Research On Modeling And Optimization Of Pulverizing System In Thermal Power Plant

Coal plays an important role in the energy sector.China consumes huge amounts of coal every year.The efficient use of coal is of great value to Chinese social and economic development and improvement of Chinese livelihood.At this stage,power plants mainly use pulverized coal combustion as a power generation method,therefore,optimizing the pulverizing system to improve the economic benefits of the pulverizing system becomes very important.However,it is difficult to accurately and real-time monitor the internal running state of pulverizing system.It is a feasible method to establish the prediction model of pulverizing system coal fineness and mill current size by using the operational parameters and coal quality parameters of pulverizing system in thermal power plant.Taking HP983 coal mill as the research object,this paper designs and implements a single factor cyclic experiment in the pulverizing system of #5 furnace in a power plant in Henan Province.The coal feed rate,primary air rate,outlet primary air temperature,dynamic separator speed,coal feed rate,coal mill current,coal fineness,and corresponding coal quality data of the coal mill are collected.Using these data,combined with different algorithms,the pulverizing system is modeled to predict the coal fineness and the current of coal mill.The prediction error and root mean square deviation of each model are analyzed and compared,and finally a better prediction effect is achieved.The average relative error between the predicted value of coal fineness and the actual value is 6.48%,and the average relative error between the predicted value of mill current and the actual value is 1.41%.The availability of the model is verified by simulation.Taking the maximum of the comprehensive benefit as the optimization objective,the ant colony algorithm and particle swarm optimization algorithm are used to simulate and optimize the working state of the pulverizing system respectively.The results show that the particle swarm optimization algorithm achieves better results under the same working condition and the same number of iterations.Based on the particle swarm optimization method and the established model,the pulverizing optimization system software is developed and implemented in the thermal power plant.The experimental results show that the software has achieved good results in the on-line optimization of pulverizing system.