Defect recognized system of friction welding based on compensatory fuzzy neural network

Because having many advantages, friction welding was applied widely in high-tech fields and industry section. But the existence of defeat will decrease the impact tenacity of joint evidently. A set of defect recognized system based on the compensatory fuzzy neural network of using wavelet and with fast algorithm. The dasiaenergy-defectpsila method to extract eigenvalue was used firstly, then defect was classified and recognized by fuzzy neural network. The results of simulation shows that the model established by making use of this algorithm has higher efficiency, and the possibility of wrap in network minimum during the training process is smaller, which can compare to approach the precision utmost steadily and classification recognize the defect precision.