SMOTE-Based Fault Diagnosis Method for Unbalanced Samples

Yuan Xu, Xiaoqian Cheng, Wei Ke, Qun Xiong Zhu, Yan Lin He, Yang Zhang

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

Abstract

Industrial processes are changing with each passing day, and the probability of failure is also increasing, and accurate fault diagnosis is becoming extremely important. In this paper, SMOTE-based fault diagnosis method for unbalanced samples is proposed. First, the SMOTE algorithm is used to oversample the unbalanced sample. Second, considering the high dimensionality of industrial data, the FDA algorithm is used for feature extraction. Third, the AdaBoost algorithm is used for fault diagnosis. Finally, the simulation validation is performed on the TFF dataset. The method proposed in this paper has higher diagnostic accuracy than other methods.

Original languageEnglish
Title of host publicationProceedings of 2022 IEEE 11th Data Driven Control and Learning Systems Conference, DDCLS 2022
EditorsMingxuan Sun, Zengqiang Chen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages682-686
Number of pages5
ISBN (Electronic)9781665496759
DOIs
Publication statusPublished - 2022
Event11th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2022 - Emeishan, China
Duration: 3 Aug 20225 Aug 2022

Publication series

NameProceedings of 2022 IEEE 11th Data Driven Control and Learning Systems Conference, DDCLS 2022

Conference

Conference11th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2022
Country/TerritoryChina
CityEmeishan
Period3/08/225/08/22

Keywords

  • AdaBoost
  • FDA
  • Fault Diagnosis
  • SMOTE
  • Unbalanced Samples

Fingerprint

Dive into the research topics of 'SMOTE-Based Fault Diagnosis Method for Unbalanced Samples'. Together they form a unique fingerprint.

Cite this