Optimization Of Furnace Temperature Based On Assessment Of Particle Swarm Optimization Algorithm

The heating furnace is not only the core thermal equipment but also the main energy consumption equipment in the iron and steel industry.The furnace temperature optimization of the heating furnace is to determine the furnace temperature setting value of each section of the heating furnace,so that the billet can meet the requirements of rolling temperature,reduce the consumption of fuel and reduce the oxidation burning rate of the billet,so as to improve the quality of the heating billet and reduce the production cost.Therefore,the determination of a reasonable furnace temperature system is of great significance to improve the heating efficiency of the furnace and reduce energy consumption for the energy conservation of the whole iron and steel industry.The distribution model of furnace temperature along the direction of furnace length is established for the difficulty of continuous on-line measurement of furnace temperature and steel temperature.Combined with the practical project,the temperature prediction model of billet based on the total absorption rate is established by using the total absorption rate method.Furnace temperature optimization is a complex multi-dimensional and multi-constraint optimization problem.The classical optimization method is easy to fall into the local optimal problem because of the influence of the initial value.The current intelligent algorithms such as particle swarm optimization also have the problem of premature convergence and low convergence precision.Therefore,on the basis of the standard particle swarm optimization algorithm,it is improved.The idea of evaluating and selecting the best is introduced into the particle swarm optimization algorithm.The algorithm constructs a series of events such as ranking,elimination and rectification in the process of assessment.The improved particle swarm optimization algorithm,the standard particle swarm optimization algorithm,the standard genetic algorithm and the improved particle swarm optimization algorithm are tested in terms of convergence speed and convergence accuracy based on the commonly used standard test functions.The objective function of furnace temperature optimization based on minimum energy consumption and roughing process for billet temperature is established,and the particle swarm optimization algorithm with assessment mechanism is applied to the optimization calculation of furnace temperature setting with the production objective in the production process as the constraint condition.Finally,the furnace temperature,billet surface temperature,billet center temperature and billet section temperature difference before and after optimization are compared and analyzed.The results show that the heating quality of the billet is.improved and the energy consumption of the furnace is reduced.