An optimized nearest prototype classifier for power plant fault diagnosis using hybrid particle swarm optimization algorithm

Abstract Correct and rapid fault diagnosis is of great importance for the safe and reliable operation of a large-scale power plant. It is a difficult task, however, due to the structural complexity of a power plant, which needs to deal with hundreds of variables simultaneously in case of fault occurrence. A novel nearest prototype classifier is proposed in this paper to diagnose faults in a power plant. A constructive approach is employed to automatically determine the most appropriate number of prototypes per class, while a hybrid particle swarm optimization (HGLPSO) algorithm is used to optimize the position of the prototypes. The aim is to generate an automatic process for obtaining the number and position of prototypes in the nearest prototype classifier with high classification accuracy and low size. The effectiveness of the HGLPSO classifier is evaluated on eight real world classification problems. Finally, the classifier is applied to diagnose faults of a high-pressure feedwater heater system of a 600-MW coal-fired power unit. The obtained results demonstrate the validity of the proposed approach.

[1]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[2]  R. Ashok Bakkiyaraj,et al.  Optimal reliability planning for a composite electric power system based on Monte Carlo simulation using particle swarm optimization , 2013 .

[3]  Hung-Jen Chang,et al.  Identification of pressurized water reactor transient using template matching , 2011 .

[4]  Utpal Garain,et al.  Prototype reduction using an artificial immune model , 2008, Pattern Analysis and Applications.

[5]  Klaus Obermayer,et al.  Soft nearest prototype classification , 2003, IEEE Trans. Neural Networks.

[6]  Wang Li.  A Cooperative Evolutionary Algorithm Based on Particle Swarm Optimization and Simulated Annealing Algorithm , 2006 .

[7]  Francisco Herrera,et al.  Differential evolution for optimizing the positioning of prototypes in nearest neighbor classification , 2011, Pattern Recognit..

[8]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[9]  Inés María Galván,et al.  Building Nearest Prototype Classifiers Using a Michigan Approach PSO , 2007, 2007 IEEE Swarm Intelligence Symposium.

[10]  Chia-Feng Juang,et al.  A hybrid of genetic algorithm and particle swarm optimization for recurrent network design , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[11]  Francisco Herrera,et al.  Prototype Selection for Nearest Neighbor Classification: Taxonomy and Empirical Study , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Loris Nanni,et al.  Particle swarm optimization for prototype reduction , 2009, Neurocomputing.

[13]  Inés María Galván,et al.  AMPSO: A New Particle Swarm Method for Nearest Neighborhood Classification , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[14]  Ali Ajami,et al.  Data driven approach for fault detection and diagnosis of turbine in thermal power plant using Independent Component Analysis (ICA) , 2012 .

[15]  Poong Hyun Seong,et al.  A dynamic neural network aggregation model for transient diagnosis in nuclear power plants , 2007 .

[16]  María José del Jesús,et al.  KEEL: a software tool to assess evolutionary algorithms for data mining problems , 2008, Soft Comput..

[17]  Saman K. Halgamuge,et al.  Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients , 2004, IEEE Transactions on Evolutionary Computation.

[18]  Poong Hyun Seong,et al.  A dynamic neural network based accident diagnosis advisory system for nuclear power plants , 2005 .

[19]  Celso Marcelo Franklin Lapa,et al.  Neural and genetic-based approaches to nuclear transient identification including 'don't know' response , 2006 .

[20]  James C. Bezdek,et al.  Nearest prototype classifier designs: An experimental study , 2001, Int. J. Intell. Syst..

[21]  Ma Liang-yu,et al.  Fault intelligent diagnosis for high-pressure feedwater heater system of a 300 MW coal-fired power unit based on improved BP neural network , 2002, Proceedings. International Conference on Power System Technology.

[22]  Liangyu Ma,et al.  An Intelligent Power Plant Fault Diagnostics for Varying Degree of Severity and Loading Conditions , 2010, IEEE Transactions on Energy Conversion.

