| 基于神经网络的水泥生料配料多目标优化设计方法 |
| |
| 引用本文： | 庞强,苑明哲,吴星刚,王景杨.基于神经网络的水泥生料配料多目标优化设计方法[J].东南大学学报(自然科学版),2009(Z1). |
| |
| 作者姓名： | 庞强 苑明哲 吴星刚 王景杨 |
| |
| 作者单位： | 中国科学院沈阳自动化研究所工业信息学重点实验室;中国科学院研究生院; |
| |
| 基金项目： | 国家高技术研究发展计划(863计划)资助项目(2006AA04Z185) |
| |
| 摘 要： | 为了降低生料成分的不确定性给水泥生料质量控制系统带来的影响,提出了率值补偿的控制策略.分别为三率值创建目标函数,并利用状态空间搜索策略解决多目标优化问题.针对初始样本空间不能覆盖所有样本的问题,提出了基于神经网络的估算模型,对初始样本空间进行拓扑.通过估价函数对状态空间中的状态量进行评价,得到最优的率值状态量;根据率值对原料配比进行调整,最后使率值偏差得到补偿,同时使给配比造成的波动最小.工业实验结果表明,生料的质量合格率由原来的30%提高到50%,该系统能有效地对配料过程进行优化控制.证明了基于神经网络的状态空间搜索策略为水泥生料配料多目标寻优问题提供了一种可行的方法.
|
| 关 键 词： | 生料配料 多目标优化 神经网络 状态空间搜索 |
Multi-objective optimization design method of control system in cement raw materials blending process based on neural network |
| |
| Pang Qiang Yuan Mingzhe Wu Xinggang Wang Jingyang.Multi-objective optimization design method of control system in cement raw materials blending process based on neural network[J].Journal of Southeast University(Natural Science Edition),2009(Z1). |
| |
| Authors: | Pang Qiang Yuan Mingzhe Wu Xinggang Wang Jingyang |
| |
| Institution: | Pang Qiang1 Yuan Mingzhe1 Wu Xinggang2 Wang Jingyang1(1Key Laboratory of Industrial Informatics,Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,China)(2Graduate University of the Chinese Academy of Sciences,Beijing 100039,China) |
| |
| Abstract: | In order to reduce the influence of the uncertainty of raw material components on the control system of cement raw material quality,a control strategy is proposed based on modulus value compensation.Goal functions are created for three modulus values separately,and multi-objective optimization problem is solved with the strategy of state-space search.Aiming at the problem that the initial sample space cannot cover all of the samples,the estimation model based on neural network is brought forward for initial... |
| |
| Keywords: | raw material blending multi-objective optimization neural network state-space search |
| 本文献已被 CNKI 等数据库收录！ |
