非平稳过程异常监测方法:综述与展望  

Overview and prospect of abnormal monitoring methods for nonstationary processes

作　　者：王敏 冯智彬 吴德浩 张景欣 周东华 Min WANGI;Zhibin FENGI;Dehao WU;Jingxin ZHANG;Donghua ZHOU(School of Automation Engineering,University of Electronic Science and Technology of China,Chengdu 611731,China;School of Automation,Central South University,Changsha 410083,China;School of Automation,Southeast University,Nanjing 210096,China;School of Electrical and Automation Engineering,Shandong University of Science and Technology,Qingdao 266000,China;Department of Automation,Tsinghua University,Beijing 100018,China)

机构地区：[1]电子科技大学自动化工程学院,成都611731 [2]中南大学自动化学院,长沙410083 [3]东南大学自动化学院,南京210096 [4]山东科技大学电气与自动化工程学院,青岛266000 [5]清华大学自动化系,北京100018

出　　处：《中国科学：信息科学》2024年第8期1807-1826,共20页Scientia Sinica(Informationis)

基　　金：国家自然科学基金项目(批准号:62303090,62033008)资助。

摘　　要：实际工业过程受多种因素(如原材料变化、负载波动、设备老化等)的影响,往往表现出非平稳特性,即过程监测数据统计特性随时间发生变化,因此非平稳过程异常监测备受关注并已成为监测领域的焦点之一.本文从监测方法的角度对非平稳过程异常监测相关研究成果进行了系统性的回顾:首先对非平稳过程的概念和技术难点进行了概述;其次,将非平稳过程监测方法根据原理的差异划分为五大类,并总结了各类方法的优点与不足;最后,结合当前技术发展的现状,对非平稳过程研究中的挑战进行了深入分析与展望。The actual industrial processes are often affected by various factors,such as changes in raw materials,fuctuations in workload,and aging equipment.These processes show non-stationary characteristics,meaning that the statistical properties of the data used to monitor them change over time.This has led to a significant focus on monitoring non-stationary processes in the field of process monitoring.This paper presents a systematic review of research achievements in non-stationary process anomaly monitoring,focusing on the different monitoring methods.It first explains the concept of non-stationary processes and the technical challenges associated with them.Then,it categorizes non-stationary process monitoring methods into five major types based on their principles.The paper then summarizes the advantages and limitations of each type of method.Finally,it conducts an in-depth analysis of the current state of technological development and provides an outlook on the challenges in non-stationary process monitoring.

关 键 词：非平稳过程 过程监测 自适应建模 协整分析 平稳子空间分析 慢特征分析 深度学习 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]