Parameter Identification Of Thermal Power Unit Model Based On The On-line Data

The thesis studied the parameter identification of 500MW thermal power unit model based on the on-line data. After analyzing and discussing the identifying closed-loop of control system, several identifiable conditions were given; The thesis selected data from dynamic process of unit to meet the continued inspirit conditions of input signals; In view of the characteristic of the running data of power plant, a lot of work was done on data processing, such as eliminating and correcting the unreasonable data, removing the noise from the corrupted data with wavelet transform, data smoothing; After analyzing the mill process, boiler heat storage process, super-heater pressure differential process, turbine dynamic, it established simplified model of 500MW thermal power unit and analyzed identifying parameter of model, then the method of parameter identification is given; The steam turbine dynamic model was taken as identification object. It is identified by using HNN optimize arithmetic. Through testing the obtained model, the results show that the model has high fitness and the identification result is good.