EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Explainable Artificial Intelligence in Rotating Machinery Fault Diagnosis: A Comprehensive Review and Emerging Trends

Shengnan Tang iD, Zengyu Ren iD, Leiqi Zheng, Jiaming Wang

Sensors · 25.08.2026 · 26 (17) · 5379

DOI: 10.3390/s26175379 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 25.08.2026. Verfasst von Shengnan Tang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Jiangsu University, Zhenjiang 212013, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 157 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Natural Science Foundation of China, the Open Foundation of the State Key Laboratory of Mechanical Transmission for Advanced Equipment, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rotating machinery is essential to energy, aerospace, manufacturing, and other safety-critical industries. Although deep-learning-based fault diagnosis has achieved high accuracy, its black-box nature limits trust, verification, and industrial deployment. This review examines explainable artificial intelligence for rotating machinery fault diagnosis and classifies existing methods into ante hoc and post hoc approaches according to their integration with model architectures. Their physical interpretability, applicable fault scenarios, explanation quality, computational overhead, robustness, and edge-deployment potential are critically compared. Quantitative criteria, including fidelity, stability, robustness, localization, and physical consistency are discussed to support objective evaluation of explanations. The review further highlights the gap between laboratory validation and industrial operation, particularly under sensor degradation, electromagnetic interference, variable working conditions, limited computing resources, and scarce fault data. It also discusses how model-relative explanations can be mapped to calibrated vibration quantities, fault-characteristic frequencies, industrial diagnostic standards, and actionable maintenance decisions. The distinction between correlation-based attribution and causal root-cause analysis is clarified, together with the role of digital twins and human-in-the-loop decision support. Finally, future research priorities are identified in standardized benchmarking, robust lightweight models, causal reasoning, and human-centered industrial deployment.

Schlagwörter

Stichwörter der Autor:innen

ante hoc explainabilitydeep learningintelligent fault diagnosispost hoc explainabilityrotating machinery

Autor:innen und Institutionen

  • School of Mechanical Engineering, Jiangsu University, Zhenjiang 212013, China.
  • State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing 400044, China.
  • Leo Group Co., Ltd., Wenling 317500, China.

ORCID-Profile: Shengnan Tang, Zengyu Ren

Förderung

  • the National Natural Science Foundation of China
  • the Open Foundation of the State Key Laboratory of Mechanical Transmission for Advanced Equipment
  • National Natural Science Foundation of China
  • Open Foundation of the State Key Laboratory of Mechanical Transmission for Advanced Equipment

Zitieren

APA

Tang, S., Ren, Z., Zheng, L., & Wang, J. (2026). Explainable Artificial Intelligence in Rotating Machinery Fault Diagnosis: A Comprehensive Review and Emerging Trends. Sensors, 26(17), 5379. https://doi.org/10.3390/s26175379

Vancouver

Tang S, Ren Z, Zheng L, Wang J. Explainable Artificial Intelligence in Rotating Machinery Fault Diagnosis: A Comprehensive Review and Emerging Trends. Sensors. 2026;26(17):5379. doi:10.3390/s26175379

BibTeX
@article{Tang2026,
  author = {Tang, Shengnan and Ren, Zengyu and Zheng, Leiqi and Wang, Jiaming},
  title = {Explainable Artificial Intelligence in Rotating Machinery Fault Diagnosis: A Comprehensive Review and Emerging Trends},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {17},
  pages = {5379},
  doi = {10.3390/s26175379}
}
Kostenlos starten →