神经网络的石灰回转窑质量控制模型研究  

Research on Quality Control Model of Lime Rotary Kiln Based on Neural Network

作　　者：朱玲利[1] 张涛[2] 乔斌 栗继魁 

机构地区：[1]洛阳师范学院信息技术学院,河南洛阳471002 [2]新乡学院,河南新乡453003 [3]洛阳矿山机械工程设计研究院有限责任公司,河南洛阳471039

出　　处：《机械设计与制造》2015年第5期268-272,共5页Machinery Design & Manufacture

基　　金：河南省重大科技专项(081100610100);国家十一五科技支撑计划项目(2007BAF26B03);河南省科技攻关项目(142102210475)

摘　　要：石灰回转窑控制系统监测与控制参数多,且具有强的耦合性、时变性,难以针对产品质量建立准确的预测与控制数学模型。为此文章提出以神经网络与关联规则库相结合的方法,构建产品质量在线预测与控制参数调整信息实时反馈的一种控制模型。借助于神经网络处理非线性问题强大功能,通过在线监测参数蕴含的产品质量信息,实时预测产品质量,并与预先设定的优质产品质量信息相比较。以比较结果和当前控制参数信息为输入,结合关联规则库匹配控制参数调整量,并反馈给自动控制系统,实现对产品质量的及时、精确控制。该控制模型运用到实际生产中后,石灰回转窑生产质量和效率有明显的提高。The lime rotary kiln control system has lots of system monitoring and control parameters,which have strong coupling,time-varying,so it is difficult to establish accurate mathematical model to predict and control the quality of the products. Adopting the method that combines the neural network with association rule base,it presents a new method of online predicting of product quality and real-time feedback of control parameter adjustment information. Making use of the powerful function of neural network in dealing with nonlinear problems,this quality control model can predict the quality of products through the product quality information in the on-line monitoring parameters. After comparing with predetermined product quality information,the results obtained and current control parameter information will be input to the associated rule base. This model can achieve the timely and accurate control of product quality by calling the associated rule base to obtain control parameter adjustment amount and feedbacking it to the automatic control system. The results show that the quality and effectiveness of production of lime can be improved after using the control model in actual production.

关 键 词：神经网络 石灰回转窑 智能控制 产品质量 关联规则 

分 类 号：TH16[机械工程—机械制造及自动化] TP273.2[自动化与计算机技术—检测技术与自动化装置]