[1] Zhang Xi, Yan Weiwu, Zhao Xu, Shao Huihe, et al. Nonlinear online process monitoring and fault diagnosisof condenser based on kernel PCA plus FDA [J]. Journal of Southeast University (English Edition), 2007, 23 (1): 51-56. [doi:10.3969/j.issn.1003-7985.2007.01.012]
Copy
Nonlinear online process monitoring and fault diagnosisof condenser based on kernel PCA plus FDA(
)
基于核PCA和FDA的凝汽器非线型过程监控和故障诊断
)Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]
- Volumn:
- 23
- Issue:
- 2007 1
- Page:
- 51-56
- Research Field:
- Energy and Power Engineering
- Publishing date:
- 2007-03-30
Info
- Title:
- Nonlinear online process monitoring and fault diagnosisof condenser based on kernel PCA plus FDA
- 基于核PCA和FDA的凝汽器非线型过程监控和故障诊断
- Author(s):
- Zhang Xi, Yan Weiwu, Zhao Xu, Shao Huihe
- Department of Automation, Shanghai Jiaotong University, Shanghai 200040, China
- Keywords:
- nonlinear; kernel PCA; FDA; process monitoring; fault diagnosis; condenser
- PACS:
- TK267;TP277
- DOI:
- 10.3969/j.issn.1003-7985.2007.01.012
- Abstract:
- A novel online process monitoring and fault diagnosis method of condenser based on kernel principle component analysis(KPCA)and Fisher discriminant analysis(FDA)is presented. The basic idea of this method is: First map data from the original space into high-dimensional feature space via nonlinear kernel function and then extract optimal feature vector and discriminant vector in feature space and calculate the Euclidean distance between feature vectors to perform process monitoring. Similar degree between the present discriminant vector and optimal discriminant vector of fault in historical dataset is used for diagnosis. The proposed method can effectively capture the nonlinear relationship among process variables. Simulating results of the turbo generator’s fault data set prove that the proposed method is effective.
- 提出了基于核主元分析和Fisher判别分析相结合的非线性统计过程监控和故障诊断新方法.该方法首先利用非线性核函数将数据从原始空间映射到高维空间, 然后在高维空间中利用线性Fisher判别分析法提取数据最优的核Fisher判别矢量和特征矢量, 通过计算特征矢量之间的欧式距离来实现过程监控.若系统发生故障, 则根据当前故障的判别矢量和历史故障数据集中所含故障的最优核Fisher判别矢量的相似度进行故障诊断.所提出的方法能有效的捕获过程变量之间的非线性关系, 汽轮机特征故障数据集仿真试验验证了该方法的有效性.
References:
[1] Hou Guolian, Sun Xiaogang, Zhang Jianhua, et al.Research on fault diagnosis of condenser via nonlinear principal component analysis and probabilistic neural networks[J].Proceedings of the CSEE, 2005, 25(18):104-108.(in Chinese)
[2] Wang Peihong, Zhu Yuna, Jia Junying, et al.Application of fuzzy pattern recognition to fault diagnosis of condensers[J].Proceedings of the CSEE, 1999, 19(10):46-49.(in Chinese)
[3] Ma Liangyu, Wang Bingshu, Tong Zhensheng, et al.Fuzzy pattern recognition and artificial neural networks used for fault diagnosis of the double channel condenser[J].Proceedings of the CSEE, 2001, 21(8):68-73.(in Chinese)
[4] Zhang Jianhua, Hou Guolian, Zhang Wei, et al.A research on fuzzy rules and genetic algorithm based method for a condenser fault diagnosis[J].Proceedings of the CSEE, 2004, 24(4):205-209.(in Chinese)
[5] Yu Zhiwei, Su Baoku, Zeng Ming.Application of wavelet packet in fault diagnosis system of large scale DC motor rotor[J].Proceedings of the CSEE, 2005, 25(22):158-162.(in Chinese)
[6] Zhang Guoyun, Zhang Jing.Fuzzy SVM-based multilevel binary tree classifier for fault diagnosis of hydro turbine speed regulating system[J].Proceedings of the CSEE, 2005, 25(8):100-104.(in Chinese)
[7] Jiang Dongxiang, Diao Jinhui, Zhao Gang, et al.Study on methods of vibration fault diagnosis based on time-frequency contour map for turbine generator unit[J].Proceedings of the CSEE, 2005, 25(6):146-151.(in Chinese)
[8] Bakshi B R.Multiscale PCA with application to multivariate statistical process monitoring[J].AIChE Journal, 1998, 44(7):1596-1610.
[9] Simoglou A, Martin E B, Morris A J.Statistical performance monitoring of dynamic multivariate processes using state space modeling[J].Computers and Chemical Engineering, 2002, 26(6):909-920.
[10] Negiz A, Cinar A.Statistical monitoring of multivariable dynamic processes with state-space models [J].AIChE Journal, 1997, 43(8):2002-2020.
[11] Yang Jian, Jin Zhong, Yang Jingyu, et al.Essence of kernel Fisher discriminant:KPCA plus LDA[J].Pattern Recognition, 2004, 37(10):2097-2100.
[12] Yang Jian, Frangi Alejandro F, Yang Jinyu, et al.KPCA plus LDA:A complete kernel Fisher discriminant framework for feature extraction and recognition[J].IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27(2):230-244.
[13] Yang Jian, Gao Xiumei, Zhang David, et al.Kernel ICA:An alternative formulation and its application to face recognition[J].Pattern Recognition, 2005, 38(10):1784-1787.
[14] Lee Jong-Min, Yoo Chang-Kyoo, Choi Sang-Wook, et al.Nonlinear process monitoring using kernel principal component analysis[J].Chemical Engineering Science, 2004, 59(1):223-234.
[15] Baudat G, Anouar F.Generalized discriminant analysis using a kernel approach[J].Neural Computation, 2000, 12(10):2385-2404.
[16] Schölkopf B, Smola A, Müller K.Nonlinear component analysis as a kernel eigenvalue problem[J].Neural Computation, 1998, 10(5):1299-1319.
[17] Johnson R A, Wichern D W.Applied multivariate statistical analysis[M].3rd ed.Englewood Cliffs, New Jersey:Prentice-Hall, 1992.
[18] Martin E B, Morris A J.Non-parametric confidence bounds for process performance monitoring charts[J].Journal of Process Control, 1996, 6(6):349-358.
[19] Chen Q, Wynne R J, Goulding P, et al.The application of principal component analysis and kernel density estimation to enhance process monitoring[J].Control Engineer Practice, 2000, 8(5):531-543.
Memo
- Memo:
- Biographies: Zhang Xi(1974—), male, graduate; Shao Huihe(corresponding author), male, professor, HHshao@sjtu.edu.cn.