| With the acceleration of urbanization and the increase of domestic waste,the waste incineration power generation method has been more and more widely used.Because the process has complex characteristics such as frequent interference,strong coupling and nonlinearity,which is not conducive to the design and implementation of the control system,and may cause a series of environmental pollution problems,so the research on the stability control,operation optimization and parameter soft measurement of the process has been widely concerned.In order to minimize the cost and risk of on-site debugging,it is necessary to carry out simulation experiments in the laboratory to determine the safety and effectiveness of the methods before implementing operation optimization,stability control and other methods in the actual industrial site.Therefore,the development of simulation modeling and experimental platform for production process is particularly important.In order to provide a convenient operating environment for the study of parameters control and optimization method of municipal solid waste incineration process,this paper establishes a furnace temperature model of the process of waste incineration,develops a set of model operating software for the process control of waste incineration,and designs a series of experiments to test and analyze the furnace temperature model and software system.The main work is as follows:(1)The temperature model of MSW incinerator is established.Based on the analysis of the modeling difficulties of the process and mechanism of MSW incineration,the temperature model of MSW incinerator furnace is established by using the data-driven method.As the furnace temperature is the most important control variable in the process of MSW incineration,the accuracy of its model plays an important role in the control of the incineration process.Based on the analysis of the advantages and disadvantages of the traditional Gradient boosting decison tree(GBDT)modeling method,this paper proposes an improved GBDT modeling algorithm,which combines the ideas of Bagging method and Random subspace method with GBDT,constructs the BR-GBDT algorithm,realizes the parallel integration of multiple GBDTs,and improves the generalization ability of the model.Compared with other classical algorithms in UCI data set,the results show that BR-GBDT algorithm has smaller error and can achieve more accurate prediction function;(2)The model operation software of MSW incineration process is designed and developed.Based on the analysis of the experimental functions and data requirements,combined with the characteristics of many models and complex control tasks of waste incineration process,a set of software for dynamic model operation of waste incineration process is developed based on the dynamic model of the process.Firstly,the structure and function of the model software are designed.The structure consists of three layers: background model layer,module communication layer and human-machine interface layer.The main functions include dynamic simulation of incineration process,model calculation,data management,real-time communication,real-time trend chart display and user management,etc.;secondly,according to the modular programming idea,the user login management module,unity3 d simulation module,parameter setting module,trend chart module,data query module and OPC communication module are developed with C# advanced language;at last,the background model is developed by MATLAB,and the background algorithm support is provided by the hybrid programming technology of.Net and MATLAB;(3)Experimental study.Using the historical data provided by Gao’antun waste incineration power plant,Chaoyang District,Beijing,the temperature model of BR-GBDT furnace has been tested.The experimental results show that the model is better than some classical methods,which proves the effectiveness of the model.In addition,a series of experiments are designed to test the function of the model operation software.The results show that the model software can run normally,carry out 3D simulation and data operation for the industrial process of waste incineration,and communicate with other hardware devices in real time,thus providing a virtual research object for the hardware in the loop simulation platform,as well as laying a foundation for the follow-up research on the industrial process of waste incineration. |