Neural Network based Modeling of Power Plant with Reduced Number of Input Variables

Abstract

This paper describes the development of an artificial neural network based modeling of a 210MW coal based thermal power plant. As the power plant involves large number of parameters (variables), it is very difficult to identify the significant inputs that affect the output. A criterion for input variable identification of dynamical systems using fuzzy curve method is applied to reduce the number of inputs to the NN model. The method also establishes the correlation between input and output. Due to complexity and non-linearity of the system, the model finds its application in design, analysis and operational studies. Evaluation and validation of the model are performed by predicting the boiler-turbine parameters using different set of actual plant data. The neural network model is shown to be capable of predicting the output parameters with good accuracy and therefore it has got real time application. The dynamic model of the power plant has been built with MATLAB.

Indexing terms:

• Power plant
• Dynamic model
• Fuzzy curve
• Input identification
• NN model
• Multilayer feed forward network

Additional information

Notes on contributors

S P Karna

S P Karna was born on 1st May 1967 in Darbhanga, Bihar. He received the BSc (Engg) degree in Electronics & Communication Engineering from Bihar Institute of Technology, Sindri (Dhanbad), Ranchi University in 1989. Presently, he is working as a Supdt (C&l) in NTPC Kahalgaon (Bhagalpur), Bihar. He received the NTPC sponsored MTech degree in Power Generation Technology from the Indian Institute of Technology (IIT) Delhi in 2001. His main areas of interest are Artificial neural network, Measurement and Instrumentation. He is a life member of IETE, ISTE & IE (I) and member of CSI & AIMA.

Nesar Ahmad

Nesar Ahmad was born in 1961 in I Patna, India. He received the BSc (Engg) degree in Electronics & Communication Engineering from Bihar College of Engineering, Patna University, Patna, India, in 1984, the Master's degree in Information Engineering from City University, London, UK, in 1989, and the PhD degree from the Indian Institute of Technology (IIT) Delhi, India, in 1993. He is currently an Assistant Professor in the Department of Electrical Engineering, IIT Delhi. His research interests include Soft Computing, Web Applications, Real Time Systems and Microprocessor/Micro-controller based system design.