Mihaela Banu, Sara Behdad, Daniel Cooper, Karl R. Haapala, Chao Hu, Harrison Kim, Astrid Layton, Barbara S Linke, Jie Zhang
This special issue presents a collaborative initiative between the ASME Manufacturing Engineering Division (MED) and the Design Engineering Division (DED) to promote research in sustainability within the design and manufacturing communities. As the need grows for methodologies and tools capable of supporting sustainable systems, this compilation presents recent research trends exploring the integration of sustainability principles into and progression towards sustainability goals by the design and implementation of engineered systems.
{"title":"Joint Special Issue on Advances in Design and Manufacturing for Sustainability","authors":"Mihaela Banu, Sara Behdad, Daniel Cooper, Karl R. Haapala, Chao Hu, Harrison Kim, Astrid Layton, Barbara S Linke, Jie Zhang","doi":"10.1115/1.4064362","DOIUrl":"https://doi.org/10.1115/1.4064362","url":null,"abstract":"\u0000 This special issue presents a collaborative initiative between the ASME Manufacturing Engineering Division (MED) and the Design Engineering Division (DED) to promote research in sustainability within the design and manufacturing communities. As the need grows for methodologies and tools capable of supporting sustainable systems, this compilation presents recent research trends exploring the integration of sustainability principles into and progression towards sustainability goals by the design and implementation of engineered systems.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"53 20","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138950866","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}
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.
{"title":"Accounting for Machine Learning Prediction Errors in Design","authors":"Xiaoping Du","doi":"10.1115/1.4064278","DOIUrl":"https://doi.org/10.1115/1.4064278","url":null,"abstract":"\u0000 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.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"76 1","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139002254","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}
RV reducer is mainly applied in high precision transmission. Its manufacturing errors strongly influence transmission accuracy. In order to select the optimal gear profile parameters and manufacturing accuracy to meet the transmission conditions in actual machining, a model of gear tooth contact analysis of involute and cycloid transmission considering tooth profile modification and manufacturing errors was established according to the principle of coordinate transformation and conjugate contact of gear. The sensitivity of different manufacturing errors to transmission errors was analyzed. At the same time, the optimization method of gear tooth profile modification parameters and manufacturing accuracy configuration under transmission reliability constraints was designed. The results showed that based on the optimization calculation of samples by DIRECT algorithm, it was possible to obtain a set of RV reducer modification parameters and manufacturing tolerance bands with the lowest manufacturing cost under the condition of transmission accuracy. The selected parameters had high reliability characteristics. Therefore, this method provides a theoretical optimization reference for manufacturing high reliability RV reducer.
RV 减速器主要应用于高精度传动。其制造误差对传动精度影响很大。为了在实际加工中选择满足传动条件的最佳齿廓参数和制造精度,根据齿轮的坐标变换和共轭接触原理,建立了考虑齿廓修正和制造误差的渐开线和摆线传动轮齿接触分析模型。分析了不同制造误差对传动误差的敏感性。同时,设计了在传动可靠性约束下的齿形修正参数和制造精度配置的优化方法。结果表明,基于 DIRECT 算法对样本的优化计算,可以获得一组在传动精度条件下制造成本最低的 RV 减速器齿形修正参数和制造公差带。所选参数具有高可靠性的特点。因此,该方法为制造高可靠性 RV 减速器提供了理论优化参考。
{"title":"Optimization of Tooth Profile Modification Amount and Manufacturing Tolerance Allocation for RV Reducer under Reliability Constraint","authors":"Yutao Li, Yuewen Su, Shaohu Wang","doi":"10.1115/1.4064277","DOIUrl":"https://doi.org/10.1115/1.4064277","url":null,"abstract":"\u0000 RV reducer is mainly applied in high precision transmission. Its manufacturing errors strongly influence transmission accuracy. In order to select the optimal gear profile parameters and manufacturing accuracy to meet the transmission conditions in actual machining, a model of gear tooth contact analysis of involute and cycloid transmission considering tooth profile modification and manufacturing errors was established according to the principle of coordinate transformation and conjugate contact of gear. The sensitivity of different manufacturing errors to transmission errors was analyzed. At the same time, the optimization method of gear tooth profile modification parameters and manufacturing accuracy configuration under transmission reliability constraints was designed. The results showed that based on the optimization calculation of samples by DIRECT algorithm, it was possible to obtain a set of RV reducer modification parameters and manufacturing tolerance bands with the lowest manufacturing cost under the condition of transmission accuracy. The selected parameters had high reliability characteristics. Therefore, this method provides a theoretical optimization reference for manufacturing high reliability RV reducer.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"11 11 1","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138973128","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}
Critical Thinking (CT) skills are highly valued by employers, leading to their integration into engineering education through various design- and problem-based approaches. Despite their recognized importance, the varying perceptions of CT present challenges in achieving a unified approach to its development and assessment. This paper reviews CT assessment in engineering education, particularly mapping Facione's CT skills with assessment approaches to discern how CT is evaluated. We conducted a systematic keyword search in the SCOPUS database and identified 462 articles from 2010 to March 2023. These were reviewed and distilled down to 80 articles included in this study. We find that CT has been recognized as an essential skill set, but there are no consistent definitions or means to assess it. Further, while CT is a multifaced skill, we find that very few assessment methods assess CT holistically. We identify three goals for CT assessment: 1) understand and recognize CT, 2) demonstrate CT, and 3) identify if CT has changed due to intervention. We discuss how different assessment approaches, including rubrics, surveys, standardized tests, and customized assessments, have been used and propose recommendations to support reaching a better understanding of CT assessment in engineering education. Further research is needed to understand better how these skills can be taught and assessed as part of engineering education to meet the needs of employers.
