Machine Learning enabled diagnostics and prognostics of composite structures.

This special session will gather the research community active in the area of SHM towards damage diagnostics & prognostics, address the challenges, discuss the present as well as future trends and exchange ideas & experiences across different engineering applications. Studies in the area of damage detection covering the first three levels of the SHM hierarchy i.e. (anomaly detection, localization and quantification of damage) as well as studies aiming the ultimate-level of SHM i.e. prognostics of the remaining useful life of composite structures subjected to various types loading, i.e. fatigue, impact, using data-driven and physics-based models or a combination of those models, are welcomed to be presented in this session among others.

Emphasis is given in the utilization of various SHM techniques, different modeling philosophies (data-driven/physics based) and paradigms that utilize machine learning algorithms to enable the achievement of diagnosis/prognosis. Issues of optimized Health Indicator identification based on multi-sensor data fusion towards more effective diagnostic/prognostic schemes are also of potential interest.