Feature Parameters Extraction Based on Local Mean Decomposition for Leakage Current of Underwater Equipment

In order to efficiently identify leakage current signals of underwater equipment, this paper proposes a method for extracting leakage current feature parameters of underwater equipment based on local mean decomposition (LMD). For non-stationary and non-linear leakage current signals of underwater equipment, LMD adaptively decomposes them into the sum of single component amplitude modulation and frequency modulation signals, where each single component leakage current signal of underwater equipment is equal to the product of its own envelope signal and a pure frequency modulation signal. To verify the performance of LMD, the signal is also decomposed by empirical mode decomposition (EMD). By comparing them, the decomposition time of LMD is 22.34 % shorter than that of EMD, and the instantaneous amplitude and frequency curves of the characteristic components of the leakage current signal of underwater equipment obtained from LMD are smoother, which has a better suppression effect on end effects. The method for extracting leakage current feature parameters of underwater equipment based on LMD provides an effective method for correctly identifying the leakage current of underwater equipment, which is beneficial for improving the safety of power supply.