As an emerging research field, physics-informed machine learning and its structural integrity applications may bring new opportunities to the intelligent solution of engineering problems. Pure data-driven approaches have some limitations when solving engineering problems due to lack of interpretability and data hungry applications. Therefore, further unlocking the potential of machine learning will be an important research direction in the future. Knowledge-driven machine learning methods may have a profound impact on future engineering research. The theme of this special issue focuses on more specific physics-informed machine learning methods and case studies. This issue presents a series of practical ideas to demonstrate the huge potential of physics-informed machine learning for solving engineering problems with high precision and efficiency. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 2)'.
Keywords: failure mechanism modelling; machine learning; physics-informed machine learning; prognostic and health management; structural integrity.