang, Chao Hu
Abstract Remanufacturing is a process that returns end-of-life equipment to as-new conditions and offers numerous environmental and economic benefits. To fully capitalize on remanufacturing, its synergistic interactions with design must be fully realized and addressed during the design stage. Although this fact is widely recognized in the literature, most of the current studies focus primarily either on the design or remanufacturing aspects of design for remanufacturing (DfRem). In an effort to offer a more integrated DfRem approach than those reported in the literature, we propose a new combined design and remanufacturing optimization (reman co-design) framework that takes a holistic approach by leveraging the intricate interplay between design and remanufacturing. The aim of this formulation is to identify the optimal decisions that maximize the benefits of remanufacturing throughout the entire lifespan of a product. To showcase the utility of the new formulation, we are using a case study of a hydraulic manifold, (re)manufactured by John Deere. Using this industry example, we compare the results of reman codesign to the ones from a decoupled remanufacturing design approach. Results reveal that remanufacturing benefits are better realized and improved upon when using the developed reman co-design approach.
{"title":"Reman Co-Design: A Combined Design and Remanufacturing Optimization Framework for the Sustainable Design of High-Value Components","authors":"Mohammad Behtash, Xinyang Liu, Matthew Davied, Todd Thompson, Roger Burjes, Michael Lee, Pingfeng Wang, Chao Hu","doi":"10.1115/1.4063660","DOIUrl":"https://doi.org/10.1115/1.4063660","url":null,"abstract":"Abstract Remanufacturing is a process that returns end-of-life equipment to as-new conditions and offers numerous environmental and economic benefits. To fully capitalize on remanufacturing, its synergistic interactions with design must be fully realized and addressed during the design stage. Although this fact is widely recognized in the literature, most of the current studies focus primarily either on the design or remanufacturing aspects of design for remanufacturing (DfRem). In an effort to offer a more integrated DfRem approach than those reported in the literature, we propose a new combined design and remanufacturing optimization (reman co-design) framework that takes a holistic approach by leveraging the intricate interplay between design and remanufacturing. The aim of this formulation is to identify the optimal decisions that maximize the benefits of remanufacturing throughout the entire lifespan of a product. To showcase the utility of the new formulation, we are using a case study of a hydraulic manifold, (re)manufactured by John Deere. Using this industry example, we compare the results of reman codesign to the ones from a decoupled remanufacturing design approach. Results reveal that remanufacturing benefits are better realized and improved upon when using the developed reman co-design approach.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135481169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Robotic devices are capable of reducing the physical burden on rehabilitation therapists and providing training programs of good repeatability, high efficiency and high precision. When designing the kinematic structure for rehabilitation robots, there has been a growing interest towards 1-degree-of-freedom (DOF) end-effector mechanisms due to their simpler structure and less complicated control algorithms. Compared with current 1-DOF mechanism designs that are mainly customized for multi-joint robotic training, spherical coupled serial chain (SCSC) mechanisms are proposed in this paper to specifically deliver the single-joint robotic training, which is of equal importance to the effective physical recovery. Using kinematic mapping theory, the end-effector motion of SCSC mechanisms can be naturally transformed to two trigonometric curves composed of finite Fourier series in two separate planes of the image space. This novel formulation helps to establish an analytical and direct relationship between the design parameters of SCSC mechanism and the harmonic parameters of the image-space representation of the task rehabilitation motion. The result is a simple and effective method to kinematic synthesis of SCSC mechanisms for generation of single-joint motion with an arbitrary number of spherical poses. An example of designing SCSC mechanisms for shoulder-joint rehabilitation is presented at the end of this paper to illustrate the feasibility of the proposed method.