[23]  R. Eberhart,et al.  Empirical study of particle swarm optimization , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[24]  Nian Zhang,et al.  Time series prediction with recurrent neural networks trained by a hybrid PSO-EA algorithm , 2004, Neurocomputing.

[25]  Kalyan Veeramachaneni,et al.  Fitness-distance-ratio based particle swarm optimization , 2003, Proceedings of the 2003 IEEE Swarm Intelligence Symposium. SIS'03 (Cat. No.03EX706).

[26]  José Neves,et al.  The fully informed particle swarm: simpler, maybe better , 2004, IEEE Transactions on Evolutionary Computation.

[27]  Roberto Schirru,et al.  Identification of nuclear power plant transients using the Particle Swarm Optimization algorithm , 2008 .

[28]  Jouni Lampinen,et al.  Differential evolution based nearest prototype classifier with optimized distance measures for the features in the data sets , 2013, Expert Syst. Appl..

[29]  Waclaw Gudowski,et al.  Feasibility Study on Transient Identification in Nuclear Power Plants Using Support Vector Machines , 2006 .

[30]  Celso Marcelo Franklin Lapa,et al.  An efficient Neuro-Fuzzy approach to nuclear power plant transient identification , 2011 .

[31]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[32]  Francisco Herrera,et al.  A preliminary study on the use of differential evolution for adjusting the position of examples in nearest neighbor classification , 2010, IEEE Congress on Evolutionary Computation.

[33]  Mark J. Embrechts,et al.  Hybrid identification of nuclear power plant transients with artificial neural networks , 2004, IEEE Transactions on Industrial Electronics.

[34]  Amir F. Atiya,et al.  Self-generating prototypes for pattern classification , 2007, Pattern Recognit..

[35]  Jouni Lampinen,et al.  Differential Evolution Classifier in Noisy Settings and with Interacting Variables , 2011, Appl. Soft Comput..

[36]  Enrico Zio,et al.  Fuzzy identification of transients in nuclear power plants , 2003 .

[37]  James M. Keller,et al.  A possibilistic approach to clustering , 1993, IEEE Trans. Fuzzy Syst..

[38]  Ginés Rubio,et al.  New method for instance or prototype selection using mutual information in time series prediction , 2010, Neurocomputing.

[39]  Francisco Herrera,et al.  A Taxonomy and Experimental Study on Prototype Generation for Nearest Neighbor Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[40]  Qiong Li,et al.  On-line monitoring the performance of coal-fired power unit: A method based on support vector machine , 2009 .

[41]  Jing J. Liang,et al.  Comprehensive learning particle swarm optimizer for global optimization of multimodal functions , 2006, IEEE Transactions on Evolutionary Computation.

[42]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[43]  Tony R. Martinez,et al.  Reduction Techniques for Instance-Based Learning Algorithms , 2000, Machine Learning.

[44]  Jin Ma,et al.  Fault Diagnosis for the Feedwater Heater System of a 300MW Coal-Fired Power Generating Unit Based on RBF Neural Network , 2005, ICMLC.

[45]  Fernando Fernández,et al.  Evolutionary Design of Nearest Prototype Classifiers , 2004, J. Heuristics.

[46]  Sandip Sen,et al.  PLEASE: A Prototype Learning System Using Genetic Algorithms , 1995, ICGA.

[47]  Salman Mohagheghi,et al.  Particle Swarm Optimization: Basic Concepts, Variants and Applications in Power Systems , 2008, IEEE Transactions on Evolutionary Computation.

[48]  Liangyu Ma,et al.  Fuzzy neural network approach for fault diagnosis of power plant thermal system under different operating points , 2008, 2008 IEEE Power and Energy Society General Meeting - Conversion and Delivery of Electrical Energy in the 21st Century.

[49]  Suneet Singh,et al.  Optimal allocation of capacitors in distribution systems using particle swarm optimization , 2012 .

[50]  E. S. Ali,et al.  A hybrid Particle Swarm Optimization and Bacterial Foraging for optimal Power System Stabilizers design , 2013 .