Acoustic emission source localization in plate-like structures using least-squares support vector machines with delta t feature

To deal with the difficulties of current acoustic emission (AE) source location methods, such as classical approaches based on times of arrival and artificial neural networks based on AE signal features, the least squares support vector machines (LS-SVM) approach was attempted in acoustic emission (AE) source location of plate-like structures. The AE events were produced by pencil lead breaks, and the response wave was received by piezoelectric sensors. The time of arrival, determined through the conventional threshold-crossing technique, was used to prepare delta t feature for the input to LS-SVM. Training and testing data sets were generated for the case of plates monitored by four transducers and were adopted to validate the source location methodology using LS-SVM with delta t feature. Experimental tests were carried out, with the source positioned at predetermined points evenly distributed within the plate area. A satisfactory correlation was found between the actual source locations and those predicted by the trained LS-SVM model. The results of the experiments show that the LS-SVM-based location method, with delta t feature, permits an alternative effective positioning in plate-like structures.