The applicability of Artificial Neural Network Systems (ANN) to identify the features in the acoustic emission (AE) signals that can be used to predict delamination defects is investigated. Characteristic features in the acoustic emission signals are identified through extensive review of the available data and development of suitable ANN. Results of six carbonization runs including those for components with and without delamination are presented. In general, the results of the preliminary investigation are very encouraging and demonstrate the benefit of combined AE and ANN techniques.
|Original language||English (US)|
|Number of pages||4|
|Journal||Proceedings of the IEEE Ultrasonics Symposium|
|State||Published - 1994|
All Science Journal Classification (ASJC) codes