Intelligent Predictive Control Of Cement Mill

The mill is one of the most important equipment in cement grinding system.Mill load is closely related to the production efficiency and the quality of cement products.Therefore,it is great significance to study the load of the mill.With the continuous improvement of automation level,the requirements of model research and optimization control will be higher and higher.Because the mill is a complex industrial object,it has the characteristics of multi variable,nonlinear,time delay,strong coupling,and a lot of disturbance factors,the conventional control algorithm is difficult to achieve good control effect.In this paper,the automatic control system of a cement plant is taken as the research object.Based on the research of the cement grinding system at home and abroad,the intelligent predictive control is used to optimize the mill load.On the basis of summarizing the expert's experience,this paper chooses the separator speed as the input and the output current of the grinder as the output,and selects the forecasting strategy based on the neural network to optimize the mill load,and the cement mill Neural Network Predictive Control Software for Machine Current.The main work of this paper is as follows:(1)BP neural network with three layer is used to identify the model of the mill load system and the predictive controller is designed.Firstly,the input and output data are collected to identify the input and output delay order number of the system model and the parameters of the BP neural network;Then the neural network model is used as the predictive control model,and the N-R rolling optimization method is used to calculate the future control sequence;Finally,the effectiveness of the algorithm in the automatic control system of cement mill is verified by Matlab simulation.(2)It is used to develop predictive control software by MFC and Matlab mixed programming.First of all,Matlab Compiler method by using M files compiled into dynamic link library file,and call the DLL file to achieve the function of the algorithm module in VC ++;Then,the use of OPC technology to achieve data read and write functions;Finally,in order to achieve the dynamic effect of the display,in the MFC program to import TeeChart5 control,used to show real-time display grinder current trends to achieve the user interface design.(3)For the practical application of the project,it is necessary to verify the effectiveness of the optimization control software.The input and output data are written to the DCS to restore the operating conditions.The software is used to verify the optimal control effect by observing the real-time curve.The results show that the optimal control software developed in this paper can adjust the current of the elevator to reach the set value.