NEURO-FUZZY MODELING OF SUPERHEATING SYSTEM OF A STEAM POWER PLANT
ABSTRACT
Fuzzy control is an application of fuzzy reasoning to control. Although most applications of fuzzy theory have been biased toward engineering, these applications have recently reached other disciplines, such as medical diagnostics, psychology, education, economy, management, sociology, etc..
An artificial neuron model simulates multiple inputs and one output, the switching function of input–output relation, and the adaptive synaptic weights. Today, several continuous functions, such as sigmoidal or radial functions, are used as a neuron characteristic functions , which results higher performance of NNs.
In this paper how a neuro-fuzzy algorithm is employed for the modeling of power plant superheating subsystems, including three superheaters and four de- super heatersare explained. Time delays that exist in the real system are considered in the modeling. After that, using subtractive clustering, in order to reduce the number of fuzzy rules, a model with high accuracy is achieved for set of complex subsystems. Then, all these models are put together to reach the global model of the superheating process. .To explain these concept in this paper Superheating system of a 325MW steam power plant is modeled based on the recurrent neuro-fuzzy networks and subtractive clustering. The experimental data are obtained from a complete set of field experiments under various operating conditions. Nine neuro-fuzzy models are constructed and trained for seven subsystems of the superheating unit. Then, these nine fuzzy models are put together merging series and parallel units according to the real power plant subsystems, to obtain the global model of the superheating process. Comparing the time response of the nonlinear neuro-fuzzy model of a subsystem with the time response of its linear model based on the Least Square Error (LSE) method, indicates that the nonlinear neuro-fuzzy model is more accurate and reliable than the linear model in the sense that its response is closer to the response of the actual superheating system.
