Parameter simulation in performance monitoring system of steam turbine unit for a fossil-fuel power plant

We propose to use a radial basis function neural network to solve the problem brought by the invalid parameters in the steam turbine performance monitoring system. This network has good stability and accuracy. This paper introduces how to use the network to simulate the parameters. At the same time, the paper presents a method of off-line training by MATLAB. This method is simple and convenient to deal with the invalid parameters.