A Novel Method for Gas Turbine Condition Monitoring Based on KPCA and Analysis of Statistics T2 and SPE

Gas turbines are widely used all over the world, in order to ensure the normal operation of gas turbines, it is necessary to monitor the condition of gas turbine and analyze the tested parameters to find the state information contained in parameters. There is a problem in gas turbine condition monitoring that how to locate the fault accurately if failure occurs. To solve the problem, this paper proposes a method to locate the fault of gas turbine components by evaluating the sensitivity of tested parameters to fault. Firstly, the tested parameters are decomposed by the kernel principal component analysis. Then construct the statistics of T2 and SPE in the principal elements space and residual space, respectively. Furthermore, the thresholds of the statistics must be calculated. The influence of tested parameters on faults is analyzed, and the degree of influence is quantified. The fault location can be realized according to the analysis results. The research results show that the proposed method can realize fault diagnosis and location accurately.

[1]  Wanlu Jiang.  Exponentially Weighted Dynamic Kernel Principal Component Analysis Algorithm and Its Application in Fault Diagnosis , 2011 .

[2]  Wang Huawei,et al.  Fault fusion diagnosis of aero-engine based on deep learning , 2018 .

[3]  Zhiqiang Ge,et al.  HMM-Driven Robust Probabilistic Principal Component Analyzer for Dynamic Process Fault Classification , 2015, IEEE Transactions on Industrial Electronics.

[4]  K. Mathioudakis,et al.  Combining Classification Techniques With Kalman Filters for Aircraft Engine Diagnostics , 2004 .

[5]  Joachim Kurzke,et al.  Gas Turbine Cycle Design Methodology: A Comparison of Parameter Variation With Numerical Optimization , 1998 .

[6]  Steven X. Ding,et al.  A Survey of Fault Diagnosis and Fault-Tolerant Techniques—Part II: Fault Diagnosis With Knowledge-Based and Hybrid/Active Approaches , 2015, IEEE Transactions on Industrial Electronics.

[7]  Steven X. Ding,et al.  A Survey of Fault Diagnosis and Fault-Tolerant Techniques—Part I: Fault Diagnosis With Model-Based and Signal-Based Approaches , 2015, IEEE Transactions on Industrial Electronics.

[8]  K. Khorasani,et al.  Fault detection and isolation of gas turbine engines using a bank of neural networks , 2015 .

[9]  Jose A. Romagnoli,et al.  A strategy for detection and isolation of sensor failures and process upsets , 2001 .

[10]  Huang Jin-quan.  Contracted Kalman filter estimation for turbofan engine gas-path health , 2012 .

[11]  Vasile Palade,et al.  FAULT DIAGNOSIS OF AN INDUSTRIAL GAS TURBINE USING NEURO-FUZZY METHODS , 2002 .

[12]  Xiaojun Wu,et al.  KPCA method based on within-class auxiliary training samples and its application to pattern classification , 2017, Pattern Analysis and Applications.

[13]  Wang Le.  Fault Estimation for Actuators in Aero-engine Control System Based on Fault Decomposition , 2014 .

[14]  Claire Gaiani,et al.  Ultra-fine grinding increases the antioxidant capacity of wheat bran , 2013 .

[15]  Silvio Simani,et al.  Fault Diagnosis of a Wind Turbine Benchmark via Identified Fuzzy Models , 2015, IEEE Transactions on Industrial Electronics.

[16]  Jun Li,et al.  Effect of gas turbine endwall misalignment with slashface leakage on the blade endwall aerothermal performance , 2019, International Journal of Heat and Mass Transfer.

[17]  Vicenç Puig,et al.  Fault Diagnosis of an Advanced Wind Turbine Benchmark Using Interval-Based ARRs and Observers , 2015, IEEE Transactions on Industrial Electronics.

[18]  Janos Gertler,et al.  Fault Detection and Diagnosis , 2008, Encyclopedia of Systems and Control.

[19]  Chris Bingham,et al.  Fault detection and diagnosis based on extensions of PCA , 2013 .

[20]  Steven X. Ding,et al.  Real-time fault diagnosis and fault-tolerant control , 2015, IEEE Transactions on Industrial Electronics.

[21]  Jinquan Huang,et al.  An improved extended Kalman filter with inequality constraints for gas turbine engine health monitoring , 2016 .

[22]  Subhrakanti Dey,et al.  Stability of Kalman filtering with Markovian packet losses , 2007, Autom..

[23]  Muhammad Ehtisham Siddiqui,et al.  Energy Analysis of the S-CO2 Brayton Cycle with Improved Heat Regeneration , 2018, Processes.

[24]  Zhiwei Gao,et al.  Real-time monitoring, prognosis, and resilient control for wind turbine systems , 2017 .

[25]  S. Wold.  Exponentially weighted moving principal components analysis and projections to latent structures , 1994 .

[26]  Nader Meskin,et al.  Sensor fault detection and isolation of an industrial gas turbine using partial adaptive KPCA , 2018 .

[27]  Jun-Ho Huh,et al.  A Cost-Effective Redundant Digital Excitation Control System and Test Bed Experiment for Safe Power Supply for Process Industry 4.0 , 2018 .

[28]  Alain Rakotomamonjy,et al.  Variable Selection Using SVM-based Criteria , 2003, J. Mach. Learn. Res..