Research And Application Of Timing Prediction In Coal-Fired Unit Coordinated Control System

As a solution to balance the energy supply and demand of boiler and turbine,coordinated control system is widely used in the production process of coal-fired units.However,the classical coordinated control system can not overcome the large delay and inertia of the boiler side completely,resulting in overshoot and fluctuation of some key parameters,which seriously affects the control quality of the system and the safety of operation.With the concept of intelligent power plant put forward,more intelligent algorithms are used to optimize the coordinated control system.It is of great significance to study an algorithm model which can predict the future trend of signals accurately and embed it in the control loop to improve the response ability of the control system,ensure the operation efficiency of the unit and maintain the stability of key parameters.In this paper,the existing coordinated control system optimization scheme is studied in detail,and the timing prediction technology is proposed to optimize the coordinated control system performance.On this basis,all kinds of time series prediction methods are synthetically analyzed,and ARMA model is proved to have better prediction accuracy and applicability through experiments.A series of experiments are carried out to analyze the ARMA model with simulation data,and the relevant characteristics of the model are obtained.On this basis,the modeling process is optimized for the actual application scenario.At the same time,the particle filter algorithm is selected to optimize the prediction model,and then the optimization effect is verified by simulation data.The optimized prediction model is applied to the unit control system of APROS simulation platform,and the application value of the model is proved by comparing the main steam pressure operation data before and after optimization.Finally,it summarizes the main parameters that affect the performance of the prediction model,analyzes the influence of parameter changes on the model by using the test data,puts forward the parameter setting scheme and provides the theoretical basis for the development of the parameter self-tuning program.From the operation data of APROS,it can be observed that the introduction of time series prediction model significantly reduces the overshoot of main steam pressure,and enhances the following of the actual value of main steam pressure to the setting value of sliding pressure curve.The work of this paper provides a new research idea for solving the problem of large delay and inertia on the boiler side and improving the control quality of the coordinated control system.The time series prediction model has strong theoretical significance and engineering application value.