EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A process-guided uncertainty-aware deep learning framework for reliable and interpretable industrial fault diagnosis

Babar Hayat iD, Shabeer Ahmad, Muhammad Asfandyar Shahid, Adil Khan, Md Rajibul Islam iD, Md Shohel Sayeed iD, Yasir Ullah

PLOS One · 02.06.2026 · 21 (6) · e0349385

DOI: 10.1371/journal.pone.0349385 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 02.06.2026. Verfasst von Babar Hayat und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Xi'an Eurasia University, Xi'an, Shaanxi, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Timely fault detection is essential for safety, product quality, and energy efficiency in advanced industrial processes. However, many existing fault diagnosis methods insufficiently exploit process structure and sensor reliability, which limits their robustness and practical usefulness for process engineers. This study presents an improved framework SAU-PGA-CNN-BiLSTM that first couples Convolutional Neural Networks and Bidirectional Long Short-Term Memory layers to extract multivariate temporal dynamics and spatial correlations of the process data, secondly a process guided and sensor-aware attention mechanism is introduced which embeds process centrality, sequence level sensor reliability and uncertainty to the attention learning, to suppress unreliable channels and bias towards informative and stable sensors. In addition, Monte Carlo dropout with sensor prior-conditioning is used to provide calibrated confidence estimates that reflect both predictive uncertainty and sensor reliability. Finally, two lightweight sigmoid output heads perform fault detection and diagnosis combinedly, promoting mutual reinforcement between the tasks. Validated on the Tennessee Eastman Process benchmark, the proposed framework outperforms baselines model and achieves 93.6% multiclass diagnosis accuracy with 94.0% F1 score. After temperature scaling, the proposed model also demonstrates improved calibration compared with an otherwise identical model without sensor awareness, reducing negative log-likelihood from 0.197 to 0.182, Brier score from 0.101 to 0.095, and expected calibration error from 0.040 to 0.037. Attention visualizations further show that the model focuses on process-relevant and reliable sensors, supporting reliable industrial fault diagnosis.

Autor:innen und Institutionen

  • School of Information Engineering, Xi'an Eurasia University, Xi'an, Shaanxi, China.
  • School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China.
  • School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China.
  • Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, Bangladesh.
  • Centre for Intelligent Cloud Computing, CoE for Advanced Cloud, Faculty of Information Science and Technology, Multimedia University, Bukit Beruang, Melaka, Malaysia.
  • Centre for Wireless Technology, Faculty of AI and Engineering, Multimedia University, Cyberjaya, Selangor, Malaysia.

ORCID-Profile: Babar Hayat, Md Rajibul Islam, Md Shohel Sayeed

Zitieren

APA

Hayat, B., Ahmad, S., Shahid, M. A., Khan, A., Islam, M. R., Sayeed, M. S., & Ullah, Y. (2026). A process-guided uncertainty-aware deep learning framework for reliable and interpretable industrial fault diagnosis. PLOS One, 21(6), e0349385. https://doi.org/10.1371/journal.pone.0349385

Vancouver

Hayat B, Ahmad S, Shahid MA, Khan A, Islam MR, Sayeed MS, et al. A process-guided uncertainty-aware deep learning framework for reliable and interpretable industrial fault diagnosis. PLOS One. 2026;21(6):e0349385. doi:10.1371/journal.pone.0349385

BibTeX
@article{Hayat2026,
  author = {Hayat, Babar and Ahmad, Shabeer and Shahid, Muhammad Asfandyar and Khan, Adil and Islam, Md Rajibul and Sayeed, Md Shohel and Ullah, Yasir},
  title = {A process-guided uncertainty-aware deep learning framework for reliable and interpretable industrial fault diagnosis},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {6},
  pages = {e0349385},
  doi = {10.1371/journal.pone.0349385}
}
Kostenlos starten →