EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Robust Multivariate Time Series Classification Approach Based on Topological Data Analysis for Channel Fault Tolerance

Seong-Yeon Jeung iD, Jang-Woo Kwon iD

Sensors · 24.04.2025 · 25 (9) · 2709

DOI: 10.3390/s25092709 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 24.04.2025. Verfasst von Seong-Yeon Jeung und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, Inha University, Incheon 22212, Republic of Korea. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Institute of Energy Technology Evaluation and Planning, Ministry of Science and ICT, Korean government (MOTIE).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this study, we propose a robust artificial intelligence (AI) model for vibration monitoring of rotating equipment to support reliable operation across various industries, including manufacturing, power plants, and aerospace. The reliability and completeness of sensor data are essential for early detection of anomalies in equipment and for performing predictive maintenance. While AI-based predictive maintenance and condition-monitoring technologies have advanced in recent years, the issue of data loss caused by sensor failures remains a significant challenge that leads to performance degradation of AI models. In particular, for equipment utilizing multiple sensors, the complete loss of data from a single sensor significantly diminishes the predictive maintenance capability of AI models, thereby reducing their reliability. To address this issue, this study introduces topological data analysis (TDA) to develop a robust AI model. TDA analyzes the topological structure of sensor data to generate consistent feature vectors that capture the intrinsic characteristics of the data. This enables stable predictions even when certain channels of multi-sensor data are entirely missing. The proposed method demonstrates high performance resilience under conditions of partial sensor data loss, thereby contributing to enhanced reliability of AI-based predictive maintenance systems and the establishment of efficient maintenance strategies in the future.

Schlagwörter

Stichwörter der Autor:innen

MTSCTDAchannel faultdeep learningrotary machine

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, Inha University, Incheon 22212, Republic of Korea.
  • Department of Computer Engineering, Inha University, Incheon 22212, Republic of Korea.

ORCID-Profile: Seong-Yeon Jeung, Jang-Woo Kwon

Förderung

  • Korea Institute of Energy Technology Evaluation and Planning
  • Ministry of Science and ICT
  • Korean government (MOTIE)
  • National Research Foundation of Korea (NRF)

Zitieren

APA

Jeung, S. Y., & Kwon, J. W. (2025). A Robust Multivariate Time Series Classification Approach Based on Topological Data Analysis for Channel Fault Tolerance. Sensors, 25(9), 2709. https://doi.org/10.3390/s25092709

Vancouver

Jeung SY, Kwon JW. A Robust Multivariate Time Series Classification Approach Based on Topological Data Analysis for Channel Fault Tolerance. Sensors. 2025;25(9):2709. doi:10.3390/s25092709

BibTeX
@article{Jeung2025,
  author = {Jeung, Seong-Yeon and Kwon, Jang-Woo},
  title = {A Robust Multivariate Time Series Classification Approach Based on Topological Data Analysis for Channel Fault Tolerance},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {9},
  pages = {2709},
  doi = {10.3390/s25092709}
}
Kostenlos starten →