Corrosion detection and severity level prediction using acoustic emission and machine learning based approach

Abstract

Failure caused by corrosion in industries are the major cause of breakdown maintenance. Acoustic emission during the accelerated corrosion testing is a reliable method for corrosion detection, however, classification of these acoustic emission signals by machine learning techniques is still in its infancy. Proposed approach uses a hybrid technique that combines the detection of corrosion through acoustic emission signals from accelerated corrosion testing with machine learning techniques to accurately predict the corrosion severity levels. Laboratory based experimentation setup was established for accelerated corrosion testing of mild steel samples for different time spans and mass loss of samples were recorded. Acoustic emission signals were acquired at high frequency sampling rate with Sound Well AE sensor, NI Elvis kit and NI Labview software. AE mean, AE RMS, AE energy, and kurtosis were selected as distinct features as they represent a linear relationship with the corrosion process. For multi-class problem, five Corrosion severity levels have been made based on mass loss occurred during accelerated corrosion testing for which Naive Bayes, BP-NN and RBF-NN showed accuracy of 90.4%, 94.57%, and 100% respectively.