A Fuzzy Framework for System Diagnosis

2018 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA) Pub Date : 2018-06-01 DOI:10.1109/CIVEMSA.2018.8439983

T. P. Fries

{"title":"A Fuzzy Framework for System Diagnosis","authors":"T. P. Fries","doi":"10.1109/CIVEMSA.2018.8439983","DOIUrl":null,"url":null,"abstract":"Diagnosis of system problems relies on a variety of diverse data. The data can be composed of sensor data supplemented by a knowledge base of past problems. Difficulties arise when the data obtained from sensors is uncertain, imprecise, or appears to be contradictory. Further, the sensory data may conflict with potential diagnoses based upon past experiences. This research presents framework for system diagnosis using fuzzy linguistic variables represent sensory data and possible diagnoses based upon experience. A novel data fusion method for the fuzzy opinions is introduced. Additionally, the research develops an innovative procedure for ranking the fuzzy opinions to arrive at diagnosis. The technique first represents data in the form of fuzzy linguistic variables to accommodate diverse and conflicting data and opinions. The fuzzy representation accommodates the uncertainty and imprecision inherent in many sensors. Testing demonstrates that the framework provides accurate diagnosis of system faults.","PeriodicalId":305399,"journal":{"name":"2018 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CIVEMSA.2018.8439983","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Diagnosis of system problems relies on a variety of diverse data. The data can be composed of sensor data supplemented by a knowledge base of past problems. Difficulties arise when the data obtained from sensors is uncertain, imprecise, or appears to be contradictory. Further, the sensory data may conflict with potential diagnoses based upon past experiences. This research presents framework for system diagnosis using fuzzy linguistic variables represent sensory data and possible diagnoses based upon experience. A novel data fusion method for the fuzzy opinions is introduced. Additionally, the research develops an innovative procedure for ranking the fuzzy opinions to arrive at diagnosis. The technique first represents data in the form of fuzzy linguistic variables to accommodate diverse and conflicting data and opinions. The fuzzy representation accommodates the uncertainty and imprecision inherent in many sensors. Testing demonstrates that the framework provides accurate diagnosis of system faults.

查看原文本刊更多论文

系统诊断的模糊框架

系统问题的诊断依赖于各种不同的数据。数据可以由传感器数据和过去问题的知识库组成。当从传感器获得的数据不确定、不精确或看起来相互矛盾时，就会出现困难。此外，感官数据可能与基于过去经验的潜在诊断相冲突。本研究提出了一个系统诊断框架，使用模糊语言变量表示感官数据和基于经验的可能诊断。提出了一种新的模糊意见数据融合方法。此外，研究开发了一种创新的程序，对模糊意见进行排序，以达到诊断。该技术首先以模糊语言变量的形式表示数据，以适应不同和冲突的数据和意见。模糊表示适应了许多传感器固有的不确定性和不精确性。测试结果表明，该框架能够准确地诊断系统故障。

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

2018 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA)

自引率

0.00%

发文量