Aero-Engine Gas-path Fault Diagnosis Based on Spatial Structural Characteristics of QAR Data

Civil aero-engine gas-path fault diagnosis is challenging due to its complicated parametric variation mechanism and the nonlinear relationship between fault performance and parameter variation. There still lacks effective approaches to provide reliable fault detection and isolation results with the massive Quick Access Recorder(QAR) data which has been used to monitor the gas-path condition by expert experience. In this paper, we propose a fault diagnosis methodology which is based on the spatial structural characteristics of QAR data. The spatial structures in high-dimensional space of QAR data which imply important information for fault diagnosis are extracted and visualized in low dimensional space. Based on different spatial structural forms and the changes of spatial structures of QAR data, fault information is presented and faults are located to certain fault mode. The proposed method is validated using the QAR data for the application studies of four civil turbofan engines. The diagnosis result shows the method is able to reliably monitor the aero-engine condition and detects the gas-path fault automatically.