Fault analysis and fault degree evaluation via an improved ResNet method for aircraft hydraulic system

The hydraulic system is crucial for the safety of the aircraft, which is the key to ensuring the safety of both the aircraft and passengers. It is necessary to study and analyze the normal and fault mode of the system to provide a way for evaluating the fault degree of the hydraulic system. Therefore an improved ResNet based fault degree evaluation method was proposed to evaluate the fault degree of the aircraft hydraulic system. First, the aircraft hydraulic system is constructed by the AMESim, one normal and five fault modes are simulated. Then the effects of the parametric variations for the five fault models are studied, in which pump oil leakage is chosen for analysis. After the analysis of the 5 kinds of faults, each of them is divided to 3 different fault degree, then 16 kinds of states are definition. Second, using the SE-ResNet based method to evaluate the system fault degree. The structure of the two improved ResNet blocks are designed, after that the whole structure of the SE-ResNet fault degree evaluation model is given. Then the parameters of the SE-ResNet are optimization by simulation. After that the evaluate results are given and analyzed, moreover the comparison between the SE-ResNet method with the other machine learning methods are given. The results show that the method in this paper has the best accuracy and shortest test time, therefore the method proposed in this paper has effective measures to improve the reliability of the aircraft hydraulic system.