Hybrid machine learning with mode shape assessment for damage identification of plates

Machine learning-based structural health monitoring (ML-based SHM) methods are researched extensively in the recent decade due to the availability of advanced information and sensing technology. ML methods are well-known for their pattern recognition capability for complex problems. However, the main obstacle of ML-based SHM is that it often requires pre-collected historical data for model training. In most actual scenarios, damage presence can be detected using the unsupervised learning method through anomaly detection, but to further identify the damage types would require prior knowledge or historical events as references. This creates the cold-start problem, especially for new and unobserved structures. Modal-based methods identify damages based on the changes in the structural global properties but often require dense measurements for accurate results. Therefore, a two-stage hybrid modal-machine learning damage detection scheme is proposed. The first stage detects damage presence using Principal Component Analysis-Frequency Response Function (PCA-FRF) in an unsupervised manner, whereas the second stage further identifies the damage. To solve the cold-start problem, mode shape assessment using the first mode is initiated when no trained model is available yet in the second stage. The damage identified by the modal-based method would be stored for future training. This work highlights the performance of the scheme in alleviating the cold-start issue as it transitions through different phases, starting from zero damage sample available. Results showed that single and multiple damages can be identified at an acceptable accuracy level even when training samples are limited.

Automated summary

Machine learning-based structural health monitoring methods have been extensively studied in recent years due to the availability of advanced information and sensing technology. These methods have excellent pattern recognition capabilities for complex problems. However, the main challenge is the requirement of pre-collected historical data for model training. To address this "cold-start" problem, a two-stage hybrid modal-machine learning damage detection scheme is proposed, which includes an unsupervised detection stage and a further identification stage. Modal-based methods are used to detect damage based on changes in global properties, while unsupervised learning is used to detect damage presence. The performance of this scheme in alleviating the cold-start issue is highlighted, showing that it can identify single and multiple damages accurately even with limited training samples.