Speech Title:
Speaker:
Ruqiang Yan, Xi’an Jiaotong University
Abstract:
The emergence of Prognostics and Health Management (PHM) systems is reshaping how we manage complex, high-end equipment across its entire lifecycle, driving the shift toward intelligent operation and maintenance in the Industry 4.0 era. At the heart of PHM lies fault diagnosis—a critical capability now undergoing rapid transformation. Fueled by advances in deep learning, data-driven approaches have surpassed traditional physics-based models in managing massive volumes of measurement data. Yet, despite their success, these black-box models often fall short in interpretability and trustworthiness, especially in safety-critical applications. This keynote explores a new frontier in intelligent fault diagnosis: the convergence of data science and physics through physics-informed deep learning. By embedding physical laws into neural networks, this collaborative approach bridges the gap between empirical insights and theoretical understanding. It enhances transparency, improves controllability, and unlocks new pathways for knowledge discovery. As we move deeper into the big data era, such hybrid models offer a promising route to more reliable, explainable, and robust PHM systems—ushering in a new generation of smart diagnostics for complex physical systems.
Bio:
Ruqiang Yan is a Full Professor and Director of International Machinery Center at the School of Mechanical Engineering, Xi’an Jiaotong University, China. His research interests include data analytics, AI, and energy-efficient sensing and sensor networks for the condition monitoring and health diagnosis of large-scale, complex, dynamical systems. Dr. Yan is a Fellow of IEEE (2022) and ASME (2019). He is the recipient of several prestigious awards including the First Prize for Technological Invention in Shaanxi Province in 2020, the First Prize for Natural Science from the Ministry of Education in 2020, and the 2019 IEEE Instrumentation and Measurement Society Technical Award. He has led the development of one IEEE standard and published over one hundred papers in IEEE and ASME journals, and other publications. He was the Editor-in-Chief of the IEEE Transactions on Instrumentation and Measurement, currently serves as an IEEE Instrumentation and Measurement Society Distinguished Lecturer and Associate Editor-in-Chief of Chinese Journal of Mechanical.
Speech Title:
Speaker:
Jay Lee, Univ. of Maryland College Park
Abstract:
This presentation will introduce the trends and recent advances of Industrial AI and LLM and their impacts to future development of PHM. First, trends of data-centric industrial systems and unmet needs of productivity are introduced. Next, some recent advances of industrial AI and non-traditional machine learning including topological data analytics, stream-of-quality (SoQ) based data analytics, similarity-based machine learning, domain adaptation and transfer learning, etc. for highly connected and complex industrial systems will be introduced with some examples including advanced semiconductor manufacturing, resilient automation systems, etc. Furthermore, the development of Industrial Large Knowledge Model based on RAG based LLM will be discussed. Finally, we will address the outlook of PHM transformation in the next 5-10 years.
Bio:
Dr. Jay Lee is Clark Distinguished Professor and Founding Director of Industrial AI Center in the Mechanical Engineering of the Univ. of Maryland College Park. His current research is focused on developing non-traditional machine learning technologies including transfer learning, domain adaptation, similarity-based machine learning, stream-of-x machine learning, as well as industrial large knowledge model (ILKM), etc. In addition, he is leading AI Foundry and Data Foundry which consist of over 30 different machine learning analytic tools and 100 diversified industrial datasets including semiconductor manufacturing, jet engines, wind turbine, EVs, high speed train, machine tools, robots, medical TBI, etc. for rapid development and deployment of AI.
Previously, he was the founding director of National Science Foundation (NSF) Industry/University Cooperative Research Center (I/UCRC) on Intelligent Maintenance Systems (www.imscenter.net) in partnership with over 100 global company members and the Center was selected as the most economically impactful I/UCRC in the NSF Economic Impact Study Report in 2012. He mentored his students and developed a number of start-up companies including Predictronics through NSF iCorps in 2013.
He is a member of Global Future Council on Advanced Manufacturing and Production of the World Economics Council (WEF), a member of Board of Governors of the Manufacturing Executive Leadership Council of National Association of Manufacturers (NAM), Board of Trustees of MTConnect, as well as a senior advisor to McKinsey.
