首页 | 本学科首页   官方微博 | 高级检索  
     

工业过程故障根源诊断与传播路径识别技术综述EI北大核心CSCD
引用本文:马亮,彭开香,董洁. 工业过程故障根源诊断与传播路径识别技术综述EI北大核心CSCD[J]. 自动化学报, 2022, 48(7): 1650-1663. DOI: 10.16383/j.aas.c200257
作者姓名:马亮  彭开香  董洁
作者单位:1.北京科技大学顺德研究生院 佛山 528399
基金项目:国家自然科学基金(62003030,61873024,61773053);;中国博士后科学基金资助项目(2019M660464);;广东省基础与应用基础研究基金(2019A1515110991);;中央高校基本科研业务费专项资金资助项目(FRF-TP-19-049A1Z);
摘    要:故障根源诊断与传播路径识别是故障诊断框架下的关键核心问题,是保障工业过程安全生产及获得可靠产品质量的有效手段,是当前过程控制领域的研究热点.该技术的研究不仅丰富了故障诊断理论,而且对故障诊断技术在工程中的推广与应用具有重要意义.阐述了基于知识、数据及知识与数据联合驱动的故障根源诊断与传播路径识别方法的基本思想、适用条件和优劣特点,分类概述了相关方法的研究现状.探讨了该领域亟待解决的问题及未来的发展方向,包括:1)“三个维度”视角下的工业过程故障根源诊断与传播路径识别;2)基于制造大数据分析与因果关系挖掘的工业过程质量精准追溯;3)面向传播、耦合、多重并发特性的工业过程复合故障分布式诊断;4)基于多源异构动态信息融合的工业过程异常工况时空追溯可视化.

关 键 词:根源诊断  传播路径识别  因果关系分析  故障诊断  工业过程
收稿时间:2020-04-27

Review of Root Cause Diagnosis and Propagation Path Identification Techniques for Faults in Industrial Processes
Affiliation:1.Shunde Graduate School of University of Science and Technology Beijing, Foshan 5283992.School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 1000833.Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education, Beijing 100083
Abstract:Root cause diagnosis and propagation path identification are the key issues under fault diagnosis framework, which are effective means to guarantee safety production and obtain reliable product quality for industrial processes, and thus, have recently become active areas of process control field. Research of these two techniques not only enriches the fault diagnosis theory, but also has important significance for promotion and application of fault diagnosis technology in actual projects. In this paper, the basic ideas, application conditions, advantages, as well as disadvantages of knowledge based, data based and joint knowledge and data based methods are illustrated. Moreover, research status of related methods is classified and summarized. Finally, some urgent problems and future directions in this field are discussed, including: 1) Root cause diagnosis and propagation path identification under three-dimensional perspective; 2) Manufacturing big data analysis and causality mining based accurate quality tracing; 3) Distributed diagnosis for propagative, coupled, and concurrent multiple faults; 4) Multi-source heterogeneous dynamic information fusion based timespace traceability visualization for abnormal conditions.
Keywords:
本文献已被 维普 等数据库收录!
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号