A Fault Identification Method of Generator Excitation System Based on DNA Chain and Two-stage LD Algorithm

A fault identification method of excitation system based on DNA chain and two-stage Levenshtein Distance (LD) algorithm is proposed. Firstly, the identification number, unit information and operating waveform of the power generator are put into the DNA chain, and the time-frequency characteristics of the waveform are extracted by wavelet transform. In addition, the obtained characteristics are divided into approximation parts to improve the speed of fault identification, and detailed departments to accurately identify the type of fault. Based on multiple simulation tests, the accuracy of fault identification is compared with the common AI recognition accuracy rate, which verifies the feasibility of this fault identification method.