Fault Diagnosis of Priority Valve in Aircraft Hydraulic System Based on Whale Optimization Algorithm Optimizating Convolutional Neural Network and Bi-directional Long-short Term Memory
The priority valve,a critical component of the aircraft hydraulic system,is responsible for prioritizing oil supply to the main flight control system when hydraulic system pressure is low.Maintaining its stability is essential for ensuring flight safety.However,the aircraft hydraulic system only has pressure sensors that makes traditional diagnostic methods difficult to implement.To overcome this challenge,a fault diagnosis algorithm using a whale optimization algorithm to optimization convolutional neural network bi-directional long short-term memory networks is proposed.Based on the differential pressure signals between the inlet and outlet of the priority valve,the fault feature is extracted by using the fusion algorithm of convolutional neural network and bi-directional long-short term memory and the super parameters are optimized by whale optimization algorithm to avoid the proposed algorithm falling into local optimization.Results from a multidisciplinary joint simulation using AMESim and MATLAB show that the proposed method achieves an average diagnostic accuracy of over 95％in complex working conditions.Compared to existing methods,this approach demonstrates significant improvements in diagnostic accuracy and stability.
万方数据
维普
