Fault Diagnosis and Reconstruction for Sensor of Aeroengine Control System Based on AANN Network

Aeroengine is a high safety requirement system, thus the consequences of sensor faults are often extremely serious. The inherent complexity of the engine structure creates difficulty in establishing accurate mathematical models for the model-based sensor fault diagnosis. The traditional model-based fault diagnosis method is difficult to achieve satisfactory results. The emergence of neural network intelligent algorithm provides a new idea. Based on Autoassociative Neural Network (AANN), a fault diagnosis system for aeroengine is designed to detect and isolate engine sensor faults. Firstly, the signal of the sensor of the aeroengine control system was preprocessed, and then a group of AANN network was designed according to the fault parameters, and the improved learning algorithm is adopted to complete the fault detection and isolation of multi-sensor faults. Finally, it was verified based on the MATLAB/Simulink platform. It can be seen from simulation results that the proposed method can effectively reduce the noise of measurement data. Moreover, it has the advantages of fast diagnosis speed, strong robustness and synchronous detection and isolation. And it can effectively detect, isolate and reconstruct the faults of aeroengine.