Research On Multi-population Intelligent Optimization Algorithm And Its Application In Cement Grate Cooler

The cement industry is facing high pollution and high energy consumption.How to effectively improve the environment and increase the efficiency of cement production has become the focus of the industry.The cooling of high-temperature cement clinker and the accompanying heat recovery are urgent problems to be solved.The cement grate cooler is the key equipment to solve the above problems.The gas-solid heat exchange process of the clinker cooler directly affects the quality of the cement and the energy consumption of production.Optimizing the important parameters involved in the gas and solid heat exchange process in the cement grate cooler can greatly improve the grate cooling The heat exchange efficiency of the machine reduces pollutant emissions.The traditional method based on mechanism analysis is difficult to establish its model,and it is difficult to optimize and adjust the working conditions.The swarm intelligence optimization algorithm has been well applied in system modeling and problem optimization,so it has received extensive attention and research from all walks of life.Therefore,the in-depth study of swarm intelligent optimization algorithm and its application to the identification and parameter optimization of grate coolers have important theoretical guidance significance and practical reference value for improving the heat transfer efficiency of grate coolers.The main research contents of this article are as follows:Firstly,in order to solve the problems of low convergence accuracy and poor search performance of the multi-objective particle swarm algorithm,a research on multi-population MOPSO algorithm based on velocity communication(MVCMOPSO)was proposed.The algorithm introduces a speed communication mechanism,divides the population into multiple sub-populations to achieve speed information sharing,improves the single search mode formula of particles,and improves the global search ability of the algorithm.Chaotic sequences are used to optimize the inertial weights,improve the traversal and globality of particle search,and to reduce the possibility of the algorithm falling into the local optimal Pareto front at the later stage of the operation,different mutation operations are performed on each subpopulation.The algorithm is compared with multiple advanced multi-objective optimization algorithms.The experimental resultsshow that the solution set obtained by the algorithm has better convergence and distribution,which provides an algorithm basis for the optimization of grate cooler parameters.Secondly,in order to solve the problem that the gray wolf algorithm is easy to fall into local optimum and poor global optimization ability,an improved Multi-population gray wolf algorithm(MPGWO)is proposed to divide a single population into multiple groups and use chaos In order to initialize the subpopulations in sequence,in order to prevent the algorithm from converging prematurely,reverse learning mutations are made on the decision-level individuals of each sub-population,and competitive strategies are introduced to dynamically update the various group decision-level individuals to improve the algorithm's global optimization capabilities.An improved multi-group gray wolf algorithm is used to optimize the input weights and hidden layer threshold parameters of the extreme learning machine to improve the prediction accuracy and generalization ability of the model,and establish the MPGWO-ELM prediction model.The validity of the model is verified using sample data sets.It can be seen from the experimental simulations that the established MPGWO-ELM prediction model has high identification accuracy and strong generalization ability.Make full preparations for the subsequent establishment of the key parameter prediction model of the grate cooler.Finally,the MPGWO-ELM identification model is used to establish the identification models of the secondary air temperature and the clinker temperature at the outlet of the cement grate cooler.The improved MVCMOPSO algorithm is used to optimize the grate cooler parameters to find that the controlled variable is optimal.The value of the control variable.Through the analysis of the secondary air temperature of the cement grate cooler,the clinker temperature at the outlet and the heat transfer efficiency,the necessity of optimizing the key parameters of the grate cooler and the effectiveness of the algorithm are verified.