Independent component analysis approach for fault diagnosis of condenser system in thermal power plant

Abstract

A statistical signal processing technique was proposed and verified as independent component analysis (ICA) for fault detection and diagnosis of industrial systems without exact and detailed model. Actually, the aim is to utilize system as a black box. The system studied is condenser system of one of MAPNA’s power plants. At first, principal component analysis (PCA) approach was applied to reduce the dimensionality of the real acquired data set and to identify the essential and useful ones. Then, the fault sources were diagnosed by ICA technique. The results show that ICA approach is valid and effective for faults detection and diagnosis even in noisy states, and it can distinguish main factors of abnormality among many diverse parts of a power plant’s condenser system. This selectivity problem is left unsolved in many plants, because the main factors often become unnoticed by fault expansion through other parts of the plants.

Keywords

condenser / fault detection and diagnosis / independent component analysis / independent component analysis (ICA) / principal component analysis (PCA) / thermal power plant

References

[1] OrdysW, PikeA W, JohnsonM A, KetabiR M, GrimbleM JModeling and simulation of power generation plants [M], 1994, London, Springer-Verlag: 4-13

[2] ChiangL H, RusselE L, BraatzR DFault detection and diagnosis in industrial systems [M], 2001, London, Springer-Verlag: 3-6

[3] IsermannR. Model based fault detection and diagnosis methods [C]. American Control Conf, 1995, New Jersey, IEEE Press: 1605-1609

[4] GertlerJ G. Survey of model-based failure detection and isolation in complex plants [J]. IEEE Control Systems Magazine, 1988, 8(6): 3-11

[5] SreedharRFault diagnosis and control of a thermal power plant [D], 1995, Texas, University of Texas at Austin

[6] WillskyS. A survey of design methods for failure detection in dynamic systems [J]. Automatica, 1976, 12(1): 601-611

[7] IsermannR. Process fault detection based on modeling and estimation methods: A survey [J]. Automatica, 1984, 20(4): 309-326

[8] BasevilleM. Detecting changes in signals and systems: A survey [J]. Automatica, 1988, 24(3): 309-326

[9] PattonR J, ChenJ. Parity space approach to model based fault diagnosis: A tutorial survey and some new result [C]. IFAC/IMACS Symp, 1991, Baden, Germany, SAFER PROCESS’91 Baden (G): 115-123

[10] LouX-shengExpert system for power plants monitoring [D], 1996, Wuhan, Huazhong University of Science & Tech

[11] KramerM A. Malfunction diagnosis using quantitative models with non-Boolean reasoning in expert systems [J]. American Institute of Chemical Engineers Journal, 1987, 33: 130-140

[12] PattonR J, FrankP M, ClarkR NFault diagnosis in dynamic systems, theory and application [M], 1989, New York, Prentice-Hall: 15-28

[13] DOYLE R J, CHAREST L, ROUQUETTE N, WYATT J, ROBERTSON C. Causal modeling and event-driven simulation for monitoring of continuous systems [J]. Computers in Aerospace, 1993: 395.

[14] JacksonJ EA user guide to principal components [M], 1991, New York, John Wiley & Sons: 64-78

[15] DaneshvarM, FarhangiB. Data driven approach for fault detection and diagnosis of boiler system in coal fired power plant using principal component analysis [J]. International Review of Automatic Control (IREACO), 2010, 3(2): 198-208

[16] AjamiA, DaneshvarM. Data driven approach for fault detection and diagnosis of turbine in thermal power plant using independent component analysis (ICA) [J]. Electrical Power and Energy Systems: Elsevier, 2012, 43(1): 728-735

[17] JolliffeI T, IncEPrincipal component analysis [M], 20022nd EdNew York, Springer

[18] KeZ, UpadhyayaB R. Model based approach for fault detection and isolation of helical coil steam generator systems using principal component analysis [J]. IEEE Transactions on Nuclear Science: IEEE, 2006, 53(4): 2343-2352

[19] HyvarinenA. Fast and robust fixed-point algorithms for independent component [J]. IEEE Transactions on Neural Networks: IEEE, 1999, 10(3): 626-634

[20] HyvarinenA, OjaE. A fast fixed-point algorithm for independent component analysis [J]. Neural Computation, 1997, 9(7): 1483-1492

[21] PuttenH V, ColonnaP. Dynamic modeling of steam power cycles (Part I): Simulation of a small simple Rankine cycle system [J]. Applied Thermal Engineering, 2007, 27(2/3): 467-480

[22] PuttenH V, ColonnaP. Dynamic modeling of steam power cycles (Part II): Simulation of a small simple Rankine cycle system [J]. Applied Thermal Engineering, 2007, 27(14/15): 2566-2582

[23] BollandO. A comparative evaluation of advanced combined cycle alternatives [J]. Journal of Engineering Gas Turbines Power, 1991, 113(2): 190-197