{"title":"An Integrated Kinematic Mapping and Fourier Method to Design Spherical Coupled Serial Chain Mechanisms for Single-Joint Rehabilitation","authors":"Xiangyun Li, Lv Hao, Yu Xi, Peng Chen, Kang Li","doi":"10.1115/1.4063656","DOIUrl":"https://doi.org/10.1115/1.4063656","url":null,"abstract":"Abstract Robotic devices are capable of reducing the physical burden on rehabilitation therapists and providing training programs of good repeatability, high efficiency and high precision. When designing the kinematic structure for rehabilitation robots, there has been a growing interest towards 1-degree-of-freedom (DOF) end-effector mechanisms due to their simpler structure and less complicated control algorithms. Compared with current 1-DOF mechanism designs that are mainly customized for multi-joint robotic training, spherical coupled serial chain (SCSC) mechanisms are proposed in this paper to specifically deliver the single-joint robotic training, which is of equal importance to the effective physical recovery. Using kinematic mapping theory, the end-effector motion of SCSC mechanisms can be naturally transformed to two trigonometric curves composed of finite Fourier series in two separate planes of the image space. This novel formulation helps to establish an analytical and direct relationship between the design parameters of SCSC mechanism and the harmonic parameters of the image-space representation of the task rehabilitation motion. The result is a simple and effective method to kinematic synthesis of SCSC mechanisms for generation of single-joint motion with an arbitrary number of spherical poses. An example of designing SCSC mechanisms for shoulder-joint rehabilitation is presented at the end of this paper to illustrate the feasibility of the proposed method.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134976505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Indranil Hazra, Arko Chattejee, Joseph Southgate, Matthew Weiner, Katrina Groth, Shapour Azarm
Abstract 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.
{"title":"A Reliability-Based Optimization Framework for Planning Operational Profiles for Unmanned Systems","authors":"Indranil Hazra, Arko Chattejee, Joseph Southgate, Matthew Weiner, Katrina Groth, Shapour Azarm","doi":"10.1115/1.4063661","DOIUrl":"https://doi.org/10.1115/1.4063661","url":null,"abstract":"Abstract 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.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135483085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Solving a multiple-criteria optimization problem with severe constraints remains a significant issue in multi-objective evolutionary algorithms (MOEA). The problem primarily stems from the need for a suitable constraint-handling technique for an MOEA. One potential approach is to balance the search in both 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 for the MOEA, 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 large number of constraints. 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 and diversity by utilizing the generalized version of the multiple constraint ranking techniques.
{"title":"On the Advantages of Searching Infeasible Regions in Constrained Evolutionary-based Multi-Objective Engineering Optimization","authors":"Yohanes Bimo Dwianto, Pramudita Satria Palar, Lavi Rizki Zuhal, Akira Oyama","doi":"10.1115/1.4063629","DOIUrl":"https://doi.org/10.1115/1.4063629","url":null,"abstract":"Abstract Solving a multiple-criteria optimization problem with severe constraints remains a significant issue in multi-objective evolutionary algorithms (MOEA). The problem primarily stems from the need for a suitable constraint-handling technique for an MOEA. One potential approach is to balance the search in both 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 for the MOEA, 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 large number of constraints. 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 and diversity by utilizing the generalized version of the multiple constraint ranking techniques.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135739274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Technical organizations increasingly rely on innovation contests to find novel ideas for designing complex systems. These activities involve outsiders in the early stages of the design process, potentially leading to ground-breaking designs that surpass expectations. Here, the contest's rules document plays a crucial role: this design artifact communicates the organization's problem and the desired system performance to the participants—significantly impacting the resulting solutions. However, the contest's nature amplifies the challenges of communicating complex design problems across boundaries. Existing strategies for formulating—i.e., requirement and objective allocation—might not suit this context. We developed an inductive model of their formulation process based on a multi-year field study of five complex innovation contests. We found that the formulation team (or “seeker”) balanced the need to communicate their problem in detail with the risk of excluding valuable participants. Here, they chose among three approaches—incentivize, impose, or subsume—depending on their knowledge of potential solutions and the participants' capabilities. Notably, the seeker formulated more granularly than the literature describes, employing multiple approaches within each rules document. These findings shed light on a poorly understood aspect of innovation contests, resolve a longstanding debate in the engineering design literature, and guide practitioners' formulation processes.
