Complex System Fault Diagnostic Method Based on Convolutional Neural Network

As a branch of machine learning, deep learning is characterized by multi-level learning to obtain different abstraction levels of raw data, thus improving the accuracy of the tasks such as classification and prediction. It brings a new idea of the complex system fault diagnostics and prognostics. Combining the characteristics of complex system test data and the advantages of deep learning, a fault diagnostics method based on convolutional neural network is proposed, including preprocessing, model training and optimization. Then a complex system fault diagnostic algorithm platform based-on deep learning method is realized. The simulation method of an aero-engine gas path test proves that the proposed method has good feasibility and effect, can fully utilize the advantages of deep learning, and is more suitable for characterizing the complex and varied characteristics hidden inside the complex system data. It can provide the technical support for the design, test and management of the complex system, and improve the safety and effectively reduce the life cycle costs of the complex system.