{"title":"Critical thinking assessment in engineering education: A Scopus-based literature review","authors":"Saurabh Deo, Katja Hölttä-Otto","doi":"10.1115/1.4064275","DOIUrl":"https://doi.org/10.1115/1.4064275","url":null,"abstract":"\u0000 Critical Thinking (CT) skills are highly valued by employers, leading to their integration into engineering education through various design- and problem-based approaches. Despite their recognized importance, the varying perceptions of CT present challenges in achieving a unified approach to its development and assessment. This paper reviews CT assessment in engineering education, particularly mapping Facione's CT skills with assessment approaches to discern how CT is evaluated. We conducted a systematic keyword search in the SCOPUS database and identified 462 articles from 2010 to March 2023. These were reviewed and distilled down to 80 articles included in this study. We find that CT has been recognized as an essential skill set, but there are no consistent definitions or means to assess it. Further, while CT is a multifaced skill, we find that very few assessment methods assess CT holistically. We identify three goals for CT assessment: 1) understand and recognize CT, 2) demonstrate CT, and 3) identify if CT has changed due to intervention. We discuss how different assessment approaches, including rubrics, surveys, standardized tests, and customized assessments, have been used and propose recommendations to support reaching a better understanding of CT assessment in engineering education. Further research is needed to understand better how these skills can be taught and assessed as part of engineering education to meet the needs of employers.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"2 23 1","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139001619","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}
Anastasia M. K. Schauer, Hunter Schaufel, Margaret Nunn, Noah Kohls, Katherine Fu
Throughout the mechanical design process, designers, the majority of whom are men, often fail to consider the needs of women, resulting in consequences ranging from inconvenience to increased risk of serious injury or death. Although these biases are well-studied in other fields of research, the mechanical design field lacks formal investigation into this phenomenon. In this study, engineering students (n = 300) took a survey in which they read a Persona describing a student makerspace employee and a Walkthrough describing their interaction with the makerspace while completing a project. During the Walkthrough, the user encountered various obstacles, or Pain Points. Participants were asked to recall and evaluate the Pain Points that the user encountered, then evaluated their perceptions of the makerspace and user. The independent variables under investigation were the gender of the user Persona (woman, gender-neutral, or man), Walkthrough room case (crafting or woodworking makerspace), and modality of the Persona and Walkthrough (text- /audio-based). Results showed that participants from the Text-based modality were better able to recall Pain Points compared to participants from the Audio-based modality, although the Pain Points were assessed as more severe when they impacted women users. In addition to finding that the gender of a user impacted the way a task environment was perceived, results confirmed the presence of androcentrism, or “default man” assumptions, in the way designers view end users of unknown gender. Promisingly, providing user Persona information in an audio modality eliminated this bias compared to text-based modalities.
