Artificial Intelligence | Hybrid Workshop | Chinese | Asia-Pacific
Description:
环境性能化设计（Environmental performance-based design）的出现旨在为城市与建筑应对气候变化，提供更舒适的生活空间提供方案和策略。传统上，环境性能只被作为概念性的设计指导和评价因素，对于空间形体的调整主要由设计师与咨询师合作，开展“盲盒式”、“经验式”的被动设计方法；而相比之下，由于高速增长的人工智能工具催生出的环境性能驱动的设计（Environmental performance-driven design）则是一种主动的设计思路，强调在设计方案初期阶段选取环境性能为目标，通过模拟分析、结果反馈、迭代寻优的方式，引导设计方案的生成式设计。
本次工作营将围绕环境性能驱动的生成设计的关键理论和技术问题，与学员共同探讨如何将环境性能的评估优化和生成设计相结合，探索人工智能在环境性能优化中应用的更多可能性。工作营将以理论教学和技术指导相结合的方式，帮助学员理解环境性能驱动的生成设计框架涉及的关键问题和解决方案。学员将基于课程内容以小组的形式进行主题研究，工作营成果包括展板，2-3分钟视频和汇报。
The emergence of environmental performance-based design aims to provide solutions and strategies for cities and buildings to cope with climate change and provide more comfortable living space. Traditionally, environmental performance is only regarded as a conceptual design guidance and evaluation factor. For the adjustment of spatial form, designers and consultants cooperate to carry out "blind box" and "experiential" passive design methods; In contrast, environmental performance-driven design is a kind of active design idea, which is produced by the rapid growth of artificial intelligence tools. It emphasizes the selection of environmental performance as the goal in the early stage of design and completes the design through simulation analysis, result feedback, and iterative optimization.
Our workshop will focus on the key theoretical and technical issues of environmental performance-driven generative design. It will be discussed with students that how to combine environmental performance evaluation and optimization with generative design, explore more possibilities of application of AI in environmental performance optimization. The workshop will combine theory course with technical guidance to help students understand the key issues and solutions involved in the environment performance-driven generative design framework. Based on the content of the series of courses, the students will carry out theme research in the form of groups, and the results of the workshop include display boards, 2-3 minutes video, and presentations.
Key Words:
环境性能 Environmental Performance,数字设计 Digital Design,人工智能 Artificial Intelligence,生成对抗网络 Generative Adversarial Network
Required Skills:
掌握Rhino/Grasshopper；掌握Python等编程语言等优先 intermediate Rhino, beginner Python
Required Software:
Rhinoceros/Grasshopper, Python/Anaconda3/TensorFlow
Required Hardware:
个人电脑 PC
Maximum number of participating students:
20（线下）+50（线上）
本次工作营将围绕环境性能驱动的生成设计的关键理论和技术问题，与学员共同探讨如何将环境性能的评估优化和生成设计相结合，探索人工智能在环境性能优化中应用的更多可能性。工作营将以理论教学和技术指导相结合的方式，帮助学员理解环境性能驱动的生成设计框架涉及的关键问题和解决方案。学员将基于课程内容以小组的形式进行主题研究，工作营成果包括展板，2-3分钟视频和汇报。
The emergence of environmental performance-based design aims to provide solutions and strategies for cities and buildings to cope with climate change and provide more comfortable living space. Traditionally, environmental performance is only regarded as a conceptual design guidance and evaluation factor. For the adjustment of spatial form, designers and consultants cooperate to carry out "blind box" and "experiential" passive design methods; In contrast, environmental performance-driven design is a kind of active design idea, which is produced by the rapid growth of artificial intelligence tools. It emphasizes the selection of environmental performance as the goal in the early stage of design and completes the design through simulation analysis, result feedback, and iterative optimization.
Our workshop will focus on the key theoretical and technical issues of environmental performance-driven generative design. It will be discussed with students that how to combine environmental performance evaluation and optimization with generative design, explore more possibilities of application of AI in environmental performance optimization. The workshop will combine theory course with technical guidance to help students understand the key issues and solutions involved in the environment performance-driven generative design framework. Based on the content of the series of courses, the students will carry out theme research in the form of groups, and the results of the workshop include display boards, 2-3 minutes video, and presentations.
