Fault diagnosis research of gearbox based on ICEEMDAN and PFA-ELM

Gearboxes are commonly used transmission components in industrial equipment. To address the problem of insufficient gearbox fault feature extraction and diagnosis accuracy, a fault diagnosis method based on improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and pathfinder algorithm (PFA) optimized extreme learning machine (ELM) is proposed. First, the signal is decomposed using ICEEMDAN to obtain intrinsic mode functions (IMFs). Secondly, based on the Spearman correlation coefficient, the valid IMFs are screened out and the fuzzy entropy and permutation entropy of each valid IMF are calculated as the fault feature vector. Finally, the PFA algorithm is used to optimize the weights and biases in ELM and construct a fault diagnosis model based on PFA-ELM. Experiments show that the fault diagnosis accuracy of PFA-ELM is as high as 98.67%. The method can accurately describe the working condition of gearboxes and has high practical value.