An Iterative Reduced KPCA Hidden Markov Model for Gas Turbine Performance Fault Diagnosis
To improve gas-path performance fault pattern recognition for aircraft engines, a new data-driven diagnostic method based on hidden Markov model (HMM) is proposed. A redundant sensor somewhat interferes with fault diagnostic results of the HMM, and it also increases the computational burden. The con...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-07-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1996-1073/11/7/1807 |
| _version_ | 1811297569622458368 |
|---|---|
| author | Feng Lu Jipeng Jiang Jinquan Huang Xiaojie Qiu |
| author_facet | Feng Lu Jipeng Jiang Jinquan Huang Xiaojie Qiu |
| author_sort | Feng Lu |
| collection | DOAJ |
| description | To improve gas-path performance fault pattern recognition for aircraft engines, a new data-driven diagnostic method based on hidden Markov model (HMM) is proposed. A redundant sensor somewhat interferes with fault diagnostic results of the HMM, and it also increases the computational burden. The contribution of this paper is to develop an iterative reduced kernel principal component analysis (IRKPCA) algorithm to extract fault features from original high-dimension observation without large additional calculation load and combine it with the HMM for engine gas-path fault diagnosis. The optimal kernel features are obtained by iterative sequential forward selection of the IRKPCA, and the features with lower dimensions are contracted through a trade-off between the fault information and modeling data scale in reduced kernel space. The similarity degree is designed to simplify the HMM modeling data using fault kernel features. Test results show that the proposed methodology brings a significant improvement in diagnostic confidence and computational efforts in the applications of a turbofan engine fault diagnosis during its steady and dynamic process. |
| first_indexed | 2024-04-13T06:07:18Z |
| format | Article |
| id | doaj.art-b63131650c7144b59a93f37c9be581b8 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-13T06:07:18Z |
| publishDate | 2018-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-b63131650c7144b59a93f37c9be581b82022-12-22T02:59:13ZengMDPI AGEnergies1996-10732018-07-01117180710.3390/en11071807en11071807An Iterative Reduced KPCA Hidden Markov Model for Gas Turbine Performance Fault DiagnosisFeng Lu0Jipeng Jiang1Jinquan Huang2Xiaojie Qiu3Jiangsu Province Key Laboratory of Aerospace Power Systems, College of Energy & Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaJiangsu Province Key Laboratory of Aerospace Power Systems, College of Energy & Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaJiangsu Province Key Laboratory of Aerospace Power Systems, College of Energy & Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaAviation Motor Control System Institute, Aviation Industry Corporation of China, Wuxi 214063, ChinaTo improve gas-path performance fault pattern recognition for aircraft engines, a new data-driven diagnostic method based on hidden Markov model (HMM) is proposed. A redundant sensor somewhat interferes with fault diagnostic results of the HMM, and it also increases the computational burden. The contribution of this paper is to develop an iterative reduced kernel principal component analysis (IRKPCA) algorithm to extract fault features from original high-dimension observation without large additional calculation load and combine it with the HMM for engine gas-path fault diagnosis. The optimal kernel features are obtained by iterative sequential forward selection of the IRKPCA, and the features with lower dimensions are contracted through a trade-off between the fault information and modeling data scale in reduced kernel space. The similarity degree is designed to simplify the HMM modeling data using fault kernel features. Test results show that the proposed methodology brings a significant improvement in diagnostic confidence and computational efforts in the applications of a turbofan engine fault diagnosis during its steady and dynamic process.http://www.mdpi.com/1996-1073/11/7/1807gas turbinefault diagnosishidden Markov modelkernel principal component analysisfeature extraction |
| spellingShingle | Feng Lu Jipeng Jiang Jinquan Huang Xiaojie Qiu An Iterative Reduced KPCA Hidden Markov Model for Gas Turbine Performance Fault Diagnosis Energies gas turbine fault diagnosis hidden Markov model kernel principal component analysis feature extraction |
| title | An Iterative Reduced KPCA Hidden Markov Model for Gas Turbine Performance Fault Diagnosis |
| title_full | An Iterative Reduced KPCA Hidden Markov Model for Gas Turbine Performance Fault Diagnosis |
| title_fullStr | An Iterative Reduced KPCA Hidden Markov Model for Gas Turbine Performance Fault Diagnosis |
| title_full_unstemmed | An Iterative Reduced KPCA Hidden Markov Model for Gas Turbine Performance Fault Diagnosis |
| title_short | An Iterative Reduced KPCA Hidden Markov Model for Gas Turbine Performance Fault Diagnosis |
| title_sort | iterative reduced kpca hidden markov model for gas turbine performance fault diagnosis |
| topic | gas turbine fault diagnosis hidden Markov model kernel principal component analysis feature extraction |
| url | http://www.mdpi.com/1996-1073/11/7/1807 |
| work_keys_str_mv | AT fenglu aniterativereducedkpcahiddenmarkovmodelforgasturbineperformancefaultdiagnosis AT jipengjiang aniterativereducedkpcahiddenmarkovmodelforgasturbineperformancefaultdiagnosis AT jinquanhuang aniterativereducedkpcahiddenmarkovmodelforgasturbineperformancefaultdiagnosis AT xiaojieqiu aniterativereducedkpcahiddenmarkovmodelforgasturbineperformancefaultdiagnosis AT fenglu iterativereducedkpcahiddenmarkovmodelforgasturbineperformancefaultdiagnosis AT jipengjiang iterativereducedkpcahiddenmarkovmodelforgasturbineperformancefaultdiagnosis AT jinquanhuang iterativereducedkpcahiddenmarkovmodelforgasturbineperformancefaultdiagnosis AT xiaojieqiu iterativereducedkpcahiddenmarkovmodelforgasturbineperformancefaultdiagnosis |