Schedule:
Jun 27 - Jul 3
-
Day 1 / Jun 27
-
Day 2 / Jun 28
-
Day 3 / Jun 29
-
Day 4 / Jun 30
-
Day 5 / Jul 1
-
Day 6 / Jul 2
-
Day 7 / Jul 3
Instructors:
-
Jiawei Yao 同济大学 Tongji University,副教授 Associate Professor姚佳伟，同济大学建筑与城市规划学院建筑系副教授，上海市青年科技扬帆人才，上海建筑数字建造工程技术研究中心副主任、上海建筑学会数字建筑分会副秘书长、中国建筑学会计算性设计学术委员会委员、DigitalFUTURES数字未来学术委员会委员。已主持国家自然科学基金、全国博士后面上基金等多项国家与省部级课题。担任《Building and Environment》等国内外期刊客座编辑，并参与起草发布多项上海市地方标准。 Yao Jiawei is an associate professor in the Department of Architecture at the College of Architecture and Urban Planning, Tongji University. He is funded by Shanghai Sailing Talent Program and serves as the Vice Director of Shanghai Engineering Research Center of Digital Building Construction and the Deputy Secretary-General of the Digital Architecture Branch of Shanghai Architecture Society. He is also a member of the Academic Committee of Computational Design of the Architectural Society of China and DigitalFUTURES. Yao has led several national and provincial-level research projects, including the National Natural Science Foundation of China and the Postdoctoral Fund of China. He is a guest editor for several international and domestic journals, such as Building and Environment, and has participated in the drafting and release of several local standards in Shanghai. -
Minggang Yin 华东建筑设计研究院有限公司 East China Architectural Design and Research Institute Co., Ltd,资深建筑性能分析师 Senior Building Performance Analyst殷明刚，目前就职于华东建筑设计研究院有限公司上海建筑科创中心，资深建筑性能分析师，长期从事绿色建筑节能设计咨询、建筑性能专项分析与相关课题科研，参与并完成了多个地标项目的绿色建筑咨询服务，熟悉国内外建筑性能化设计的方法、流程与分析软件，在国内建筑环境领域的核心期刊发表多篇论文，多次在国内绿色建筑行业会议上做过主题报告，积极推行将 BIM 技术、参数化分析、机器学习、VR/AR等先进方法应用于绿色低碳建筑的设计中. Yin,Minggang , worked in Shanghai Archi-Scientific Creation Center of East China Architectural Design and Research Institute Co., Ltd, is a senior building performance analyst who has long been engaged in green building energy-saving design consulting, building performance special analysis and related topics of scientific research, participated and completed more than 10 landmark projects of green building consulting services, familiar with domestic and international building performance design methods, processes and analysis software.He has published several papers in core journals in the field of built environment in China, has given many keynote presentations in domestic green building industry conferences, and actively promotes the application of BIM technology, parametric analysis, machine learning, VR/AR and other advanced methods in the design of green low-carbon buildings. -
Chenyu Huang 北方工业大学 North China University of Technology,硕士研究生 Master Student黄辰宇，北方工业大学建筑学硕士研究生。他本科毕业于西安建筑科技大学建筑环境与能源应用专业，在校期间获得全国大学生数学建模竞赛一等奖和全国大学生数学竞赛二等奖。毕业后，他曾在同济大学和创盟国际&一造科技担任算法开发和机器人建造实习生。在过去的三年中，他曾参与组织多次DigitalFUTURES工作营。他的研究兴趣包括环境性能驱动的生成式设计和人工智能在量化城市形态学中的应用。目前，他已经在国内外知名期刊和会议中发表了学术论文10余篇。此外，他还担任Revista Diseña国际期刊审稿人。 CHENYU HUANG, Master of Architecture from North China University of technology. He graduated from Xi’an University of Architecture and Technology. He has won the first prize of the national college students mathematical modeling competition and the second prize of the national college students mathematics competition during the undergraduate period. After graduation, he worked as an intern in algorithm development and robot fabrication at Tongji University and Fab-Union. In the past three years, Huang has been involved in organizing Shanghai DigitalFUTURES workshop. And his interests include environmental performance-driven generative design and the application of AI in quantitative analysis of urban morphology, etc. His publication includes more than 10 papers in top international conferences and journals. Also, he served as the reviewer for the international journal Revista Diseña.