Clustering analysis of acoustic emission signals in 2D-C/SiC tensile damage using genetic simulated annealing optimization algorithm

Carbon fiber composite materials are susceptible to process parameters in the preparation process, resulting in point defects, dislocation defects and surface defects. During the use process, surface distortion, unevenness, delamination, degumming, perforation and cracking may occur due to external force, which seriously affects the performance of the material members. In this paper, the acoustic emission signals generated by carbon fiber composite damage are used to analyze the characteristic parameters of acoustic emission signals during the damage process. The tensile damage test was carried out on the carbon fiber composite board, the acoustic emission parameter signal was detected, and the acoustic emission parameter signal was analyzed by k-means clustering to obtain the relationship between the signal parameters. In order to solve the problem that k-means clustering is easy to fall into local optimality, this paper proposes a k-means clustering method based on genetic simulated annealing algorithm optimization, and proves that the method can achieve global optimization.