Document Type

Conference Paper

Publication Date

2026

DOI

10.18260/1-2--59713

Publication Title

2026 ASEE Annual Conference & Exposition

Pages

12 pp.

Conference Name

2026 ASEE Annual Conference & Exposition, June 21-24, 2026, Charlotte, NC, USA

Abstract

Nowadays, Industry 4.0 has transformed manufacturing industries into a data-rich system driven by IoT, automation, and Artificial Intelligence (AI). Within this context, Predictive Maintenance (PdM) provides a proactive strategy that leverages heterogeneous sensor data such as vibration, acoustic, electrical, and visual signals along with historical performance and advanced analytics to forecast equipment failures before they occur. Usually, AI-driven PdM (AI-PdM) enhances this capability by integrating AI-based sensor analytics to automate fault prediction and optimize system reliability. However, traditional AI-PdM often functions as a “black box,” providing limited interpretability of its decision-making process and posing challenges for trust, validation, and human oversight in critical manufacturing environments. To address these challenges, explainable AI-based PdM (XAI-PdM) extends beyond prediction accuracy by leveraging explainability through transparent-based analysis into intelligent maintenance decision-making. XAI-PdM-based framework integrates heterogeneous sensor data with interpretable AI models that not only predict equipment degradation but also clarify which sensors and features contribute to each prediction. Such transparency bridges the gaps between complex AI algorithms and engineering expertise, fostering trustworthy AI, traceability, and actionable insights for real-time maintenance. Identifying this need, it is essential to transfer XAI-PdM concepts to future educators, empowering teachers to prepare students for the demands of smart manufacturing environments. This paper provides condense guidelines for utilizing cutting-edge XAI tools with real industrial datasets, enabling students to enhance their problem-solving skills and workforce readiness for next-generation advanced manufacturing. The XAI-PdM-driven context integrates both theoretical and experiential learning to equip students with cross-disciplinary competencies in AI and data analytics. Ultimately, these guidelines provide to prepare students who can design, interpret, and deploy data-driven intelligent PdM systems that foster sustainability and innovations in the manufacturing industry.

Rights

© 2026 American Society for Engineering Education.

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2026 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference.

Original Publication Citation

Al Mamun, A., Kuzlu, M., Smith, K., Jovanovic, V. M., Ismael, D., El-Shahat, A., Sicaja, A., & Chy, M. H. I. (2026, June 21-24). Explainable AI-driven predictive maintenance curriculum for smart manufacturing [Conference paper]. 2026 ASEE Annual Conference & Exposition, Charlotte, NC, USA. https://doi.org/10.18260/1-2--59713

ORCID

0000-0002-8719-2353 (Kuzlu), 0000-0002-8719-2353 (Smith), 0000-0002-8626-903X (Jovanovic), 0009-0003-7410-3045 (Ismael), 0000-0003-0148-5014 (El-Shahat), 0009-0007-5734-5316 (Chy)

Download

Share

COinS