An Independent Component Analysis Based on Sliding Window Statistics and its Application to Power Plant Equipment State Monitoring

Abstract:

Traditional condition monitoring methods are not suitable for the nonlinear operation parameters and time-variable operation conditions. We propose an independent component analysis method based on sliding window statistics (SSWICA). This method uses statistics in sliding windows of parameters as input samples, then uses a N-step forward sliding window ICA method to modeling. Then we monitor the operating state of the equipments by observing whether the SPE index of real-time parameters exceeds the control limits. SSWICA is applied to condition monitoring of condenser in 600MW unit, comparing with traditional ICA monitoring methods based on sliding window. The results show SSWICA can accurately reflect current operating state and related changes of condensers state parameters, recognize steady, unsteady and fault conditions effectively. It is valuable for engineering practice and suitable for the application to equipments condition monitoring in power plant.

• Periodical: Advanced Materials Research (Volumes 860-863)
• Pages: 1801-1806
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.860-863.1801
• Online since: December 2013
• Authors: Yue Zhao, Feng Qi Si, Zhi Gao Xu
• Keywords: Condenser, ICA, Power Plant, Sliding Window, State Monitoring, Statistics

References

[1] Kamal Hadad, Mojtaba Mortazavi, Mojtaba Mastali and Ali Akbar Safavi. IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 2008, 55(6): 3611-3619.

DOI: 10.1109/tns.2008.2006491

[2] Weili Xiong, Yingwang Xiong, Baoguo Xu. Computers and Applied Chemistry, 2006, 23(4): 303-306. (in Chinese).

[3] Liqing Di, Jie Zhang. Journal of Jilin University (Information Science Edition), 2004, 22(4): 397-400. (in Chinese).

[4] H. Shinzawa, M. Shigeaki, O. Yukihiro, T. Roumiana. Applied Spectroscopy, 2006, 60(8): 884-891.

[5] Xun Wang, Uwe Kruger, George W. Ind. Eng. Chem. Res. 2005, 44: 5691-5702.

[6] Binzhang Lu, Yuhong Zhao, Zhenhua Mao. Fault Diagnosis Method Based on Moving Window PCA[C]. Chinese Control and Decision Conference, (2009).

DOI: 10.1109/ccdc.2009.5195109

[7] Jyh-Cheng Jeng. Journal of the Taiwan Institute of Chemical Engineers, 2010, 41: 475-481.

[8] Jin Wang, Q. Peter He. Ind. Eng. Chem. Res , 2010, 49: 7858-7869.

[9] Q. Peter He, Jin Wang. AIChE Journal, 2011, 57(1): 107-121.

[10] Jutten. C and Hérault.J. Signal Processing, 1991, 24: 1–10.

[11] Hyvarinen A, Oja E.A. Neural Computation, 1997, 9(7): 1483-1492.

[12] Lanxin Zhou, Xuelei Zhang, Yong Li. Turbine Technology, 2002, 44(3): 149-151. (in Chinese).