{"title":"REQUIREMENTS, OBJECTIVES, BOTH, OR NEITHER: HOW TO FORMULATE COMPLEX DESIGN PROBLEMS FOR INNOVATION CONTESTS","authors":"Ademir-Paolo Vrolijk, Zoe Szajnfarber","doi":"10.1115/1.4063568","DOIUrl":"https://doi.org/10.1115/1.4063568","url":null,"abstract":"Abstract Technical organizations increasingly rely on innovation contests to find novel ideas for designing complex systems. These activities involve outsiders in the early stages of the design process, potentially leading to ground-breaking designs that surpass expectations. Here, the contest's rules document plays a crucial role: this design artifact communicates the organization's problem and the desired system performance to the participants—significantly impacting the resulting solutions. However, the contest's nature amplifies the challenges of communicating complex design problems across boundaries. Existing strategies for formulating—i.e., requirement and objective allocation—might not suit this context. We developed an inductive model of their formulation process based on a multi-year field study of five complex innovation contests. We found that the formulation team (or “seeker”) balanced the need to communicate their problem in detail with the risk of excluding valuable participants. Here, they chose among three approaches—incentivize, impose, or subsume—depending on their knowledge of potential solutions and the participants' capabilities. Notably, the seeker formulated more granularly than the literature describes, employing multiple approaches within each rules document. These findings shed light on a poorly understood aspect of innovation contests, resolve a longstanding debate in the engineering design literature, and guide practitioners' formulation processes.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135344831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Design artifacts provide a mechanism for illustrating design information and concepts, but their effectiveness relies on alignment across design agents in what these artifacts represent. This work investigates the agreement between multi-modal representations of design artifacts by humans and artificial intelligence (AI). Design artifacts are considered to constitute stimuli designers interact with to become inspired (i.e., inspirational stimuli), for which retrieval often relies on computational methods using AI. To facilitate this process for multi-modal stimuli, a better understanding of human perspectives of non-semantic representations of design information, e.g., by form or function-based features, is motivated. This work compares and evaluates human and AI-based representations of 3D-model parts by visual and functional features. Humans and AI were found to share consistent representations of visual and functional similarities, which aligned well to coarse, but not more granular, levels of similarity. Human-AI alignment was higher for identifying low compared to high similarity parts, suggesting mutual representation of features underlying more obvious than nuanced differences. Human evaluation of part relationships in terms of belonging to same or different categories revealed that human and AI-derived relationships similarly reflect concepts of “near” and “far”. However, levels of similarity corresponding to “near” and “far” differed depending on the criteria evaluated, where “far” was associated with nearer visually than functionally related stimuli. These findings contribute to a fundamental understanding of human evaluation of information conveyed by AI-represented design artifacts needed for successful human-AI collaboration in design.
{"title":"Comparing and evaluating human and computationally derived representations of non-semantic design information","authors":"Elisa Kwon, Kosa Goucher-Lambert","doi":"10.1115/1.4063567","DOIUrl":"https://doi.org/10.1115/1.4063567","url":null,"abstract":"Abstract Design artifacts provide a mechanism for illustrating design information and concepts, but their effectiveness relies on alignment across design agents in what these artifacts represent. This work investigates the agreement between multi-modal representations of design artifacts by humans and artificial intelligence (AI). Design artifacts are considered to constitute stimuli designers interact with to become inspired (i.e., inspirational stimuli), for which retrieval often relies on computational methods using AI. To facilitate this process for multi-modal stimuli, a better understanding of human perspectives of non-semantic representations of design information, e.g., by form or function-based features, is motivated. This work compares and evaluates human and AI-based representations of 3D-model parts by visual and functional features. Humans and AI were found to share consistent representations of visual and functional similarities, which aligned well to coarse, but not more granular, levels of similarity. Human-AI alignment was higher for identifying low compared to high similarity parts, suggesting mutual representation of features underlying more obvious than nuanced differences. Human evaluation of part relationships in terms of belonging to same or different categories revealed that human and AI-derived relationships similarly reflect concepts of “near” and “far”. However, levels of similarity corresponding to “near” and “far” differed depending on the criteria evaluated, where “far” was associated with nearer visually than functionally related stimuli. These findings contribute to a fundamental understanding of human evaluation of information conveyed by AI-represented design artifacts needed for successful human-AI collaboration in design.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135344962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：