Educating Generative Designers in Engineering

教育工程领域的生成设计师

• 批准号: 2207408
• 负责人: Zhenghui Sha
• 金额: $ 218.02万
• 依托单位: University of Texas at Austin
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-02-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2207408&HistoricalAwards=false
• 关键词: Educating; Generative; Designers; Engineering

With support from NSF's Accelerating Discovery program, this project aims to re-envision undergraduate engineering education to include generative design. Generative design is a transformative design technology that uses open-ended artificial intelligence algorithms to arrive at solutions for engineering problems. Generative design software can be freed from preconceived ideas or past solutions. As a result, it allows exploration of a wider variety of potential solutions, with the goal of arriving at an optimal solution in partnership with the human engineer. The proposed project will support the development of open-source educational tools for teaching and learning generative design. These tools will be based on existing computer-assisted design and engineering software, and will include a set of project modules to guide students through authentic design problems. The software and associated design problems will be pilot tested by students at thirteen institutions, including community colleges, Historically Black Colleges and Universities, liberal arts colleges, and public universities. Information from these pilots will be used iteratively to refine the software and teaching approach. This project represents a novel application of artificial intelligence to engineering that could augment the creativity and productivity of the engineering workforce of the future. The overall goal of this project is to facilitate the teaching and learning of generative design at the undergraduate level. To accomplish this goal, the University of Arkansas, the University of Illinois at Urbana-Champaign, Oregon State University, and the Concord Consortium will collaborate to define, implement, and disseminate generative design tools and projects for use in undergraduate courses. Research questions from three perspectives will drive the project: 1) Theoretical perspective: What are the essential elements of generative design thinking that students must acquire so they can work effectively at the human-technology frontier in engineering? 2) Practical perspective: To what extent and in what ways can the curriculum and materials support the learning of generative design as indicated by students' gains in generative design thinking? and 3) Affective perspective: To what extent and in what ways can artificial intelligence affect the professional formation of engineers as indicated by the changes of students' interest and self-efficacy in engineering? To answer these questions, interdisciplinary research that integrates the perspectives and knowledge in engineering design, computer science, learning science, and workforce development will be conducted. The project will involve more than 1,000 students at 13 institutions around the country. The research will include data from demographic surveys, questionnaires, self-efficacy measures, design reports, screencast videos, classroom observations, and participant interviews. The materials developed by the project will be open source, including an open-source tool for teaching and learning generative design and a set of project-based learning modules that guide use of the tool to solve authentic design problems in architectural engineering and energy engineering. The products of this project are expected to equip students with essential skills and mindsets needed to master using artificial intelligence approaches in contemporary engineering practices.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

在NSF加速发现计划的支持下，该项目旨在重新设想本科工程教育，将生成性设计包括在内。生成式设计是一种变革性的设计技术，它使用开放式人工智能算法来得出工程问题的解决方案。生成式设计软件可以从先入为主的想法或过去的解决方案中解脱出来。因此，它允许探索更广泛的潜在解决方案，目标是与人类工程师合作得出最优解决方案。拟议的项目将支持开发用于教与学的开源教育工具--生成性设计。这些工具将基于现有的计算机辅助设计和工程软件，并将包括一套项目模块，以指导学生解决真实的设计问题。该软件和相关的设计问题将由13个机构的学生进行试点测试，包括社区学院、历史上的黑人学院和大学、文科学院和公立大学。来自这些试点的信息将被反复使用，以改进软件和教学方法。该项目代表了人工智能在工程中的一种新应用，可以增强未来工程劳动力的创造力和生产力。这个项目的总体目标是促进本科阶段生成性设计的教与学。为了实现这一目标，阿肯色大学、伊利诺伊大学厄巴纳-香槟分校、俄勒冈州立大学和协和联盟将合作定义、实施和传播用于本科课程的生成性设计工具和项目。研究问题将从三个角度推动这个项目：1)理论角度：学生必须获得什么基本要素，才能有效地在工程人类技术前沿工作？2)实践角度：根据学生在生成设计思维中的收获，课程和材料可以在多大程度上和以什么方式支持生成设计的学习？3)情感视角：从学生对工程的兴趣和自我效能感的变化可以看出，人工智能在多大程度上和以什么方式影响工程师的专业形成？为了回答这些问题，将进行跨学科研究，整合工程设计、计算机科学、学习科学和劳动力发展方面的观点和知识。该项目将涉及全国13所院校的1000多名学生。研究将包括人口统计调查、问卷调查、自我效能感测量、设计报告、截屏视频、课堂观察和参与者访谈的数据。该项目开发的材料将是开源的，包括一个用于教学和学习的开源工具--生成性设计，以及一套指导使用该工具解决建筑工程和能源工程中真实设计问题的基于项目的学习模块。该项目的产品预计将使学生掌握在当代工程实践中使用人工智能方法所需的基本技能和心态。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Design representation for performance evaluation of 3D shapes in structure-aware generative design

• DOI: 10.1017/dsj.2023.25
• 发表时间: 2023-09
• 期刊: Design Science
• 影响因子: 2.4
• 作者: Xingang Li;Charles Xie;Z. Sha

Beyond Solar Cookers: Modeling and Designing Concentrated Solar Power as Engineering Projects in Physics Classrooms

超越太阳能炊具：将聚光太阳能建模和设计为物理课堂的工程项目

• DOI: 10.1119/5.0090548
• 发表时间: 2023
• 期刊: The Physics Teacher
• 作者: Xie, Charles

Deep Learning of Cross-Modal Tasks for Conceptual Design of Engineered Products: A Review

• DOI: 10.1115/detc2022-90696
• 发表时间: 2022-08
• 期刊: Volume 6: 34th International Conference on Design Theory and Methodology (DTM)
• 作者: Xingang Li;Ye Wang;Z. Sha

Human-Centered Generative Design Framework: An Early Design Framework to Support Concept Creation and Evaluation

以人为本的生成设计框架：支持概念创建和评估的早期设计框架

• DOI: 10.1080/10447318.2023.2171489
• 发表时间: 2023
• 期刊: International Journal of Human–Computer Interaction
• 作者: Demirel, H. Onan;Goldstein, Molly H.;Li, Xingang;Sha, Zhenghui
• 通讯作者: Sha, Zhenghui

Exploring Generative Design Thinking for Engineering Design and Design Education

探索工程设计与设计教育的生成设计思维

• 发表时间: 2021
• 期刊: 2021 ASEE Midwest Section Conference
• 作者: Li, Xingang;Demirel, H. Onan;Goldstein, Molly H.;Sha, Zhenghui
• 通讯作者: Sha, Zhenghui