Fault diagnosis and failure prognosis for engineering systems: A global perspective

C. Ly, K. Tom, C. Byington, R. Patrick, G. Vachtsevanos
{"title":"Fault diagnosis and failure prognosis for engineering systems: A global perspective","authors":"C. Ly, K. Tom, C. Byington, R. Patrick, G. Vachtsevanos","doi":"10.1109/COASE.2009.5234094","DOIUrl":null,"url":null,"abstract":"Engineering systems, such as aircraft, industrial processes, manufacturing systems, transportation systems, electrical and electronic systems, etc., are becoming more complex and are subjected to failure modes that impact adversely their reliability, availability, safety and maintainability. Such critical assets are required to be available when needed, and maintained on the basis of their current condition rather than on the basis of scheduled or breakdown maintenance practices. Moreover, on-line, real-time fault diagnosis and prognosis can assist the operator to avoid catastrophic events. Recent advances in Condition-Based Maintenance and Prognostics and Health Management (CBM/PHM) have prompted the development of new and innovative algorithms for fault, or incipient failure, diagnosis and failure prognosis aimed at improving the performance of critical systems. This paper introduces an integrated systemsbased framework (architecture) for diagnosis and prognosis that is generic and applicable to a variety of engineering systems. The enabling technologies are based on suitable health monitoring hardware and software, data processing methods that focus on extracting features or condition indicators from raw data via data mining and sensor fusion tools, accurate diagnostic and prognostic algorithms that borrow from Bayesian estimation theory, and specifically particle filtering, fatigue or degradation modeling, and real-time measurements to declare a fault with prescribed confidence and given false alarm rate while predicting accurately and precisely the remaining useful life of the failing component/system. Potential benefits to industry include reduced maintenance costs, improved equipment uptime and safety. The approach is illustrated with examples from the aircraft and industrial domains.","PeriodicalId":386046,"journal":{"name":"2009 IEEE International Conference on Automation Science and Engineering","volume":"21 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"47","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 IEEE International Conference on Automation Science and Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/COASE.2009.5234094","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 47

Abstract

Engineering systems, such as aircraft, industrial processes, manufacturing systems, transportation systems, electrical and electronic systems, etc., are becoming more complex and are subjected to failure modes that impact adversely their reliability, availability, safety and maintainability. Such critical assets are required to be available when needed, and maintained on the basis of their current condition rather than on the basis of scheduled or breakdown maintenance practices. Moreover, on-line, real-time fault diagnosis and prognosis can assist the operator to avoid catastrophic events. Recent advances in Condition-Based Maintenance and Prognostics and Health Management (CBM/PHM) have prompted the development of new and innovative algorithms for fault, or incipient failure, diagnosis and failure prognosis aimed at improving the performance of critical systems. This paper introduces an integrated systemsbased framework (architecture) for diagnosis and prognosis that is generic and applicable to a variety of engineering systems. The enabling technologies are based on suitable health monitoring hardware and software, data processing methods that focus on extracting features or condition indicators from raw data via data mining and sensor fusion tools, accurate diagnostic and prognostic algorithms that borrow from Bayesian estimation theory, and specifically particle filtering, fatigue or degradation modeling, and real-time measurements to declare a fault with prescribed confidence and given false alarm rate while predicting accurately and precisely the remaining useful life of the failing component/system. Potential benefits to industry include reduced maintenance costs, improved equipment uptime and safety. The approach is illustrated with examples from the aircraft and industrial domains.
工程系统的故障诊断和故障预测:一个全局视角
工程系统,如飞机、工业过程、制造系统、运输系统、电气和电子系统等,正变得越来越复杂,并且受到对其可靠性、可用性、安全性和可维护性产生不利影响的故障模式的影响。这些关键资产需要在需要时可用,并根据其当前状况进行维护,而不是根据计划或故障维护实践。此外,在线、实时的故障诊断和预测可以帮助操作员避免灾难性事件的发生。基于状态的维护和预测以及健康管理(CBM/PHM)的最新进展促进了新的和创新的故障算法的发展,或早期故障,诊断和故障预测旨在提高关键系统的性能。本文介绍了一种通用的、适用于各种工程系统的诊断与预后集成系统框架(体系结构)。使能技术基于合适的健康监测硬件和软件、侧重于通过数据挖掘和传感器融合工具从原始数据中提取特征或状态指标的数据处理方法、借鉴贝叶斯估计理论的准确诊断和预测算法,特别是粒子滤波、疲劳或退化建模。实时测量以规定的置信度和给定的虚警率宣布故障,同时准确和精确地预测故障部件/系统的剩余使用寿命。对工业的潜在好处包括降低维护成本,提高设备正常运行时间和安全性。用飞机和工业领域的实例说明了这种方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信