Classification of Located Acoustic Emission Events Using Neural Network

Abstract Location of acoustic emission (AE) events is one of the main evaluation tools in AE analysis. Reliable location of AE sources enables accurate investigation of the mechanisms that led to a crack in the material. It is known that the location errors are influenced by several factors, including the accuracy of the elastic wave arrival time reading, the geometric distribution of the AE sensors, and most importantly, by the physical properties of the propagation medium. The aim of this study is the application of a neural network to classify clustered AE events, which were detected during six hydraulic fracturing tests in massive salt rock. A fully connected feed forward network was used for pattern recognition and classification of the input events according to target classes. For input data the signal arrival time profiles of the longitudinal (L) and transversal (T) elastic waves were used to train, to test, and to validate the neural network. In total 765 AE events were classified in various target classes. Receiver operating characteristic analysis (ROC) was applied for analyzing the result of the neural network approach. The neural network classified clustered events correctly, while few spatially scattered events outside the region of a cluster could not be matched to any cluster. Bootstrap analysis showed that the results are robust and demonstrates the high potential of Deep Learning (DL) methods in the location of AE events.