Feature extraction and pattern recognition of acoustic emission signals generated from plywood damage based on EMD and neural network
Yunfei Liu · Zhendong yu chongji · 2012
Aiming at the non-stationary features of acoustic emission(AE) signals generated from plywood damage and considering the overlapping of damage features in practice,a method of feature extraction and pattern recognition was proposed based on empirical mode decomposition(EMD) and BP neural network.The original AE signals were decomposed by EMD,and the intrinsic mode function(IMF) including the main feature information was selected.The energy ratios of IMF were constructed as a feature vector to identify the type of damage signals.BP neutral network pattern classifier was then established to identify four types of plywood damage signals.The measured result from a five-layed plywood damage shows that the method can extract AE signals characteristics precisely and identify damage types efficiently.