应用加权LSSVM算法的PVC气提塔温度建模  

Temperature Modeling of PVC Stripping Process Using Weighted Least Square Support Vector Machine

作　　者：常学川 杨少沛 杨东芳 CHANG Xue-chuan;YANG Shao-pei;YANG Dong-fang(Songshan Shaolin Wushu College,Dengfeng 452470,China;Huanghe Jiaotong University,Jiaozuo 454000,China;Zhengzhou Shengda University of Economics,Business&Management,Zhengzhou 450000,China)

机构地区：[1]嵩山少林武术职业学院,河南登封452470 [2]黄河交通学院,河南焦作454000 [3]郑州升达经贸管理学院,河南郑州450000

出　　处：《塑料科技》2020年第4期74-77,共4页Plastics Science and Technology

基　　金：焦作市2019年科技计划项目(焦科20194830)。

摘　　要：研究基于最小二乘支持向量机(LSSVM)建立了PVC汽提塔的预测模型。为了提高LSSVM的鲁棒性,过滤离群点,将加权最小二乘支持向量机(WLSSVM)应用到PVC汽提过程的温度建模中,对汽提塔温度进行建模和仿真实验。对比仿真实验结果表明:WLSSVM建模具有更高的建模精度和更优秀的性能。The temperature control of the stripping process is particularly important.Considering that the temperature control has obvious non-linear characteristics,and support vector machine(SVM)has significant advantages in the nonlinear system control,this study establishes the prediction model of PVC stripper based on least square support vector machine(LSSVM).In addition,in order to improve the robustness of LSSVM and filter outliers,a weighted least squares support vector machine(WLSSVM)is applied to model the temperature of PVC stripping process.The above two methods are used to model and simulate the temperature of stripper.The results of simulation show that WLSSVM model has higher modeling accuracy and better performance.

关 键 词：汽提塔 加权最小二乘支持向量机 聚氯乙烯 

分 类 号：TU532.6[建筑科学—建筑技术科学]