神经网络在涡流无损检测中的应用

近年来，人工神经网络由于能不断有力替代常规的模式识别技术，已引起人们很大关注。本文提出用神经网络技术判读无损检测中涡流探头的检测信号，并提供用多层神经网络ＢＰ算法得到的信号初步分类结果。

Application of Neural Networks to Eddy Current Nondestructive Testing

Artificial neural networks have attracted considerable attention in recent years largely because of a growing recognition of the potential of these networks as a powerful alternative to conventional pattern recognition techniques. In this paper, the use of neural networks is proposed for interpreting signals from eddy current probes used in nondestructive testing (NDT). Classification results obtained by implementing a multilayered neural network using the back-propagation algorithm are presented.