A Hybrid Kalman Filtering Approach Based on Federated Framework for Gas Turbine Engine Health Monitoring

The Kalman filter (KF) is the most common state estimation method for gas turbine health monitoring, and it runs in the centralized architecture. However, health estimation cannot be achieved by the KF-based method as sensor fault occurs, and malfunction of the central monitoring unit will unavoidably result to the termination of the diagnosis task. For these purposes, this paper develops a novel hybrid federated KF approach from the previous achievements. The hybrid KF consists of a bank of local filters and one master filter, and the federated filtering structure and asynchronous fusion mechanism are designed. Both the linearized KF and extended KF are employed as the local filters based on the linear correlation of thermodynamic parameters. The local state estimates and covariance are yielded in parallel, and then integrated in a master filter to produce global state estimate. The proposed methodology is evaluated and compared with the general federated KFs in terms of estimation accuracy, computational efforts, and robustness to sensor fault in the application of gas turbine health monitoring. The result shows that the hybrid KF is the best balance off the involved performance, and confirms our viewpoints in this paper.