题目：Intelligent Manufacturing: A Future Outlook

时间：2019年6月13日 10:00-11:30 

地点：机械与动力工程学院 振华会议室

邀请人：潘尔顺 研究员、王冬 副教授 (工业工程与管理系)

Biography

Dr. Andrew Kusiak is a Professor in the Department of Industrial and Systems Engineering and Director of the Intelligent Systems Laboratory at The University of Iowa, Iowa City. He has chaired two departments, Industrial Engineering (1988-95) and Mechanical and Industrial Engineering (2010-15). His current research focuses on applications of artificial intelligence and big data in smart manufacturing, product development, renewable energy, sustainability, and healthcare. He has published numerous books and technical papers in journals sponsored by professional societies, such as the Association for the Advancement of Artificial Intelligence, the American Society of Mechanical Engineers, Institute of Industrial and Systems Engineers, Institute of Electrical and Electronics Engineers, Nature, and other societies. He speaks frequently at international meetings, conducts professional seminars, and consults for industrial corporations. Dr. Kusiak has served in elected professional society positions as well as various editorial roles in over fifty journals, including five different IEEE Transactions.

Professor Kusiak is a Fellow of the Institute of Industrial and Systems Engineers and the Editor-in-Chief of the Journal of Intelligent Manufacturing.

Abstract

Manufacturing is undergoing transformation driven the developments in process technology, information technology, and data science. The incoming changes are disruptive and will likely result in manufacturing solutions that would be unimaginable a few years ago. A future manufacturing corporation will be highly digital and it will function in new modes. After decades of integration of engineering design and manufacturing, the design-for-dedicated manufacturing will be replaced with the design-for-open manufacturing. The emerging manufacturing will be open, shared, reconfigurable, democratic, and efficient. Designing a manufacturing system will reduce to formulating and solving an enterprise configuration problem. The presence of services in the cloud will be facilitated by autonomous generation of models. A formal approach to configuration of manufacturing enterprises is discussed. The computational complexity of the configuration problem calls for different modeling and solution approaches ranging from mathematical programming and data science to quantum computing. The progress in smart manufacturing accomplished to date is illustrated with applications.