A modified fusion model-based/data-driven model for sensor fault diagnosis and performance degradation estimation of aero-engine
Yufeng Huang, Gang Sun, Jun Tao, Yan Hu, Liuyin Yuan
Abstract
Abstract Sensor fault diagnosis and performance degradation estimation (SFDPDE) plays a critical role in the operation and maintenance of aero-engines. In this study, a modified fusion model driven by sensor measurements is proposed to overcome the drawbacks of the single data-driven and single model-based methods. Two types of on-board models are established based on augmented state space equations, and a data-driven model based on an extreme learning machine (ELM) is constructed for residual correction of the on-board model. A bidirectional information transmission algorithm is designed in the SFDPDE framework in order to include the function coordination. The Kalman filter is employed as the optimal algorithm in the SFDPDE framework, containing a standardized sensor parameter selection process. The experimental results indicate that the proposed fusion model improves the accuracy of sensor fault diagnosis and reduces the mean square error of health parameter estimations, while the information sharing module expands the application scope of SFDPDE and improves its accuracy as well as stability.