【作者】 陆荣秀； 杨辉； 衷路生；

【Author】 Lu Rongxiu,Yang Hui,Zhong Lusheng School of Electrical and Electronics Engineering,East China Jiaotong University,Jiangxi,Nanchang 330013

【机构】 华东交通大学电气与电子工程学院；

【摘要】 本文针对稀土萃取过程组分含量在线检测的难题,利用混合核函数兼具局部核函数和全局核函数的特点,并可通过权重因子调节各核函数对混合核函数的作用,提出稀土萃取过程组分含量的混合核函数支持向量机建模方法.应用结果表明所提出的软测量方法具有较好的模型拟合精度和满意的预测效果,能满足稀土萃取过程组分含量在线预估的要求.更多还原

【Abstract】 In this paper,in virtue of the problem of rare-earth counter-current extraction separation process,in which the real-time online measuring for component content is very difficult,a modeling method of Support Vector Machine (SVM) based on mixtures kernels for rare-earth counter-current extraction separation process is proposed.The model makes use of the character of mixture kernel by more global and local ability and the influence of difference kernels which can be turned by weight factor in the determination of the kernels.According to the results of application,it indicates that the method based on mixtures kernels has both better fitting output and satisfied prediction output,and meets the modeling and control for rare-earth extract process.更多还原