Towards Interpretable Machine Learning for Automated Damage Detection Based on Ultrasonic Guided Waves
Christopher Schnur,
Payman Goodarzi,
Yevgeniya Lugovtsova,
Jannis Bulling,
Jens Prager,
Kilian Tschöke,
Jochen Moll,
Andreas Schütze,
Tizian Schneider
Affiliations
Christopher Schnur
Lab for Measurement Technology, Saarland University, 66123 Saarbrücken, Germany
Payman Goodarzi
Lab for Measurement Technology, Saarland University, 66123 Saarbrücken, Germany
Yevgeniya Lugovtsova
Department of Non-Destructive Testing, Acoustic and Electromagnetic Methods Division, Bundesanstalt für Materialforschung und -Prüfung (BAM), 12205 Berlin, Germany
Jannis Bulling
Department of Non-Destructive Testing, Acoustic and Electromagnetic Methods Division, Bundesanstalt für Materialforschung und -Prüfung (BAM), 12205 Berlin, Germany
Jens Prager
Department of Non-Destructive Testing, Acoustic and Electromagnetic Methods Division, Bundesanstalt für Materialforschung und -Prüfung (BAM), 12205 Berlin, Germany
Kilian Tschöke
Systems for Condition Monitoring, Fraunhofer Institute for Ceramic Technologies and Systems IKTS, 01109 Dresden, Germany
Jochen Moll
Department of Physics, Goethe University Frankfurt, 60438 Frankfurt, Germany
Andreas Schütze
Lab for Measurement Technology, Saarland University, 66123 Saarbrücken, Germany
Tizian Schneider
Lab for Measurement Technology, Saarland University, 66123 Saarbrücken, Germany
Data-driven analysis for damage assessment has a large potential in structural health monitoring (SHM) systems, where sensors are permanently attached to the structure, enabling continuous and frequent measurements. In this contribution, we propose a machine learning (ML) approach for automated damage detection, based on an ML toolbox for industrial condition monitoring. The toolbox combines multiple complementary algorithms for feature extraction and selection and automatically chooses the best combination of methods for the dataset at hand. Here, this toolbox is applied to a guided wave-based SHM dataset for varying temperatures and damage locations, which is freely available on the Open Guided Waves platform. A classification rate of 96.2% is achieved, demonstrating reliable and automated damage detection. Moreover, the ability of the ML model to identify a damaged structure at untrained damage locations and temperatures is demonstrated.
