SS 03
The practical deployment of Machine Learning (ML) and Artifical Intelligence (AI) for Prognostics and Health Management (PHM) of industrial equipment is often hindered by "black-box" limitations, including data scarcity, physical inconsistency, the lack of explainability and the lack of generalizability to unseen operating conditions. To address these challenges, Physics-Informed Machine Learning (PIML) integrates prior physics-based knowledge, such as governing equations and domain expertise, directly into the learning process. This session explores how PIML enables PHM to move toward physically grounded, interpretable and trustworthy AI solutions. We invite researchers and industry experts to share recent advancements in PIML methodologies and their specific applications to the reliability and maintenance of complex systems.
Main topics are (but not limited to): |
|
Methods:
|
Applications:
|
