Haibin Lu, Lin Yuan, Hongbo Zhang, Wentao Sui and Dan Zhang
In view of the difficulty in detecting the internal defects of the brake pad, the internal defect detection of brake pads is realized by processing the knocking sound of brake pads. Firstly, the original signal is intercepted, then the intercepted signal is decomposed by using the theory of variational mode decomposition (VMD), and then the feature is extracted. By analyzing the frequency center and bandwidth of each mode layer, two important parameters of the variational mode decomposition algorithm are optimized: the number of modes K and the penalty factor alpha. The validation of K nearest neighbor (KNN) algorithm shows that the optimized variational mode decomposition method can improve the accuracy of internal defect detection of brake pads.
Brake Pad, Internal Defect Modal, Decomposition Feature Extraction