LOCATION OF CONTINUOUS AE SOURCES BY SENSORY NEURAL NETWORKS

A brief classification of location problems which appear in acoustic e mission (AE) analysis is given. Empirical treatment of corresponding i nverse problems is explained and applied to location of sources which generate continuous AE signals. A continuous AE phenomenon is treated as a stochastic process which is represented by the source coordinates and the correlation function of the emitted sound. The empirical mode l of GE phenomenon is formed based on a set of samples. The model incl udes a network of AE sensors and a neural network (NN). During formati on of the model: the AE signals are generated by sources at typical po sitions on a specimen. Recorded ultrasonic signals are transmitted to the NN together with the source coordinates. The first layer of NN det ermines the cross-correlation functions of signals and forms from them and source coordinates the data vectors. In the second layer, a set o f prototype vectors is formed from the data vectors by a self-organize d learning. After learning, the network is capable to locate the sourc e based on detected sound. For this purpose, the sensors provide AE si gnals, while the NN determines the corresponding correlation function and associates to it the source coordinates. The association is perfor med by a non-parametric regression which is implemented in the third l ayer of NN. (C) 1998 Elsevier Science B.V.