Anfis Based Prediction Model for Reduction of Failure Frequency in Captive Power Plant

Om Prakash, Anil Kumar, T. Rav

Abstract

Boiler-Turbine unit is a complex multivariable system with high time variation, uncertainty and coupling. The improvement of its control quality is a key problem for automation improvement in thermal engineering. Adaptive Neuro-Fuzzy Inference System (ANFIS) is the neural network realization for Takagi and Sugeno fuzzy inference system. ANFIS can not only approach any linear and nonlinear function with any precision, but also quicken convergence speed, decrease errors, and lessen training data that are needed. The frequency of fluctuation of the water level in the drum may be significantly reduced by the ANFIS modeling of the water tube boiler water feed system to the drum. The ANFIS model applied for the boiler feed system in the Power plant will not only increases the efficiency of the system but shall considerably reduce the tripping of the power