Ultra Supercritical Power Unit Modelling Based On Neural Networks

Thermal power unit is a load system consisting of the boiler,the turbine and their auxiliary machines respectively.It is a complicated multivariable system with strong nonlinearity,uncertainty and multivariable coupling.These characters will be more evident with the unit tending to large-capacity and high-parameter.It is expensive to build the model of the unit using conventional method.Based on the mechanism analysis of the thermal power unit,this paper presents a simulation study on modeling a 1000MW ultra supercritical once-through boiler unit by BP neural network,RBF neural network and fuzzy neural network respectively.On the basic of mechanism analysis,the simplified nonlinear model is chosen as the basis of this dissertation.In this dissertation,all the data used to model identification and testing is sampled from the production field.This has pretty high engineering utility values.Based on these field data,many different neural networks are used to model the thermal power unit.The simulation results validate the efficiency of the neural networks in modelling the 1000MW ultra supercritical unit.