Fault Diagnosis of Transmission Lines Based on Improved Complete Ensemble Empirical Mode Decomposition

Fast and accurate identification of transmission line faults is the premise for handling line faults. Therefore, a transmission line fault detection method based on improved adaptive mode decomposition algorithm is proposed. The improved complete set empirical mode decomposition with adaptive noise (ICEEMDAN) is used to decompose the line fault signal and calculate its kurtosis factor to obtain the characteristic mode function reflecting the fault signal characteristics; Multi scale permutation entropy (MPE) is calculated for each eigenmode function component to characterize the fault type characteristics of transmission lines. least squares support vector machine (LSSVM) intelligent fault type recognition model is established, and the fault feature sample set is used to train and test it to identify specific fault types. The simulation results show that ICEEMDAN multi-scale permutation entropy method has a high accuracy in transmission line fault diagnosis