Professor Ruqiang Yan - Physics-Informed Deep Learning Empowering Intelligent Fault Diagnosis

As part of the IAS Festival of Failure, IAS Visiting Fellow Professor Ruqiang Yan delivers a seminar -

The Prognostics and Health Management (PHM) system revolutionizes the management of complex high-end equipment throughout its entire lifecycle, enabling intelligent operation and maintenance in the era of Industry 4.0. Within this system, fault diagnosis plays a pivotal role and is undergoing significant transformation. Presently, data-intensive science, propelled by deep learning, has surpassed the constraints of physics-based models in handling big data, emerging as a crucial approach for diagnosis. However, the lack of intuitive comprehension of physics models presents challenges to data science in terms of interpretability and reliability. This talk focuses on a collaborative approach that integrates data science with physics models to achieve intelligent fault diagnosis through collaborative deep learning structures known as physics-informed deep learning. This collaborative approach offers advantages in interpretability, controllability, and knowledge discovery, allowing for a more comprehensive understanding of the evolution of physical systems in the big data era.

For more information about the IAS, please visit - https://www.lboro.ac.uk/research/ias