基于神经网络的水泥回转窑温度预测模型研究  

Prediction Model of Cement Rotary Kiln Temperature Based on Neural Network

作　　者：王红君[1] 田甘露 赵辉[1,2] 岳有军[1] 

机构地区：[1]天津理工大学天津市复杂系统控制理论与应用重点实验室,天津300000 [2]天津农学院,天津300000

出　　处：《自动化与仪表》2016年第4期4-7,共4页Automation & Instrumentation

基　　金：天津市自然科学基金项目(09JCZDJC23900)

摘　　要：水泥回转窑窑尾气体温度对水泥熟料生产影响重大,建立回转窑温度控制模型对水泥生产具有重要意义。水泥生产工艺过程复杂多变,难以获得精确的数学模型。该文利用BP神经网络可实现非线性映射的特点,建立窑尾温度的预测模型,并通过遗传算法对BP神经网络进行优化,利用山东平邑中联水泥厂实时采集的生产数据进行仿真研究。将优化前后的仿真结果进行对比分析,结果表明,文中建立的神经网络模型能够很好地预测水泥回转窑的窑尾温度。The temperature of cement rotary kiln preheater gas has great significance to the cement clinker production,and it is important to establish rotary kiln temperature control model for cement production. But the cement production process is complicated,it＇s difficult to get accurate mathematical model.This artical used BP neural network which can realize the nonlinear mapping characteristics to establish prediction model of the preheater temperature,and through the genetic algorithm to optimize the BP neural network,by combining shandong pingyi zhonglian cement plant production＇s real-time acquisition data,the simulation research. Compare before and after the optimization of the results of simulation analysis ,it is concluded that the established neural network model can well predict preheater temperature of cement rotary kiln.

关 键 词：水泥回转窑 神经网络 非线性映射 遗传算法 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]