Data-driven Methodology for State Detection of Gearbox in PHM Context

Qiuan Chen, Yi Liu, Shengwen Hou, Feng Duan, Zhiqiang Cai

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

Abstract

With the development of artificial intelligence technology, data-driven PHM technology has been widely used for life cycle health management of equipment. Equipment will generate a lot of data in the process of operation and production. Analyzing the data and establishing machine learning model can accurately evaluate the operation status of equipment. Increasingly, extracting knowledge from data has become an important task in organizations for performance improvements. Data is the resource for equipment health assessment, so it is of great significance to focus on the research of data quality. Based on this, the main work of this paper is as follows. (1) The data quality issues are discussed in the context of PHM. (2) The PHM framework is proposed for improving the reliability of equipment. (3) Several machine learning algorithms are introduced for state detection. (4) The proposed technology is applied to real cases, and the results are analyzed and visualized in detail.

Original languageEnglish
Title of host publication2021 Global Reliability and Prognostics and Health Management, PHM-Nanjing 2021
EditorsWei Guo, Steven Li
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665401302
DOIs
StatePublished - 2021
Event12th IEEE Global Reliability and Prognostics and Health Management, PHM-Nanjing 2021 - Nanjing, China
Duration: 15 Oct 202117 Oct 2021

Publication series

Name2021 Global Reliability and Prognostics and Health Management, PHM-Nanjing 2021

Conference

Conference12th IEEE Global Reliability and Prognostics and Health Management, PHM-Nanjing 2021
Country/TerritoryChina
CityNanjing
Period15/10/2117/10/21

Keywords

  • Data quality
  • Gearbox
  • PHM
  • State detection

Fingerprint

Dive into the research topics of 'Data-driven Methodology for State Detection of Gearbox in PHM Context'. Together they form a unique fingerprint.

Cite this