Speech Title: Machine Learning and its Applications in Prognosis and Health Management
Abstract: Machine learning has great potential for reliability assurance through prognosis and health management (PHM) of engineering assets. It has been attracting attention from both academic and industrial sectors. Recent developments of machine learning, especially the evolving branches of deep learning, transfer learning, and reinforcement learning, bring new opportunities for effective PHM. This presentation will first introduce some general knowledge of machine learning and its applications in various disciplines. We will then introduce some fundamentals of deep learning, with emphasis on artificial neural networks. Finally, our recent research and development work on using machine learning techniques for PHM will be described.
Bio: Dr. Mingjian Zuo received his Ph.D. degree in Industrial Engineering from Iowa State University, Ames, Iowa, U.S.A. He is currently Full Professor in the Department of Mechanical Engineering at the University of Alberta, Canada. His research interests include system reliability analysis, maintenance modeling and optimization, signal processing, and fault diagnosis. He served as Department Editor of IISE Transactions, Associate Editor of IEEE Transactions on Reliability, Associate Editor of Journal of Risk and Reliability, Associate Editor of International Journal of Quality, Reliability and Safety Engineering, Regional Editor of International Journal of Strategic Engineering Asset Management, and Editorial Board Member of Reliability Engineering and System Safety, Journal of Traffic and Transportation Engineering, and International Journal of Performability Engineering. He is Fellow of Canadian Academy of Engineering (CAE), Fellow of Institute of Industrial and Systems Engineers (IISE), Fellow of Engineering Institute of Canada (EIC), Founding Fellow of International Society of Engineering Asset Management (ISEAM), and Senior Member of IEEE. He is founder of Mingserve Technology Ltd.
Speech Title: Vibration and Acoustic Analysis of EV Electric Motor using Flexible Multibody Dynamics
Abstract: The vibration and acoustic characteristics of the electric motor taking into account not only the mechanical excitations due to the dynamic stiffness and mass eccentricity caused by the rotational motion and shaft bending, but also electromagnetic forces due to the electromagnetic interaction between stator and rotor. At first, the entire structural model was constructed, including rotor structure as well as the housing, stator core, and shields. Secondly, by performing the electromagnetic-structural weak coupled vibration analysis with the dynamic stiffness proven entire structural finite element model, the differences from the electromagnetic-structural weak coupled vibration analysis results calculated by conventional simplified finite element model including only stator core and housing was analyzed. Thirdly, the electric motor vibration characteristics considering mechanical forces which caused by the rotational motion of the rotor structure, and interaction with electromagnetic force was analyzed by conducting the multibody dynamics-electromagnetic-structural fully coupled vibration analysis with the entire structural finite element model. Finally, the acoustic analysis was conducted by using the vibration analysis results, which calculated from weak coupled analysis and fully coupled analysis respectively.
Speech Title: Five-Dimensional Digital Twin Model: From Theory to Practice
Abstract: Nowadays, digital twin has been a hot topic in many fields. To better master the research in the worldwide, the global academic research of digital twin (DT) is first investigated, and a comparative analysis of digital twin research in different countries is given out. Furthermore, the industry applications of digital twin are summarized, especially in smart manufacturing, city management, healthcare, aerospace, etc. Moreover, the proposed five-dimensional digital twin model is introduced, as well as its ten applications in different industrial fields. Finally, the related works of Digital Twin Research Group at Beihang University are briefly introduced.
Bio: Dr. Fei Tao is currently a Professor at the School of Automation Science and Electrical Engineering, and the Vice-Dean of Institute of Science and Technology, Beihang University. His research interests include digital twin and smart manufacturing. He has published 4 monographs and over 70 peer review papers in Nature, CIRP Annals, IEEE and ASME Transactions, of which over 20 are ESI high cited papers. His publications have over 20000 citations in Google Scholar. He was named Global Highly Cited Researcher by Clarivate Analytics in 2019 and 2020. He initiated a yearly meeting called Conference on Digital Twin and Smart Manufacturing Service in 2017. He founded the publication platform “Digital Twin” with Taylor & Francis Group in 2021. He is also a CIRP Associate Member and IEEE Senior Member.
Speech Title: Mechanical Energy Conversion and Transmission Systems for High-efficient Triboelectric Nanogenerators (TENGs)
Abstract: Triboelectric nanogenerators (TENGs) represent a promising next-generation renewable energy technology. So far, TENGs have been successfully used as highly sensitive and self-powered internet of things (IoT) sensors and portable/wearable power sources owing to their various merits, such as their light weight, freedom of material selection, low cost, and high-power conversion. The ability to take advantage of diverse mechanical input sources is another significant advantage of TENGs. However, the irregular magnitudes and frequencies of input sources are critical limitations that currently prevent utilizing TENGs in industrial or practical applications. In this presentation, I focus on mechanical energy conversion systems (MECS) for the regular or controlled operation of TENGs; to do this, we employ kinematics or vibrational theory. Once we control the mechanical operation of TENGs, we can predict the power production from these devices. Furthermore, mechanical frequency matching can greatly reduce power loss from electrical circuits. Motion control from, rotational to linear movement, can effectively provide high-frequency operation of contact-separation mode TENGs, enabling us to obtain sustainable and high-performance TENGs. Finally, resonant system designs for TENGs can produce the maximum output power.