), 牟淼a a.电气工程与信息工程学院, 兰州理工大学, 兰州 730050
b.甘肃省工业过程先进控制重点实验室, 兰州理工大学, 兰州 730050
c.电气与控制工程国家级实验教学示范中心, 兰州理工大学, 兰州 730050
收稿日期:2020-09-14出版日期:2021-11-28发布日期:2021-12-03作者简介:赵小强(1969-),男,陕西省宝鸡市人,教授,博士生导师,研究方向为过程监控和故障诊断、生产调度及数据挖掘.E-mail: 基金资助:国家自然科学基金(61763029);国防基础科研(JCKY2018427C002);甘肃省高等学校产业支撑引导(2019C-05);甘肃省工业过程先进控制重点实验室开放基金资助项目(2019KFJJ01)Batch Process Monitoring with Dynamic-Static Joint Indicator Based on GSFA-GNPE
ZHAO Xiaoqianga,b,c(), MOU Miaoa a. College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China
b. Key Laboratory of Advanced Control for Industrial Processes of Gansu Province, Lanzhou University of Technology, Lanzhou 730050, China
c. National Demonstration Center for Experimental Electrical and Control Engineering Education, Lanzhou University of Technology, Lanzhou 730050, China
Received:2020-09-14Online:2021-11-28Published:2021-12-03摘要/Abstract
摘要： 传统的过程监控方法忽略了变量间的时序相关性,且没有区分变量间的动态关系与静态关系,从而导致监控效果不佳.针对此问题,本文提出一种基于全局慢特征分析(GSFA)-全局邻域保持嵌入(GNPE)的动态-静态联合指标间歇过程监控方法,该方法可以有效提取动态全局特征和静态全局特征.首先,对过程变量的动态特性和静态特性进行评估,把自相关和互相关性较弱的变量视为静态变量,剩余变量视为动态变量;其次,分别对动态子空间和静态子空间构建GSFA和GNPE模型;然后,对来自每个子空间的统计信息使用贝叶斯推理进行组合,以得出混合模型的联合指标实现过程监控;最后,将所提算法应用于数值算例和青霉素发酵仿真过程进行仿真验证.结果表明,GSFA-GNPE算法相较于其他算法的故障检测效果更好.
关键词: 间歇过程, 过程监控, 慢特征分析, 邻域保持嵌入, 全局-局部, 贝叶斯推断
Abstract: Traditional process monitoring methods ignore the time-series correlation between variables, and do not distinguish the dynamic relationship and static relationship between variables, resulting in poor monitoring effect. To solve these problems, a dynamic-static joint indicator monitoring method of batch process based on global slow feature analysis(GSFA)-global neighborhood preserving embedding (GNPE) is proposed in this paper, which can effectively extract dynamic global features and static global features. First, the dynamic and static characteristics of the process variables are evaluated. Variables with weak autocorrelation and cross-correlation are regarded as static variables, and the remaining variables are regarded as dynamic ones. Next, the GSFA and GNPE models are constructed for dynamic and static subspaces, respectively. Finally, the statistical information from each subspace is combined by using Bayesian inference to obtain the joint indicator of the mixed model to realize process monitoring. Finally, the proposed algorithm is applied to a numerical example and the penicillin fermentation simulation process for simulation verification. The results show that the proposed GSFA-GNPE algorithm has better fault detection effects than other algorithms.
Key words: batch process, process monitoring, slow feature analysis, neighborhood preserving embedding, globality-locality, Bayesian inference
PDF全文下载地址:
点我下载PDF
