Research On Prediction And Control Of Cement Decomposing Furnace Outlet Temperature

Cement is an indispensable building material,with huge demand,large resource consumption,and large pollution emissions,so the efficient and energy-saving production of cement is of great significance.In the cement production process,the suspension preheating and pre-decomposition process assumes 90% of the cement raw material decomposition task,the coal consumption is huge,and it plays a vital role in the production and quality of the cement.At present,the production environment of domestic cement production enterprises is complex,and there are few system measurement and control points.The optimal adjustment of the pre-decomposition process has not been widely studied and promoted.Therefore,the article starts from the current research situation of decomposition furnace control at home and abroad,and uses data-driven modeling methods and intelligent control technology to realize the prediction and optimal control design of the decomposition furnace outlet temperature,which is of great significance for the realization of efficient production of cement and energy saving.This article takes a 6000t/d cement production line of a cement production company in Anhui Province as the research background,and the decomposition furnace system as the research object.Through field study and inspection,and consulting relevant literature,starting from the structure of the decomposition furnace and the process flow,the prediction and optimal control of outlet temperature of cement calciner are studied deeply.This thesis first briefly summarizes the development and current status of new dry cement production,and systematically summarizes the control research and application of cement production systems at home and abroad.On the basis of in-depth study and analysis of the technological process and mechanism of the cement pre-decomposition system,in order to cope with complex technological processes and production environments,the thesis proposes a particle swarm optimization extreme learning machine outlet temperature prediction model based on Lasso algorithm.Compared with the research of traditional pre-decomposition systems,most of them adopt the empirical method to select variables such as wind(tertiary air),feed(raw meal),and coal(coal feed).,it is easy to cause problems such as low prediction accuracy and weak generalization ability of the model.Based on the field data,this thesis uses the Lasso algorithm to sparse multi-variables,and uses the Lars algorithm to solve,removeirrelevant and weakly correlated variables from many variables,scientifically and accurately determine the main factors that affect the temperature of the decomposition furnace outlet,and eliminate irrelevant variables Interference and reduce data redundancy,complete the screening of variables.Then divide the data set,established outlet temperature prediction based on particle swarm optimization parameters ELM calciner model.Through simulation verification and comparative analysis,the excellent prediction effect and accuracy of the model are proved.Then,on this basis,on the premise of ensuring the normal operation of industrial production,the main variable parameters of the pre-decomposition system are adjusted and optimized.And According to the production situation of the cement industry,a fuzzy neural controller with coal feeding as the controlled quantity is designed to realize the intelligent optimal control design of the outlet temperature of the calciner.The simulation results show that the control model has a better control effect.And can better meet the needs of the industry.Finally,the configuration software is used to design the man-machine interface of the upper computer of the system,and the real-time monitoring of the industrial system is realized.