{"title":"Thinking Beyond the Default User: The Impact of Gender, Stereotypes, and Modality on Interpretation of User Needs","authors":"Anastasia M. K. Schauer, Hunter Schaufel, Margaret Nunn, Noah Kohls, Katherine Fu","doi":"10.1115/1.4064263","DOIUrl":"https://doi.org/10.1115/1.4064263","url":null,"abstract":"\u0000 Throughout the mechanical design process, designers, the majority of whom are men, often fail to consider the needs of women, resulting in consequences ranging from inconvenience to increased risk of serious injury or death. Although these biases are well-studied in other fields of research, the mechanical design field lacks formal investigation into this phenomenon. In this study, engineering students (n = 300) took a survey in which they read a Persona describing a student makerspace employee and a Walkthrough describing their interaction with the makerspace while completing a project. During the Walkthrough, the user encountered various obstacles, or Pain Points. Participants were asked to recall and evaluate the Pain Points that the user encountered, then evaluated their perceptions of the makerspace and user. The independent variables under investigation were the gender of the user Persona (woman, gender-neutral, or man), Walkthrough room case (crafting or woodworking makerspace), and modality of the Persona and Walkthrough (text- /audio-based). Results showed that participants from the Text-based modality were better able to recall Pain Points compared to participants from the Audio-based modality, although the Pain Points were assessed as more severe when they impacted women users. In addition to finding that the gender of a user impacted the way a task environment was perceived, results confirmed the presence of androcentrism, or “default man” assumptions, in the way designers view end users of unknown gender. Promisingly, providing user Persona information in an audio modality eliminated this bias compared to text-based modalities.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"55 18","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139006909","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}
Dimensional and geometric variations are significant factors of products at the manufacturing stage. Because of these variations, the physical appearance or functionality of the final product may deviate from expectations. As of the present, research on variation analysis has been conducted at the feature level. To model the information and analyze the variation transfers of products, a graphical model is constructed by using the product feature and information. Through analysis of the relationship between the product and network model, a modeling process for the feature information network is proposed. Nodes, lines, and constraints in the network are defined in detail, and the dimension unit is defined to represent the dimension information within a part. Variations caused by connections between parts are divided into two categories of influence. Combining the dimension unit and the influence between parts, a variation analysis process is devised based on the proposed network model. To verify the effectiveness and feasibility of the proposed method, a case study is performed based on the grand assembly of a hull block. The result shows that the product can be modelled and the variation can be analyzed by the proposed network model.
{"title":"Variation Analysis Method Based on Product Feature Information Network","authors":"Liang Chen, Naikun Wei, Yu Zheng, Juntong Xi","doi":"10.1115/1.4064238","DOIUrl":"https://doi.org/10.1115/1.4064238","url":null,"abstract":"\u0000 Dimensional and geometric variations are significant factors of products at the manufacturing stage. Because of these variations, the physical appearance or functionality of the final product may deviate from expectations. As of the present, research on variation analysis has been conducted at the feature level. To model the information and analyze the variation transfers of products, a graphical model is constructed by using the product feature and information. Through analysis of the relationship between the product and network model, a modeling process for the feature information network is proposed. Nodes, lines, and constraints in the network are defined in detail, and the dimension unit is defined to represent the dimension information within a part. Variations caused by connections between parts are divided into two categories of influence. Combining the dimension unit and the influence between parts, a variation analysis process is devised based on the proposed network model. To verify the effectiveness and feasibility of the proposed method, a case study is performed based on the grand assembly of a hull block. The result shows that the product can be modelled and the variation can be analyzed by the proposed network model.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"33 1","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138590905","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}
Quan Lin, Jiexiang Hu, Qi Zhou, Leshi Shu, Anfu Zhang
In this paper, a multi-fidelity Bayesian optimization approach is presented to tackle computationally expensive constrained multi-objective optimization problems (MOPs). The proposed approach consists of a three-stage optimization framework designed to search for promising candidate points. In the first stage, an acquisition function is proposed to identify a feasible solution if none are available in the current set of sampling points. Subsequently, a new multi-fidelity weighted expected hypervolume improvement function is developed to find better solutions. In the third stage, a constrained weighted lower confidence bound acquisition function is presented to enhance the constraint predictions and refine the solutions near the constraint boundary. Additionally, a filter strategy is suggested to determine whether constraint updating is necessary, aiming to save computational resources and improve optimization efficiency. Moreover, to expedite the optimization process, a parallel optimization approach is further developed based on the suggested three-stage optimization framework. To achieve this, a multi-fidelity influence function is introduced, allowing the proposed approach to determine a desired number of candidate points within a single iteration. Lastly, the proposed approach is demonstrated through six numerical benchmark examples, which verifies its significant advantages in addressing expensive constrained MOPs. Besides, the proposed approach is applied to the multi-objective optimization of a metamaterial vibration isolator, resulting in the attainment of satisfactory solutions.
