基于优化支持向量机的带钢延伸量软测量研究.pdfVIP

第36卷第8期 东 北 大 学 学 报 ( 自 然 科 学 版 ) Vo l.36,No.8 2015 年 8 月 Journal of Northeastern University (Natural Science) Aug. 20 1 5 doi :10.3969/j .issn.1005 -3026.2015.08.005 基于优化支持向量机的带钢延伸量软测量研究 王 超 ,王建辉 ,顾树生 ,张宇献1 1 1 2 (1.东北大学信息科学与工程学院,辽宁沈阳 110819；2.沈阳工业大学电气工程学院,辽宁沈阳 110870) 摘 要:带钢退火过程中存在多变量非线性主导因素和数据噪声,难以用数学模型精确描述退火炉内带 钢的延伸量.针对这一问题,提出基于核主元分析(KPCA )与免疫粒子群(ICPSO )优化最小二乘支持向量机 (SSVM)的炉内带钢延伸量软测量方法.采用ICPSO 算法避免了粒子群算法易陷入局部最优的缺陷,利用 ICPSO 对 SSVM 进行参数寻优,通过KPCA 去除样本噪声,提取输入数据样本中的非线性主元信息,建立 ICPSO - SSVM 软测量模型.此方法用于退火炉内带钢延伸量预测,通过现场生产数据仿真实验进行非线性 函数估计；对比其他几种现有算法,实验结果表明本文方法具有较高的预测精度. 关 词:核主元分析；带钢延伸量；免疫粒子群算法；最小二乘支持向量机；软测量 中图分类号:TP 391.9 文献标志码:A 文章编号:1005 -3026(2015)08 -1084 -05 A Soft Sensor Based on Optimized LSSVM for Elongation Prediction of Strip Steel WANG Chao ,WANGJian-hui ,GUShu-sheng ,ZHANG Yu-xian1 1 1 2 (1.School of Information Science Engineering ,Northeastern University ,Shenyang 110819,China ；2.School of Electrical Engineering ,Shenyang University of Technology ,Shenyang 110870,China.Corresponding author : WANG Chao ,E-mail :supper king1018@163.com) Abstract:The strip elongation is difficult to predict accurately with mathematical model ,which related with multi-variable nonlinear factors and data noise in the annealing process.Thus ,the optimal soft-sensing method was proposed based on kernel principal component analysis (KPCA) and optimized least squares support vector machine (SSVM)by immune clone particle swarm optimization (ICPSO ).ICPSO can avoid the particles sinking into premature convergence and running into local optimization in the iterative process which was generated by particle swarm optimization (PSO )algorithm ,and can also optimize the parameters of SSVM.Then ,KPCA was used to denoise the input data set a