基于支持向量机的无参时变过程控制方法研究  

Research on adaptive support vector machine for time-varying process control

作　　者：何桢[1] 张静静 何曙光[1] He Zhen;Zhang Jingjing;He Shuguang(College of Management and Economics,Tianjin University,Tianjin 300072,China)

机构地区：[1]天津大学管理与经济学部,天津300072

出　　处：《系统工程学报》2023年第3期419-432,共14页Journal of Systems Engineering

基　　金：国家自然科学基金重点资助项目(72032005;72231005);国家自然科学基金国际(地区)合作与交流资助项目(722-61147706);国家自然科学基金面上资助项目(71872123)。

摘　　要：为了提高时变生产过程的监控性能,提出了基于支持向量机的时变控制图,能够根据生产过程的变化及时更新分类器模型和控制界限,并根据第二阶段的数据构建动态分类边界,以实现对时变生产过程进行有效监控.同时通过添加时间权重因子和停止更新准则,实现对模型更新速度和更新区域的调节,使所提的时变控制图能够适应不同的时变模式.最后,通过模拟数据和青霉素发酵数据进行验证,验证所提的时变控制图性能优于传统控制图.A time-varying control chart based on support vector machine is proposed to monitor the time-varying process to improve the monitoring performance of the time-varying production process.This chart can update the classifier model and control boundary according to the change of the process,and build a dynamic classification boundary according to the data of the second stage,so that an effective monitoring of the time-varying process is realized.At the same time,time parameters and update parameters are proposed to adjust the update speed and update area of the model,so that the chart can adapt to different time-varying modes.At last,both the simulation data and penicillin fermentation data prove that the proposed time-varying control chart is better than traditional control charts.

关 键 词：时变过程 过程控制 支持向量机 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]