节点文献
面向综合生产目标的铅锌烧结过程智能建模与优化方法
Intelligent Modeling and Optimization Method Based on Comprehensive Product Indices for Lead-Zinc Sintering Process
【Author】 Cui Kai,Cao Weihua,Wu Min,Wang Chunsheng School of Information Science and Engineering,Central South University,Changsha 410083,P.R.China
【机构】 中南大学信息科学与工程学院;
【摘要】 针对机理复杂、参数众多、关联耦合严重的铅锌烧结过程,提出一种面向综合生产目标的智能建模与优化方法。首先采用灰色关联度分析、主元分析、神经网络等多种智能方法,建立综合生产目标神经网络预测模型;然后利用多目标优化技术,建立综合生产目标优化模型,获得优化控制目标函数;最后提出基于SPEA2的改进多目标粒子群优化算法,求取最优操作参数以指导烧结生产。实验运行结果表明,本文提出的智能建模与优化方法可以获得较好的工业应用效果,为全流程工业优化提供了一种新的实现途径。
【Abstract】 The lead-zinc sintering process has the characters of complex mechanism,multi-parameter and strong interconnected coupling.This paper presents an intelligent modeling and optimization method based on comprehensive production Indices.First,the neural network prediction model of the comprehensive production indices is proposed,which is synthesizing some techniques,including gray correlation analysis,principal components analysis,and neural network and so on.And the target function is deduced and the model based on comprehensive production Indices is given by using the multi-objective optimization technique.At last,this paper proposes an improved multi-objective particle swarm optimization algorithm based on SPEA2 to calculate the optimization executing parameters.The applied results of actual runs show that the intelligent modeling and optimization method proposed in this paper attains a better industrial effect,and provides an effective and new way to implement the global optimization.
【Key words】 Lead-Zinc sintering process; Neural network; Multi-objective optimization; Improved particle swarm optimization algorithm;
- 【会议录名称】 第二十七届中国控制会议论文集
- 【会议名称】第二十七届中国控制会议
- 【会议时间】2008-07-16
- 【会议地点】中国云南昆明
- 【分类号】TF801;TP18
- 【主办单位】中国自动化学会控制理论专业委员会(Technical Committee on Control Theory,Chinese Association of Automation)