EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable AI-Driven Quality and Condition Monitoring in Smart Manufacturing

M Nadeem Ahangar iD, Z A Farhat iD, Aparajithan Sivanathan iD, N Ketheesram iD, S Kaur iD

Sensors · 30.01.2026 · 26 (3) · 911

DOI: 10.3390/s26030911 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 30.01.2026. Verfasst von M Nadeem Ahangar und 4 weiteren Autor:innen. Beteiligte Einrichtung: AMRC North West, University of Sheffield, Blackburn BB2 7HN, UK. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: High Value Manufacturing Catapult.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial intelligence (AI) is increasingly adopted in manufacturing for tasks such as automated inspection, predictive maintenance, and condition monitoring. However, the opaque, black-box nature of many AI models remains a major barrier to industrial trust, acceptance, and regulatory compliance. This study investigates how explainable artificial intelligence (XAI) techniques can be used to systematically open and interpret the internal reasoning of AI systems commonly deployed in manufacturing, rather than to optimise or compare model performance. A unified explainability-centred framework is proposed and applied across three representative manufacturing use cases encompassing heterogeneous data modalities and learning paradigms: vision-based classification of casting defects, vision-based localisation of metal surface defects, and unsupervised acoustic anomaly detection for machine condition monitoring. Diverse models are intentionally employed as representative black-box decision-makers to evaluate whether XAI methods can provide consistent, physically meaningful explanations independent of model architecture, task formulation, or supervision strategy. A range of established XAI techniques, including Grad-CAM, Integrated Gradients, Saliency Maps, Occlusion Sensitivity, and SHAP, are applied to expose model attention, feature relevance, and decision drivers across visual and acoustic domains. The results demonstrate that XAI enables alignment between model behaviour and physically interpretable defect and fault mechanisms, supporting transparent, auditable, and human-interpretable decision-making. By positioning explainability as a core operational requirement rather than a post hoc visual aid, this work contributes a cross-modal framework for trustworthy AI in manufacturing, aligned with Industry 5.0 principles, human-in-the-loop oversight, and emerging expectations for transparent and accountable industrial AI systems.

Schlagwörter

Stichwörter der Autor:innen

Grad-CAMIndustry 5.0SHAPacoustic anomaly detectionexplainable artificial intelligence (XAI)human-in-the-loop systemsindustrial AIpredictive maintenancesmart manufacturingtrustworthy AIvisual inspection

Autor:innen und Institutionen

  • AMRC North West, University of Sheffield, Blackburn BB2 7HN, UK.
  • School of Mechanical, Aerospace and Civil Engineering, University of Sheffield, Mappin Street, Sheffield S1 4DT, UK.

ORCID-Profile: M Nadeem Ahangar, Z A Farhat, Aparajithan Sivanathan, N Ketheesram, S Kaur

Förderung

  • High Value Manufacturing Catapult

Zitieren

APA

Ahangar, M. N., Farhat, Z. A., Sivanathan, A., Ketheesram, N., & Kaur, S. (2026). Explainable AI-Driven Quality and Condition Monitoring in Smart Manufacturing. Sensors, 26(3), 911. https://doi.org/10.3390/s26030911

Vancouver

Ahangar MN, Farhat ZA, Sivanathan A, Ketheesram N, Kaur S. Explainable AI-Driven Quality and Condition Monitoring in Smart Manufacturing. Sensors. 2026;26(3):911. doi:10.3390/s26030911

BibTeX
@article{Ahangar2026,
  author = {Ahangar, M Nadeem and Farhat, Z A and Sivanathan, Aparajithan and Ketheesram, N and Kaur, S},
  title = {Explainable AI-Driven Quality and Condition Monitoring in Smart Manufacturing},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {3},
  pages = {911},
  doi = {10.3390/s26030911}
}
Kostenlos starten →