Unbalanced Data Classification Model in PHM Field Based on Oversampling Algorithm

Xuefei Qin, Feng Duan, Shengwen Hou, Zhiqiang Cai

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

2 Scopus citations

Abstract

Fault detection based on data-driven artificial intelligence has always been a research hotspot. Due to the long- term operation of rotating machinery in a healthy state, the lack of historical data on faults leads to data unbalance problems, which hinder data-driven fault diagnosis and have become one of the stubborn problems in the field of PHM. From the perspective of data preprocessing, this paper explores the effects of SMOTE and LR-SMOTE oversampling algorithms on unbalanced data of rotating machinery. This paper uses the public data of gears and bearings to artificially establish various types of unbalanced data and combines the SMOTE and LR-SMOTE oversampling algorithms with SVM, RF, and GBDT three classifiers into multiple models for experiments. The experimental results show that the algorithm combining LR-SMOTE and SVM can achieve better classification results and has better stability. And compared with the SMOTE algorithm, LR-SMOTE can effectively avoid the overfitting problem of the GBDT classifier.

Original languageEnglish
Title of host publication2022 Global Reliability and Prognostics and Health Management Conference, PHM-Yantai 2022
EditorsWei Guo, Steven Li
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665496315
DOIs
StatePublished - 2022
Event2022 Global Reliability and Prognostics and Health Management Conference, PHM-Yantai 2022 - Yantai, China
Duration: 13 Oct 202216 Oct 2022

Publication series

Name2022 Global Reliability and Prognostics and Health Management Conference, PHM-Yantai 2022

Conference

Conference2022 Global Reliability and Prognostics and Health Management Conference, PHM-Yantai 2022
Country/TerritoryChina
CityYantai
Period13/10/2216/10/22

Keywords

  • data-driven
  • LR- SMOTE
  • oversampling
  • rotating machinery
  • unbalanced data

Fingerprint

Dive into the research topics of 'Unbalanced Data Classification Model in PHM Field Based on Oversampling Algorithm'. Together they form a unique fingerprint.

Cite this