EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Federated Learning for Predictive Maintenance and Anomaly Detection Using Time Series Data Distribution Shifts in Manufacturing Processes

Jisu Ahn iD, Younjeong Lee, Namji Kim, Chanho Park iD, Jongpil Jeong iD

Sensors · 22.08.2023 · 23 (17) · 7331

DOI: 10.3390/s23177331 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 22.08.2023. Verfasst von Jisu Ahn und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Smart Factory Convergence, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Gyeonggi-do, Republic of Korea. Die Arbeit wurde bisher 84-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: SungKyunKwan University, Ministry of Education (MOE, Korea), National Research Foundation of Korea (NRF).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the manufacturing process, equipment failure is directly related to productivity, so predictive maintenance plays a very important role. Industrial parks are distributed, and data heterogeneity exists among heterogeneous equipment, which makes predictive maintenance of equipment challenging. In this paper, we propose two main techniques to enable effective predictive maintenance in this environment. We propose a 1DCNN-Bilstm model for time series anomaly detection and predictive maintenance of manufacturing processes. The model combines a 1D convolutional neural network (1DCNN) and a bidirectional LSTM (Bilstm), which is effective in extracting features from time series data and detecting anomalies. In this paper, we combine a federated learning framework with these models to consider the distributional shifts of time series data and perform anomaly detection and predictive maintenance based on them. In this paper, we utilize the pump dataset to evaluate the performance of the combination of several federated learning frameworks and time series anomaly detection models. Experimental results show that the proposed framework achieves a test accuracy of 97.2%, which shows its potential to be utilized for real-world predictive maintenance in the future.

Schlagwörter

Stichwörter der Autor:innen

LSTManomaly detectiondata distributionfederated learningtime series

Autor:innen und Institutionen

  • Department of Smart Factory Convergence, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Gyeonggi-do, Republic of Korea.
  • AI Research Center, Gfyhealth, 20 Pangyo-ro, Bundang-gu, Seongnam-si 13488, Gyeonggi-do, Republic of Korea.

ORCID-Profile: Jisu Ahn, Chanho Park, Jongpil Jeong

Förderung

  • SungKyunKwan University
  • Ministry of Education (MOE, Korea)
  • National Research Foundation of Korea (NRF)

Zitieren

APA

Ahn, J., Lee, Y., Kim, N., Park, C., & Jeong, J. (2023). Federated Learning for Predictive Maintenance and Anomaly Detection Using Time Series Data Distribution Shifts in Manufacturing Processes. Sensors, 23(17), 7331. https://doi.org/10.3390/s23177331

Vancouver

Ahn J, Lee Y, Kim N, Park C, Jeong J. Federated Learning for Predictive Maintenance and Anomaly Detection Using Time Series Data Distribution Shifts in Manufacturing Processes. Sensors. 2023;23(17):7331. doi:10.3390/s23177331

BibTeX
@article{Ahn2023,
  author = {Ahn, Jisu and Lee, Younjeong and Kim, Namji and Park, Chanho and Jeong, Jongpil},
  title = {Federated Learning for Predictive Maintenance and Anomaly Detection Using Time Series Data Distribution Shifts in Manufacturing Processes},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {17},
  pages = {7331},
  doi = {10.3390/s23177331}
}
Kostenlos starten →