Machine‐learning‐based methods for crack classification using acoustic emission technique

In actual projects, the damage of many critical components cannot be directly observed. Therefore, it is necessary to monitor their damage with structural health monitoring (SHM) technology to get the crack modes of the damage. Acoustic emission (AE) is a non-destructive testing (NDT) technique in structural health monitoring, and crack modes can be classified by analyzing the rise angle (RA) and average frequency (AF) of acoustic emission signals. However, the dividing line for classifying different crack patterns in this method is difficult to determine, and for the same member, different parameters can lead to a huge difference in the dividing line. This problem limits the application of the method. In this study, multiple machine learning algorithms were applied to cluster AE signals with known crack modes, and the clustering results were consistent with the real crack modes, solving the problem of difficult to determine the dividing line in the traditional RA-AF method. Furthermore, dimensionality reduction was performed on this set of AE signals, and the semi-empirical RA-AF analysis method was confirmed to be accurate.