基于动态核岭回归的MTO反应器压降软测量  

Pressure drop soft measurement of MTO reactor based on dynamic kernel ridge regression

作　　者：赵泽盟 饶景之 史元腾 李超 锁良晨 Zhao Zemeng;Rao Jingzhi;Shi Yuanteng;Li Chao;Suo Liangchen(China Coal Energy Research Institute Co.,Ltd.,Xi′an Shaanxi 710054,China;China Coal Xi′an Design Engineering Co.,Ltd.,Xi′an Shaanxi 710054,China;Wuxi Research Institute of Applied Technologies,Tsinghua University,Wuxi Jiangsu 214072,China)

机构地区：[1]中煤能源研究院有限责任公司,陕西西安710054 [2]中煤西安设计工程有限责任公司,陕西西安710054 [3]清华大学无锡应用技术研究院,江苏无锡214072

出　　处：《煤化工》2024年第5期36-40,共5页Coal Chemical Industry

基　　金：中国中煤能源集团重点科技项目(20211CY005)。

摘　　要：针对甲醇制烯烃反应器生产过程中,测量其压降的仪表可能会出现异常,导致操作人员无法获取准确的测量数据的问题,考虑到实际生产过程的复杂性,过程数据往往具有动态和非线性特征,提出了一种基于动态核岭回归的软测量方法,并在某煤化工生产企业建模。结果表明:该方法能够有效提高模型的精度,相较于传统的线性回归方法,该方法对甲醇制烯烃反应器压降的预测效果更好。In the methanol to olefin production process,measuring instrument of the reactor pressure drop may become abnormal,so that the operators were unable to obtain accurate measurement data of the pressure drop.Considering the complexity of actual production process,process data often had dynamic and nonlinear characteristics.A soft sensor technique based on the dynamic kernel ridge regression method was proposed.And a model was established in a coal chemical production enterprise.The results showed that this method could effectively improve the accuracy of the model,compared with the traditional linear regression model,the method had a better predictive effect on the pressure drop in the methanol to olefin reactor.

关 键 词：DMTO反应器 压降 动态核岭回归算法 最大信息系数 精度 

分 类 号：TQ221.212[化学工程—有机化工] TP18[自动化与计算机技术—控制理论与控制工程]