Skip to main navigation Skip to search Skip to main content

Functional failure diagnosis approach based on Bayesian network for manufacturing systems

  • Zheng He
  • , Yihai He
  • , Zhaoxiang Chen
  • , Yixiao Zhao
  • , Ruohan Lian
  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The failure of traditional manufacturing systems mostly refers to the physical failure of the production equipment that constitutes the manufacturing systems. With the advancement of manufacturing technology and the improvement of the level of intelligence, the physical failure of the conventional equipment in the daily operation of the system is rare, but the quality of the work-in-progress (WIP) is unqualified frequently. Especially the hidden functional failures such as reliability degradation of the final product have become increasingly prominent. How to model and characterize the functional failure of manufacturing systems has become a bottleneck restricting the application and development of holistic PHM (Prognostic and Health Management) technology of manufacturing systems. Therefore, a novel functional failure modeling and diagnostic strategy for intelligent manufacturing systems based on RQR chain is proposed in this paper, which includes the manufacturing system reliability (R) data, manufacturing process quality (Q) data and the produced product reliability (R) data. Firstly, the definition of the functional degradation process and principle of manufacturing systems is clarified from the perspective of RQR chain. Secondly, based on the established RQR chain, the functional fault connotation of manufacturing systems is defined, and the KPCs (key product characteristics) in the Bayesian network of integrated manufacturing systems are utilized. Big data are analyzed to model and predict the functional fault state of the running manufacturing systems. Thirdly, based on the relationship of RQR chain from right to left, the holistic functional fault diagnosis strategy is given. Finally, a case study of a manufacturing system for cylinder head is presented to verify the proposed approach.

Original languageEnglish
Title of host publication2019 Prognostics and System Health Management Conference, PHAI-Qingdao 2019
EditorsWei Guo, Steven Li, Qiang Miao
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728108612
DOIs
StatePublished - Oct 2019
Event10th Prognostics and System Health Management Conference, PHM-Qingdao 2019 - Qingdao, China
Duration: 25 Oct 201927 Oct 2019

Publication series

Name2019 Prognostics and System Health Management Conference, PHM-Qingdao 2019

Conference

Conference10th Prognostics and System Health Management Conference, PHM-Qingdao 2019
Country/TerritoryChina
CityQingdao
Period25/10/1927/10/19

Keywords

  • Bayesian network (BN)
  • Failure diagnosis
  • Functional failure
  • Manufacturing systems
  • RQR chain

Fingerprint

Dive into the research topics of 'Functional failure diagnosis approach based on Bayesian network for manufacturing systems'. Together they form a unique fingerprint.

Cite this