| 基于LS-SVM的烧结矿碱度预报研究 |
| |
| 引用本文： | 宋强,程国彪,常卫兵,李华. 基于LS-SVM的烧结矿碱度预报研究[J]. 钢铁研究, 2008, 36(6) |
| |
| 作者姓名： | 宋强 程国彪 常卫兵 李华 |
| |
| 作者单位： | 1. 安阳工学院,机械工程系,河南,安阳,455000
2. 安阳钢铁(集团)公司,烧结厂,河南,安阳,455004 |
| |
| 基金项目： | 河南省教育厅自然科学基金 |
| |
| 摘 要： | 开发了最小二乘支持向量机(LS-SVM)模型,并用于对烧结矿碱度进行预测.仿真结果证明,本模型能在小样本贫信息的条件下对烧结矿碱度做出比较准确的预测.此种模型具有预测精度高、所需样本少、计算简便等优点.和BP神经网络算法相比,最小二乘支持向量机算法有很好的应用前景和推广价值.
|
| 关 键 词： | 碱度 最小二乘支持向量机 预测 神经网络 |
Prediction of sinter basicity based on a least square support vector model |
| |
| SONG Qiang,CHENG Guo-biao,CHANG Wei-bing,LI Hua. Prediction of sinter basicity based on a least square support vector model[J]. Research on Iron and Steel, 2008, 36(6) |
| |
| Authors: | SONG Qiang CHENG Guo-biao CHANG Wei-bing LI Hua |
| |
| Affiliation: | SONG Qiang1,CHENG Guo-biao2,CHANG Wei-bing2,LI Hua2 |
| |
| Abstract: | A least square support vector machine(LS-SVM)model is developed and applied in the prediction of sinter basicity.The results of model calculation show that the sinter basicity can be accurately predicted in a condition of small amount of samples.It is concluded that the LS-SVM model has advantages of high precision,less samples required and simple calculation.Compared with BP neural network algorithm,the LS-SVM model has good prospects in practical application. |
| |
| Keywords: | basicity least square support vector machine prediction neural network |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
