Artificial neural network technology for the data processing of on-line corrosion fatigue crack growth monitoring

The artificial neural network (ANN) method for the data processing of on-li ne corrosion fatigue crack growth monitoring is proposed after analyzing th e general method for corrosion fatigue crack growth data. A metabolism mode l for predicting the corrosion fatigue life by ANN is presented, which does not need all kinds of materials and environment parameters, and only needs to measure the relation between a (length of crack) and N (cyclic times of loading) in-service. The feasibility of this model was verified by some ex amples. It makes up the inadequacy of data processing for current method an d on-line monitoring. Hence it has definite realistic meaning for engineeri ng application. (C) 1999 Elsevier Science Ltd. All rights reserved.