A 12-Input-3-Output RBF Neural Network Model of Load and Main Steam Pressure Characteristics for Ultra-Supercritical Unit

Abstract

In this paper, an 1000MW ultra-supercritical boiler unit was taken as the research case. The neural network, RBF, was used to build the model for the 1000MW ultra supercritical unit based on Matlab. The inputs of the model include fuel amount, feedwater flow,turbine valve opening demand. The outputs include unit load, main steam pressure and intermediate point temperature. The simulation results proved the validity of the model. The model can be used to improve the response rate of the unit load and optimize the coordinating control with certain practical engineering significance.