工业过程异常检测、寿命预测与维修决策的研究进展  

A Survey on Anomaly Detection, Life Prediction and Maintenance Decision for Industrial Processes

作　　者：周东华[1,2] 魏慕恒[1,2] 司小胜[1,2,3] 

机构地区：[1]清华大学自动化系,北京100084 [2]清华信息科学与技术国家实验室,北京100084 [3]第二炮兵工程大学302教研室,西安710025

出　　处：《自动化学报》2013年第6期711-722,共12页Acta Automatica Sinica

基　　金：国家重点基础研究发展计划(973计划)(2010CB731800;2009CB320602);国家自然科学基金(61210012;61021063;61290324;61174030)资助~~

摘　　要：作为保障工业过程安全性、可靠性和经济性的重要技术,异常检测、寿命预测与维修决策在过去几十年得到了越来越广泛的关注和长足的发展.本文结合异常检测、寿命预测与维修决策各研究环节之间的相互联系,综述了异常检测、寿命预测与维修决策的联合研究现状,重点总结了异常检测与寿命预测、异常检测与维修决策、寿命预测与维修决策、维修决策与备件管理的联合研究动态.最后,探讨了该领域中存在的问题及未来的研究方向.The past decades have witnessed an increasingly growing research interest and significant progress on various aspects of anomaly detection, life prediction, and maintenance decision. In this paper, according to the linkages among anomaly detection, life prediction, and maintenance decision, the state of the art of the integrated studies of anomaly de- tection, life prediction, and maintenance decision are reviewed and the potential issues needed to be solved are highlighted. Particularly, the emphasis is placed on the development of integrated anomaly detection and life prediction, integrated anomaly detection and maintenance decision, integrated life prediction and maintenance decision, and integrated main- tenance decision and spare parts ordering. Finally, the unsolved problems and future research directions in the reviewed field are discussed.

关 键 词：异常检测 寿命预测 维修决策 联合研究 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]