A New Method of Fault Detection and Diagnosis for the Tennessee Eastman Process | |
Zhang PB(张鹏彬)1,2,3,4; Zou T(邹涛)5; Wang JY(王景杨)1,2,3; Yang ZJ(杨志家)1,2,3 | |
2021 | |
会议日期 | 2021年7月30日-8月1日 |
会议地点 | 山西太原 |
页码 | 474 |
英文摘要 | This paper proposes a new fault detection and diagnosis(FDD) method for the Tennessee Eastman(TE) large-scale chemical process.This method is built integrated with a curve-type recognizer and a dynamic Bayesian network(DBN).The fault detection is carried out utilizing the curve-type recognizer,while the diagnosis is completed using the DBN.Furthermore,the recognizer extracts fault symptoms from different times by distinguishes the curves' type.Hence,the DBN is constructed to handle these time-related fault symptoms capably.The DBN will give the probability of each fault more and more accurately as time goes by.The whole procedure consists of 1) deciding monitoring variables using chemical and control engineering knowledge 2) extracting fault symptoms,3) building a DBN.The advantage over other data-driven FDD methods in reasonability and interpretability is also discussed.At last,the simulation results demonstrate the availability of the proposed method. |
源文献作者 | 中国自动化学会过程控制专业委员会、中国自动化学会 |
产权排序 | 1 |
会议录 | 第32届中国过程控制会议(CPCC2021)论文集
![]() |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.sia.cn/handle/173321/30281] ![]() |
专题 | 沈阳自动化研究所_工业控制网络与系统研究室 |
通讯作者 | Zou T(邹涛) |
作者单位 | 1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China 2.Key Laboratory of Networked Control System, Chinese Academy of Sciences, Shenyang, China 3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China 4.University of Chinese Academy of Sciences, Beijing, China. Shenyang, China 5.College of Mechanical and Electrical Engineering, Guangzhou University Guangzhou, China |
推荐引用方式 GB/T 7714 | Zhang PB,Zou T,Wang JY,et al. A New Method of Fault Detection and Diagnosis for the Tennessee Eastman Process[C]. 见:. 山西太原. 2021年7月30日-8月1日. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论