He served as Vice Chairman and Board Member for Foxconn Technology Group (during 2019-2021 and had advised Foxconn business units to successfully receive six WEF Lighthouse Factory Awards. He also served as Director for Product Development and Manufacturing at United Technologies Research Center (now Raytheon Technologies Research Center) as well as Program Director for a number of programs at NSF.
He is a fellow of ASME, SME, PHM Society, and ISEAM. He was selected as 30 Visionaries in Smart Manufacturing in by SME in Jan. 2016 and 20 most influential professors in Smart Manufacturing in June 2020, and received SME Eli Whitney Productivity Award and SME/NAMRC S.M. Wu Research Implementation Award in 2022. His new book on Industrial AI was published by Springer in 2020. He is also a working group member for the recent Report on AI Engineering by NSF Engineering Research Visionary Alliance (ERVA) in 2024. He also serves as Editor-in-Chef for IOP Science Journal Machine Learning: Engineering.
Speech Title:
Speaker:
Wenyi Wang, Defence Science and Technology Group, Australia
Abstract:
This presentation will showcases the substantial contributions of the Defence Science and Technology Group (DSTG) of Australia to gearbox diagnostics for aerospace and defense applications over the past forty years. This talk will provide a brief reflection on some of DSTG's key achievements in this field, followed by a forward-looking perspective on the future of Prognostics and Health Management (PHM) research and development in the aerospace and defense context. The main focus of the presentation will be on DSTG's cutting-edge efforts to generate public datasets for the worldwide PHM community. These datasets address some of the most challenging failure modes for helicopter gearboxes, including the helicopter planetary gear rim crack and gearbox casing crack. By making these datasets publicly available, DSTG aims to contribute to the advancement of PHM research and help bridge the gap between academic research and real-life industry application. The HUMS2023 Data Challenge, which focused on the detection of the helicopter planetary gear rim crack, resulted in multiple teams developing effective techniques to detect the fault and trend its progression. The winning team provided an early detection and accurate trending of the crack growth, a significant achievement that could have major implications for the safety and reliability of helicopter operations. The HUMS2025 Data Challenge focused on the rare and critical failure mode of gearbox casing crack. The winning team utilized a structural health monitoring approach to accurately diagnose the changes induced by the propagating casing crack. This approach has the potential to revolutionize the way we monitor and maintain aerospace and defense systems. This will an opportunity for PHMAP attendees to learn about DSTG's latest contributions to the field of PHM and hear about several case studies featuring data acquired from military aircraft. This presentation is sure to inspire and engage attendees from academia and industry alike.
Bio:
Wenyi earned his Bachelor's and Master's degrees in Mechanical Engineering from Chinese institutions and a PhD in machine condition monitoring (MCM) from the University of New South Wales in Australia. He has over 30 years of experience in developing technologies for fault diagnosis of rotating machinery, with a particular focus on gear and bearing diagnostics. Wenyi has extensively published in this field, with his benchmark studies in gear diagnosis using resonance demodulation and autoregressive modelling widely cited. His research has been used for many aerospace and defence applications, including the health monitoring of F-35 and F/A-18G engines and helicopter gearboxes. Wenyi's expertise is widely recognized, as evidenced by his keynote speeches and plenary lectures at multiple international conferences in Japan and France. He has been awarded several prestigious fellowships, including a Victoria Fellowship, a DARPA Fellowship, an Australian Defence Science Fellowship, a US-Navy's ONR Visiting Fellowship, and a DSTG Best Paper Award and an Innovation Award by the International Association of Advanced Materials (IAAM) in Sweden. Wenyi has also chaired two DSTG's HUMS Conferences in 2017 and 2025 (HUMS2017 & HUMS2025). He has been a senior scientist in DSTG since 2002. Currently, his research is focused on developing methodologies to analyse some of the most challenging failure modes in helicopter gearboxes, on applying deep learning and artificial intelligence to MCM and predictive maintenance.