Abstract
Power plant equipment must be monitored closely to prevent failures from disrupting plant availability. Online monitoring technology integrated with hybrid forecasting techniques can be used to prevent plant equipment faults. A self learning rule-based expert system is proposed in this paper for fault forecasting in power plants controlled by supervisory control and data acquisition (SCADA) system. Self-learning utilizes associative data mining algorithms on the SCADA history database to form new rules that can dynamically update the knowledge base of the rule-based expert system. In this study, a number of popular associative learning algorithms are considered for rule formation. Data mining results show that the Tertius algorithm is best suited for developing a learning engine for power plants. For real-time monitoring of the plant condition, graphical models are constructed by K-means clustering. To build a time-series forecasting model, a multi layer preceptron (MLP) is used. Once created, the models are updated in the model library to provide an adaptive environment for the proposed system. Graphical user interface (GUI) illustrates the variation of all sensor values affecting a particular alarm/fault, as well as the step-by-step procedure for avoiding critical situations and consequent plant shutdown. The forecasting performance is evaluated by computing the mean absolute error and root mean square error of the predictions.
Similar content being viewed by others
References
M.N. Lakhoua, Application of functional analysis on a SCADA system of a thermal power plant. Adv. Electr. Comput. Eng. 9, 90–99 (2009)
Z.A. Vale, A. Machado e Moura, Sparse: an intelligent alarm processor and operator assistant. IEEE Expert 12, 86–93 (1997)
H.-J. Lee, D. Young, A fuzzy expert system for the integrated fault diagnosis. IEEE Trans. Power Deliv. 15, 833–838 (2000)
C. Pimpa, S. Premrudeep, Voltage control in power system using expert system based on SCADA system, in IEEE Conference on Power Engineering, 2002, pp. 1286–1288
V.N.A.L. Da Silva, R. Linden, G.F. Ribeiro, A framework for expert systems development integrated to a SCADA/EMS environment, in IEEE Conference on Intelligent Applications to Power Systems, 2007, pp. 1–5
H. Zeng, J. Guo, Z. Xiao, Real time embedded maintenance system of hydro-generator excitation system, International Conference on Condition Monitoring and Diagnosis, 402-406, 2008
E.J. Amaya, A.J. Alvares, SIMPREBAL: an expert system for real-time fault diagnosis of hydro-generator machinery, in IEEE Conference on Emerging Technologies and Factory Automation, 2010, pp. 1–8
E.A. Feigenbaum, The art of artificial intelligence: 1. Themes and case studies of Knowledge Engineering, IJCAI-77, 1977, pp. 1014–1029
S.J. Cheng, D.S. Chen, X.L. Peng, An expert system for a thermal power station alarm processing. Int. Conf. Adv. Power Syst. Control Op. Manag. 2, 316–320 (1991)
W. Guo, F. Wen, Z. Liao, L. Wei, J. Xin, An analytic model-based approach for power system alarm processing employing temporal constraint network. IEEE Trans. Power Deliv. 25(4), 2435–2447 (2010)
Y. Ping, L. Sui-sheng, Z. Hao, Fault diagnosis for large-scale equipments in thermal power plant by data mining. Control Theory Appl. 21, 927–931 (2004)
S. Russel, P. Norvig, Artificial Intelligence: A Modern Approach, 2nd edn. PHI
U.M. Fayyad, Data mining and knowledge discovery: making sense out of data. IEEE Expert: Intell. Syst. Appl. 11(5), 20–25 (1996)
R.M. Roth, W.C. Wood, A Delphi approach to acquiring knowledge from single and multiple experts, in ACM Conference on Trends and Directions in Expert Systems, 1990, pp. 301–324
M.M. Mazid, A.S. Ali, K.S. Tickle, Finding a unique association rule mining algorithm based on data characteristics, in IEEE International Conference on Electrical and Computer Engineering, 2008, pp. 902–908
R. Agarwal, J. Shafer, Parallel mining of association rules. IEEE Trans. Knowl. Data Eng. 8, 962–969 (1996)
S. Kotsianti, D. Kanellopoulos, Association rules mining: a recent overview. GESTS Int. Trans. Comput. Sci. Eng. 32, 71–82 (2006)
J. Han, Y. Fu, Discovery of multiple-level association rules from large databases. IEEE Trans. Knowl. Data Eng. 11, 345–356 (1999)
F. Bonchi, B. Goethals, F.P. Bonsai, The art of growing and pruning small FP trees, in Proceedings on Pacific-Asia Conference on Knowledge Discovery and Data mining, 2004, pp. 155–160
P.A. Flach, N. Lanchiche, Confirmation-guided discovery of first order rules with Tertius. Mach. Learn. 42, 61–95 (2001)
R.C.M. Yam, P.W. Tse, L. Li, P. Tu, Intelligent predictive decision support system for condition-based maintenance. Int. J. Adv. Manuf. Technol. 17, 383–391 (2001)
M. Vyas, B. Modhera, V. Vya, A.K. Sharma, Performance forecasting of common effluent treatment plant parameters by artificial neural network. ARPN J. Eng. Appl. Sci. 6, 38–42 (2011)
T. Kraft, K. Okagaki, R. Ishii, P. Surko, A hybrid neural network and expert system for monitoring fossil fuel power plants, in IEEE First International Forum on Applications of Neural Networks to Power Systems, 1991, pp. 215–218
T. Kanungo, D.M. Mount, N.S. Netanyahu, An efficient K-means algorithm: analysis and implementation. Trans. Pattern Anal. Mach. Intell. 24(7), 881–892 (2002)
N. Mayadevi, S.S. Vinodchandra, S. Ushakumari, Failure forecast engine for power plant expert system shell, in Proceedings of IEEE conference on Advanced Communication Control and Computing Technologies, 2012, pp. 380–384
J. Peraltadonate, G.G. Sanchez, A.S. de Miguel, Time series forecasting: a comparative study between an evolving artificial neural networks: system and statistical methods. Int. J. Artif. Intell. Tools, 21(1), 1250010 (26), 2012
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mayadevi, N., Ushakumari, S.S. & Vinodchandra, S.S. SCADA-based Operator Support System for Power Plant Equipment Fault Forecasting. J. Inst. Eng. India Ser. B 95, 369–376 (2014). https://doi.org/10.1007/s40031-014-0117-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40031-014-0117-9