Prediction of Silicon Content in Hot Metal Based on SVR Optimized by Chaos Particle Swarm Optimization

Tang Xian-Lun; 庄陵; 李学勤

您当前的位置：

首页 >

文章列表页 >

Prediction of Silicon Content in Hot Metal Based on SVR Optimized by Chaos Particle Swarm Optimization

更新时间：2023-11-28

- Prediction of Silicon Content in Hot Metal Based on SVR Optimized by Chaos Particle Swarm Optimization
- Advanced Engineering Sciences Vol. 41, Issue 4, Pages: 141-145(2009)
- 作者机构：
  
  1. 重庆邮电大学
  2. 重庆邮电大学网络化控制与智能仪器仪表教育部重点实验室重庆,400065
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2009，
  
  Published Online：28 October 2008，
扫描看全文
唐贤伦,庄陵,李学勤.基于混沌粒子群支持向量回归的高炉铁水硅含量预测[J].工程科学与技术,2009,41(4):141-145.

Tang Xian-Lun, 庄陵, 李学勤. Prediction of Silicon Content in Hot Metal Based on SVR Optimized by Chaos Particle Swarm Optimization. [J]. Advanced Engineering Sciences 41(4):141-145(2009)
唐贤伦,庄陵,李学勤.基于混沌粒子群支持向量回归的高炉铁水硅含量预测[J].工程科学与技术,2009,41(4):141-145. DOI：

Tang Xian-Lun, 庄陵, 李学勤. Prediction of Silicon Content in Hot Metal Based on SVR Optimized by Chaos Particle Swarm Optimization. [J]. Advanced Engineering Sciences 41(4):141-145(2009) DOI：

摘要

中文摘要: 参数的优化选择对支持向量回归算法(SVR)的预测精度和泛化能力影响显著，提出混沌粒子群优化算法(CPSO)寻优一种改进支持向量回归算法(v-SVR)参数的新方法，在此基础上建立高炉铁水硅含量预测模型(CPSO -vSVR)用于对某钢铁厂3号高炉铁水硅含量的实际数据进行预测，研究结果表明：基于CPSO确定的最优参数建立的铁水硅含量粒子群支持向量回归预测模型的预测效果最佳，平均相对误差为5.32%。与使用粒子群优化算法训练的神经网络(PSO-NN)、v-SVR、最小二乘支持向量回归(LS-SVR)进行比较，CPSO -vSVR模型对铁水硅含量进行预测时预测绝对误差小于0.03的样本数占总测试样本数的百分比达到90%以上，预测效果明显优于PSO-NN，且比v-SVR稳定性更强，可用于高炉铁水硅含量的实际预测。

Abstract

Abstract:The regression accuracy of the support vector regression (SVR) models depends on a proper setting of its parameters to a great extent. An optimal selection approach of v-SVR parameters was put forward based on chaos particle swarm optimization (CPSO) algorithm. Then a model based on v-SVR to predict the silicon content in hot metal was established

and the optimal parameters of the model was searched by CPSO. The data of the model were collected from No.3 BF in Panzhihua Iron and Steel Group Co.. The results showed that the proposed prediction model has better prediction results than neural network trained by particle swarm optimization and v-SVR

the percentage of samples whose absolute prediction error is less than 0.03 when predicting silicon content by v-SVR model is higher than 90%

it indicated that the prediction precision can meet the requirement of practical production.

关键词

支持向量回归粒子群优化算法混沌铁水硅含量预测

Keywords

support vector regressionparticle swarm optimizationchaossilicon content in hot metalprediction

references

更多指标>

Views

400

下载量

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Chaos Characteristics Analysis of Friction Vibration Signal in Running-in Process of Dry Gas Seal

Related Author

No data

Related Institution

School of Petrochemical Technol., Lanzhou Univ. of Technol.

四川大学水利水电学院四川

四川大学计算机学院四川成都６１００６5

四川大学制造科学与工程学院四川

西南交通大学应用力学与工程系四川

⁰