Anomaly Detection Applied to ISHM for Thickness Reduction Analysis in Controlled Environments

In this work, three machine learning approaches were evaluated for detecting anomalies in impedance-based structural health monitoring (ISHM – Impedance-based Structural Health Monitoring) of a specimen controlled environment. Supervised, unsupervised, and semi-supervised algorithms chosen to compare them regarding an aluminum beam with failure induced by surface machining on one the faces. After applying algorithms, it was found that, types learning, supervised ones that achieved best accuracy anomalies. On other hand, unsupervised type model did not obtain good results conditions investigated. Thus, can be important technique comparison achievement implementing real anomaly detection ISHM systems.