Research on Fault Diagnosis of Gas Turbine Rotor System Based on Deep Convolution Generative Adversarial

Aiming at the problems of difficult acquisition of gas turbine fault data and unbalanced data distribution, a fault diagnosis model of gas turbine rotor system based on deep convolution generation confrontation is proposed. Firstly, the original signal data optimization is realized based on the improved fuzzy reasoning, the optimized signal is decomposed by EEMD and the signal is demodulated, and then the deep convolution is used to generate an adversarial fault diagnosis model for data expansion and fault diagnosis clustering prediction, and two-dimensional fault samples are generated. After analysis, the t-sne and the maximum mean difference index of the sample are defined, and the results show that the classification accuracy of the expanded sample reaches 98%. The gas turbine fault collection data of an enterprise was input into the deep convolution generation to complete the training of the fault diagnosis model of the rotor system of the gas turbine. The fault diagnosis cluster analysis experiment is obviously better than the fault diagnosis results of the unprocessed data set. Using the expanded samples, the accuracy of gas turbine fault classification reaches 97.43%.