Correlation analysis of aeroengine operation monitoring using deep learning

To analyze the reliability of aeroengine more accurately, based on the analysis of operation reliability and complex reliability, the deep learning method is adopted to deal with the nonlinear and time-varying problems between the state parameters and operation reliability of aeroengine, and the condition monitoring method and deep learning of aeroengine are discussed. The results show that, based on the deep learning integrated network, the remaining useful life of aeroengine is predicted, and the key parameters of aeroengine are fitted and predicted by the back propagation (BP) algorithm. The artificial neural network method is used to predict the aeroengine parameters. For the collected aeroengine monitoring parameters, the greedy layer by layer training algorithm is used to mine the relationship between the parameters, extract the evaluation features, and evaluate the performance degradation, which verify the statistical significance and robustness of the conclusions. The proposed algorithm is more accurate and robust than the results of back BP neural network and support vector machine. It can prevent the over-fitting of small samples in aeroengine condition monitoring and further improve its nonlinear processing and generalization ability.