The Rotating Components Performance Diagnosis of Gas Turbine Based on the Hybrid Filter

• Published in: Processes Vol. 7; no. 11; p. 819
• Main Authors: Zeng, Li, Dong, Shaojiang, Long, Wei
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.11.2019
• Subjects: Accuracy; Aircraft performance; Algorithms; Chemical energy; Diagnosis; Efficiency; Energy; Failure rates; Fault diagnosis; Gas turbines; Genetic algorithms; Kalman filters; Methods; Monte Carlo simulation; Noise; Optimization; Parameter estimation; Principal components analysis; Production functions; Rotation; Stochastic models; Support vector machines; Tracking filters; Turbines
• ISSN: 2227-9717; 2227-9717
• DOI: 10.3390/pr7110819

Gas turbine converts chemical energy into mechanical energy and provide energy for aircraft, ships, etc. The performance diagnosis of rotating components of gas turbine are essential in terms of the high failure rate of these parts. A problem that the sudden changing of operation state of turbines may lead to the misdiagnosis due to the defect of gas turbine’s model. This paper constructs the strong tracking filter based on the unscented Kalman filter to achieve accurate estimation of gas turbine’s measured parameters when the state changes suddenly. In the strong tracking filter, a parameter optimization method based on the residual similarity of measured parameters is proposed. Next, adopt the measured parameters filtered by the strong tracking filter to construct the health parameters estimation algorithm based on the particle filter. The particle weight is optimized by the mean adjustment method. Performance diagnosis is realized by checking the changes of health parameters output by particle filter. The results show that the proposed method improves the accuracy of performance diagnosis obviously.