Fast Adaption for Multi Motor Anomaly Detection via Meta Learning and deep unsupervised learning

Yi Cheng Yu, Shang Wen Chuang, Hong Han Shuai, Chen-Yi Lee

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

5 Scopus citations

Abstract

For PHM(Predictive Health Management) in an industrial scenario, motor vibration anomaly detection requires a large number of labeled data. The problem is that the anomaly vibration signal data is scarce and difficult to be obtained, especially the problem of insufficient data in the building and deployment of multi-machine models. This paper proposes a Meta-learning method based on deep unsupervised learning(Autoencoder). We use non-labeled and a small amount of vibration signal data which is converted into 52 key physical and statistical features to build models of different motors. By inputting these 52 features into designed models, other 52 features can be reconstructed as output. We use input and output features to calculate reconstruction error which is used as the criterion for the performance of models. We also use accuracy as the criterion for the performance of models. In the actual industrial situation, the improvement of accuracy by our proposed method is about 33.50% better than the method only with unsupervised learning for the new sensor model with few vibration data.

Original languageEnglish
Title of host publication2022 IEEE 31st International Symposium on Industrial Electronics, ISIE 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1186-1189
Number of pages4
ISBN (Electronic)9781665482400
DOIs
StatePublished - 2022
Event31st IEEE International Symposium on Industrial Electronics, ISIE 2022 - Anchorage, United States
Duration: 1 Jun 20223 Jun 2022

Publication series

NameIEEE International Symposium on Industrial Electronics
Volume2022-June

Conference

Conference31st IEEE International Symposium on Industrial Electronics, ISIE 2022
Country/TerritoryUnited States
CityAnchorage
Period1/06/223/06/22

Keywords

  • Autoencoder
  • Meta-learning
  • reconstruction error
  • unsupervised learning

Fingerprint

Dive into the research topics of 'Fast Adaption for Multi Motor Anomaly Detection via Meta Learning and deep unsupervised learning'. Together they form a unique fingerprint.

Cite this