{"title":"A multi-fidelity Bayesian optimization approach for constrained multi-objective optimization problems","authors":"Quan Lin, Jiexiang Hu, Qi Zhou, Leshi Shu, Anfu Zhang","doi":"10.1115/1.4064244","DOIUrl":"https://doi.org/10.1115/1.4064244","url":null,"abstract":"\u0000 In this paper, a multi-fidelity Bayesian optimization approach is presented to tackle computationally expensive constrained multi-objective optimization problems (MOPs). The proposed approach consists of a three-stage optimization framework designed to search for promising candidate points. In the first stage, an acquisition function is proposed to identify a feasible solution if none are available in the current set of sampling points. Subsequently, a new multi-fidelity weighted expected hypervolume improvement function is developed to find better solutions. In the third stage, a constrained weighted lower confidence bound acquisition function is presented to enhance the constraint predictions and refine the solutions near the constraint boundary. Additionally, a filter strategy is suggested to determine whether constraint updating is necessary, aiming to save computational resources and improve optimization efficiency. Moreover, to expedite the optimization process, a parallel optimization approach is further developed based on the suggested three-stage optimization framework. To achieve this, a multi-fidelity influence function is introduced, allowing the proposed approach to determine a desired number of candidate points within a single iteration. Lastly, the proposed approach is demonstrated through six numerical benchmark examples, which verifies its significant advantages in addressing expensive constrained MOPs. Besides, the proposed approach is applied to the multi-objective optimization of a metamaterial vibration isolator, resulting in the attainment of satisfactory solutions.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"16 19","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138591576","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}
Semi-active adjustable constant force mechanisms (ACFMs) are an emerging alternative in applications where energy-efficient control of constant force environments is required. However, there is a lack of design strategies in the literature for semi-active ACFMs. This study addresses this gap by presenting a design strategy for ACFMs that semi-actively tunes the constant force by structural control. A design framework is presented which consists of an optimization of a high slenderness large stroke CFM followed by a parametric study on adjusting constant force through slenderness reduction by repositioning the boundary condition location. The design framework was able to change constant force ranging from 2-4 times with a stroke of 11-26% of the mechanism footprint respectively. A selected design with a larger force magnitude was fabricated and experimentally tested, demonstrating a change in constant force of 2.01 times which is comparable to that of active control designs and improved compactness, i.e., stroke of 11% of the footprint of the mechanism. In conclusion, the proposed ACFM design framework maximizes the initial CFM stroke and achieves constant force tuning by changing beam slenderness, resulting in compact and efficient ACFM designs.
{"title":"A design framework for semi-active structural controlled adjustable constant force mechanisms","authors":"T. Rehman, Jing Li, Zeeshan Qaiser, Shane Johnson","doi":"10.1115/1.4064248","DOIUrl":"https://doi.org/10.1115/1.4064248","url":null,"abstract":"\u0000 Semi-active adjustable constant force mechanisms (ACFMs) are an emerging alternative in applications where energy-efficient control of constant force environments is required. However, there is a lack of design strategies in the literature for semi-active ACFMs. This study addresses this gap by presenting a design strategy for ACFMs that semi-actively tunes the constant force by structural control. A design framework is presented which consists of an optimization of a high slenderness large stroke CFM followed by a parametric study on adjusting constant force through slenderness reduction by repositioning the boundary condition location. The design framework was able to change constant force ranging from 2-4 times with a stroke of 11-26% of the mechanism footprint respectively. A selected design with a larger force magnitude was fabricated and experimentally tested, demonstrating a change in constant force of 2.01 times which is comparable to that of active control designs and improved compactness, i.e., stroke of 11% of the footprint of the mechanism. In conclusion, the proposed ACFM design framework maximizes the initial CFM stroke and achieves constant force tuning by changing beam slenderness, resulting in compact and efficient ACFM designs.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"4 1","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138592043","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}
Kristen M. Edwards, Binyang Song, Jaron Porciello, Mark Engelbert, Carolyn Huang, Faez Ahmed
When designing evidence-based policies and programs, decision-makers must distill key information from a vast and rapidly growing literature base. Identifying relevant literature from raw search results is time and resource intensive, and is often done by manual screening. In this study, we develop an AI agent based on a bidirectional encoder representations from transformers (BERT) model and incorporate it into a human team designing an evidence synthesis product for global development. We explore the effectiveness of the human-AI hybrid team in accelerating the evidence synthesis process. We further enhance the human-AI hybrid team through active learning (AL). Specifically, we explore different sampling strategies: random, least confidence (LC), and highest priority (HP) sampling, to study their influence on the collaborative screening process. Results show that incorporating the BERT-based AI agent can reduce the human screening effort by 68.5% compared to the case of no AI assistance, and by 16.8% compared to using the industry standard model for identifying 80% of all relevant documents. When we apply the HP sampling strategy, the human screening effort can be reduced even more: by 78% for identifying 80% of all relevant documents compared to no AI assistance. We apply the AL-enhanced human-AI hybrid teaming workflow in the design process of three evidence gap maps which are now published for USAID's use. These findings demonstrate how AI can accelerate the development of evidence synthesis products and promote timely evidence-based decision making in global development.
