加入支持让我们有继续维护的动力！会员畅享查看所有预告
立即购买
【智远讲坛第14期】加拿大西安大略大学夏敏副教授：Scientific Machine Learning for Smart Manufacturing and Energy Systems
- 来源：
- 学校官网
- 收录时间：
- 2026-03-17 19:21:17
- 时间：
- 2026-03-13 15:30:00
- 地点：
- 广州国际校区D1-b110会议室
- 报告人：
- 夏敏
- 学校：
- 华南理工大学
- 关键词：
- Scientific Machine Learning, Smart Manufacturing, Smart Energy Systems, Trustworthy AI, Interpretable Models, Uncertainty Estimation, Physics-Informed Learning
- 简介：
- Machine learning, especially deep learning, has been widely investigated in data-driven solutions for smart manufacturing and smart energy systems, including monitoring, optimization, and decision-making, due to its superior capabilities in classification, regression, or content generation (e.g., Large Language Model-based approaches). However, the black box nature of deep learning has limited the practical application or acceptance of these methods in real industrial settings. Building reliable and trustworthy approaches is both an urgent and demanding task in both academia and industry. This talk will illustrate trustworthy AI-based methods, focusing on interpretable model learning, uncertainty estimation, and physics-informed learning, which can significantly enhance the reliability of AI-based solutions in smart manufacturing. Through real-world case studies, the developed solution with scientific machine learning and future application scenarios will be explored.
- -/- 22
报告介绍：
Machine learning, especially deep learning, has been widely investigated in data-driven solutions for smart manufacturing and smart energy systems, including monitoring, optimization, and decision-making, due to its superior capabilities in classification, regression, or content generation (e.g., Large Language Model-based approaches). However, the black box nature of deep learning has limited the practical application or acceptance of these methods in real industrial settings. Building reliable and trustworthy approaches is both an urgent and demanding task in both academia and industry. This talk will illustrate trustworthy AI-based methods, focusing on interpretable model learning, uncertainty estimation, and physics-informed learning, which can significantly enhance the reliability of AI-based solutions in smart manufacturing. Through real-world case studies, the developed solution with scientific machine learning and future application scenarios will be explored.
报告人介绍：
Dr. Min Xia is an Associate Professor and the Director of the Machine Intelligence Laboratory (MIN Lab) at the Department of Mechanical and Materials Engineering at The University of Western Ontario in Canada. His research interests include intelligent machine condition monitoring, advanced manufacturing process monitoring and optimization, industrial data mining, and smart clean energy systems. He has led 20 research projects as PI or Co-I funded by Horizon Europe, Innovate UK, NSERC, Mitacs, etc., with total funding of more than $21 million. Dr. Xia has published more than 100 papers in peer-reviewed journals and conferences. He is Editor-in-Chief of the Journal of Mechatronic Systems and Control, Associate Editor of IEEE Transactions on Industrial Informatics, IEEE Transactions on Systems, Man, and Cybernetics: Systems, IEEE Transactions on Instrumentation and Measurement, Journal of Intelligent Manufacturing, and IET Collaborative Intelligent Manufacturing.
购买下会员支持下吧...用爱发电已经很久了 立即购买
