The feasibility of machine learning in damage degree judgment of carbon fiber reinforced polymer cables was first verified by the improved b-value method and wavelet packet spectrum analysis. Then, a hybrid system with support vector machine classification and particle swarm optimization algorithms was proposed to realize the prediction. The b-value calculated with all acoustic emission events has better performance when noise cannot be avoided. The 1/ b-value has almost the same trend with acoustic emission signal cumulative energy, which can meet the preliminarily needs of health monitoring. The particle swarm optimization clustering algorithm works by using nine characteristic parameters of acoustic emission signals. It demonstrates that the characteristic parameters of acoustic emission signals are closely related to the failure mode of the carbon fiber reinforced polymer cable. This indicates their correspondence to the cable’s damage degree and their ability to work as training data for machine learning. With particle swarm optimization, the trained support vector machine can reach at least 77% accuracy of a single acoustic emission signal when predicting the corresponding current damage degree. In addition, using the voting mechanism can promote the performance of support vector machine. This demonstrates the practicability of applying acoustic emission combined with machine learning as a damage degree judgment method for carbon fiber reinforced polymer cables.
Multi-response optimization of carbon fiber reinforced polymer (CFRP) drilling using back propagation neural network-particle swarm optimization (BPNN-PSO)