| 引用本文: | 鲍雅萍,马金元,宋 强.基于灰色神经网络的烧结矿碱度组合预测[J].控制理论与应用,2008,25(4):791~793.[点击复制] |
| BAO Ya-ping,MA Jin-yuan,SONG Qiang.Combination forecasting of sintered ore alkalinity based on grey neural network[J].Control Theory and Technology,2008,25(4):791~793.[点击复制] |
|
| 基于灰色神经网络的烧结矿碱度组合预测 |
| Combination forecasting of sintered ore alkalinity based on grey neural network |
| 摘要点击 1397 全文点击 1567 投稿时间：2007-04-27 修订日期：2007-08-25 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 |
| 2008,25(4):791-793 |
| 中文关键词 灰色模型 神经网络 组合预测模型 烧结矿 碱度 |
| 英文关键词 grey model neural network combination forecasting model sintered ore alkalinity |
| 基金项目 |
|
| 中文摘要 |
| 针对钢铁生产过程中烧结矿碱度检测的难题, 利用灰色预测的GM(1; 1)模型与BP神经网络进行组合,建立了灰色神经网络的烧结矿碱度组合预测模型, 选取10个与矿碱度有关的输入变量, 对这些变量分别进行灰色GM(1; 1)预估, 再进行BP神经网络预测, 获得烧结矿碱度预测结果, 仿真结果的相对误差小于0.005%. |
| 英文摘要 |
| To predict the alkalinity of sintered ore accurately in sintered process, a combination grey neural network forecasting model of grey neural network is proposed by combining the grey model GM(1; 1) with BP (Back Propagation) neural network. Ten factors relating with the sintered ore alkalinity are selected as the input variables. These variables are estimated on grey model GM(1; 1) respectively and the alkalinity of sintered ore is forecasted on BP neural network based on all of these estimated data. The results of simulation show that the relative error is less than 0.005%. |
|
|
|
|
|