EUVIMEDEUVIMED entdecken
Crossref

A Two-Stage Fault Detection and Early Warning Framework for Intelligent Laboratory Measurement Systems

Wei Zhang, Yunpeng Gao, Jiangzhao Wang, Yongbin Zhou, Haili Zhao, Jianjun Zhao

IEEE Transactions on Instrumentation and Measurement · 2026 · 75 · 1-16

DOI: 10.1109/tim.2026.3682816 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Instrumentation and Measurement, 2026. Verfasst von Wei Zhang und 5 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Gefördert von: National Key Research and Development Program of China, State Key Laboratory of Intelligent Optimized Manufacturing in Mining and Metallurgy Process.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With advances in intelligent technologies for mineral beneficiation, the intelligent laboratory (ILAB) system has emerged as a novel online measurement device for real-time monitoring of ore grades. However, the reliability of ILAB is often challenged by dynamic process conditions, leading to delayed or inaccurate fault detection and disrupting quality control. To address this issue, a two-stage framework for fault detection and early warning is proposed. In the first stage, a fault prediction model based on TSFormer–bidirectional GRU (TSFormer-BiGRU) is developed to extract both global dependencies and local features from measurement time series and predict future values. In the second stage, a support vector data description (SVDD)-based fault detection mechanism with dual adaptive thresholds is designed, incorporating predicted values as key features to enable both fault detection and potential early warning. The proposed framework is validated on both the benchmark Tennessee Eastman (TE) process and the real-world ILAB process. Results show that the framework can detect faults more than three time windows in advance, with high accuracy and low false-alarm rates (FARs), significantly enhancing ILAB measurement reliability and process quality control in mineral beneficiation processes.

Förderung

  • National Key Research and Development Program of China
  • State Key Laboratory of Intelligent Optimized Manufacturing in Mining and Metallurgy Process

Zitieren

APA

Zhang, W., Gao, Y., Wang, J., Zhou, Y., Zhao, H., & Zhao, J. (2026). A Two-Stage Fault Detection and Early Warning Framework for Intelligent Laboratory Measurement Systems. IEEE Transactions on Instrumentation and Measurement, 75, 1-16. https://doi.org/10.1109/tim.2026.3682816

Vancouver

Zhang W, Gao Y, Wang J, Zhou Y, Zhao H, Zhao J. A Two-Stage Fault Detection and Early Warning Framework for Intelligent Laboratory Measurement Systems. IEEE Transactions on Instrumentation and Measurement. 2026;75:1-16. doi:10.1109/tim.2026.3682816

BibTeX
@article{Zhang2026,
  author = {Zhang, Wei and Gao, Yunpeng and Wang, Jiangzhao and Zhou, Yongbin and Zhao, Haili and Zhao, Jianjun},
  title = {A Two-Stage Fault Detection and Early Warning Framework for Intelligent Laboratory Measurement Systems},
  journal = {IEEE Transactions on Instrumentation and Measurement},
  year = {2026},
  volume = {75},
  pages = {1--16},
  doi = {10.1109/tim.2026.3682816}
}
Kostenlos starten →