Application of self-organizing neural network in ultrasonic detection of faults in bonding composite material

This paper describes the use of ultrasonic detection signal in testing the bonding composite plate material, comprehensive analyses of attenuation coefficient, harmonic amplitude, frequency of echo signals etc., and extracts the signal energy, singular wave peak value and the quantity, analyses the uncertainty of composite plate materials using self-organizing neural network classification algorithm. Finally, the collected data are going through a series of training and testing, the results show that this method can effectively classify and identify the data in bonding composite plate material.