基于故障逻辑的民机液压状态监控与故障诊断

Current monitoring data from civil aircraft are difficult to effectively apply to condition monitoring and fault diagnosis, which limits improvements in safety and reliability. To address this, this paper proposes a decision tree model based on hydraulic system component design and monitoring data to achieve operational condition monitoring of the hydraulic system. Additionally, a transfer learning model based on fault logic and operational data is proposed for fault diagnosis and localization, aiming to enhance condition monitoring capabilities and fault diagnosis efficiency. First, the principles of the hydraulic system are analyzed, and operational monitoring indicators are established based on rated parameters from the Flight Crew Operating Manual (FCOM) and monitoring data, with a decision tree model employed to monitor the hydraulic system's operational condition. Subsequently, fault formation conditions are organized into a logic diagram, and data from the Quick Access Recorder (QAR) are collected in conjunction with the input signal parameters of the logic diagram to develop a transfer learning model for fault diagnosis and localization. Finally, the proposed methods are validated using a case study of a hydraulic low-pressure fault in a specific type of domestically produced civil aircraft. The results demonstrate that the condition monitoring method effectively quantifies the hydraulic system's operational state, while the fault diagnosis method efficiently identifies the causes of faults.