融合油箱特征的航空液压系统渗漏故障诊断模型OA

In view of the shortcomings of the research on leakage fault detection of civil aviation hydraulic system,we focuse on the monitoring parameters of fuel tank oil volume which are often neglected in the existing leakage analysis of hydraulic pipeline.An improved particle swarm optimization method for hydraulic system diagnosis is proposed.Firstly,a signal processing step is proposed,and a new physical information feature weighting layer is developed to enhance the sensitivity of the model to fault-related features.Secondly,aiming at the problem of complex calculation and slow convergence of traditional particle swarm optimization algorithm,we introduce the linear decreasing inertia weight,Latin hypercube initialization and local restart strategy to improve performance.Finally,the effectiveness of the proposed method is verified by experimental investigation.The research shows that the proposed method has higher robustness and accuracy than many classical fault diagnosis methods,and it does provide an effective method for detecting leakage fault diagnosis of aviation hydraulic systems.