{"title":"ADVISE: Accelerating the Creation of Evidence Syntheses for Global Development using Natural Language Processing-supported Human-AI Collaboration","authors":"Kristen M. Edwards, Binyang Song, Jaron Porciello, Mark Engelbert, Carolyn Huang, Faez Ahmed","doi":"10.1115/1.4064245","DOIUrl":"https://doi.org/10.1115/1.4064245","url":null,"abstract":"\u0000 When designing evidence-based policies and programs, decision-makers must distill key information from a vast and rapidly growing literature base. Identifying relevant literature from raw search results is time and resource intensive, and is often done by manual screening. In this study, we develop an AI agent based on a bidirectional encoder representations from transformers (BERT) model and incorporate it into a human team designing an evidence synthesis product for global development. We explore the effectiveness of the human-AI hybrid team in accelerating the evidence synthesis process. We further enhance the human-AI hybrid team through active learning (AL). Specifically, we explore different sampling strategies: random, least confidence (LC), and highest priority (HP) sampling, to study their influence on the collaborative screening process. Results show that incorporating the BERT-based AI agent can reduce the human screening effort by 68.5% compared to the case of no AI assistance, and by 16.8% compared to using the industry standard model for identifying 80% of all relevant documents. When we apply the HP sampling strategy, the human screening effort can be reduced even more: by 78% for identifying 80% of all relevant documents compared to no AI assistance. We apply the AL-enhanced human-AI hybrid teaming workflow in the design process of three evidence gap maps which are now published for USAID's use. These findings demonstrate how AI can accelerate the development of evidence synthesis products and promote timely evidence-based decision making in global development.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"4 10","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138592528","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}
Alfred Leuenberger, Eliott Birner, Thomas S. Lumpe, T. Stanković
The design representations of lattice structures are fundamental to the development of computational design approaches. Current applications of lattice structures are characterized by ever-growing demand on the computational resources to solve difficult optimization problems or generate large datasets, opting for the development of efficient design representations which offer a high range of possible design variants, while at the same time generating design spaces with attributes suitable for computational methods to explore. In response, the focus of this work is to propose a parametric design representation based on crystallographic symmetries and investigate its implications for the computational design of lattice structures. The work defines design rules to support the design of functionally graded structures using crystallographic symmetries such that the connectivity between individual members in a structure with varying geometry is guaranteed, and investigates how to use the parametrization in the context of optimization. The results show that the proposed parametrization achieves a compact design representation to benefit the computational design process by employing a small number of design variables to control a broad range of complex geometries. The results also show that the design spaces based on the proposed parametrization can be successfully explored using a direct search-based method.
{"title":"Computational Design of 2D Lattice Structures based on Crystallographic Symmetries","authors":"Alfred Leuenberger, Eliott Birner, Thomas S. Lumpe, T. Stanković","doi":"10.1115/1.4064246","DOIUrl":"https://doi.org/10.1115/1.4064246","url":null,"abstract":"\u0000 The design representations of lattice structures are fundamental to the development of computational design approaches. Current applications of lattice structures are characterized by ever-growing demand on the computational resources to solve difficult optimization problems or generate large datasets, opting for the development of efficient design representations which offer a high range of possible design variants, while at the same time generating design spaces with attributes suitable for computational methods to explore. In response, the focus of this work is to propose a parametric design representation based on crystallographic symmetries and investigate its implications for the computational design of lattice structures. The work defines design rules to support the design of functionally graded structures using crystallographic symmetries such that the connectivity between individual members in a structure with varying geometry is guaranteed, and investigates how to use the parametrization in the context of optimization. The results show that the proposed parametrization achieves a compact design representation to benefit the computational design process by employing a small number of design variables to control a broad range of complex geometries. The results also show that the design spaces based on the proposed parametrization can be successfully explored using a direct search-based method.","PeriodicalId":50137,"journal":{"name":"Journal of Mechanical Design","volume":"56 7","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138593355","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}