Integrating Artificial Intelligence for Predictive Maintenance in Critical Infrastructure Systems at NMU: A bibliometric analysis

Back to 2025 Papers

Hannah Tsitsi Mago, Prof Theo Haupt, Onyeka Nkwonta and Progress S. Chigangacha

DOI: https://doi.org/10.64755/ZDEG3855

Keywords: Artificial Intelligence, Predictive Maintenance, Critical Infrastructure, Bibliometric Analysis

DOWNLOAD PDF

ABSTRACT

PURPOSE

As our academic institutions continue to grow and evolve, the systems that support them have become increasingly complex. This complexity underscores the necessity for more effective and proactive maintenance strategies to ensure everything operates smoothly. This study explores the evolution of Artificial Intelligence (AI) in predictive maintenance, identifies current areas of focus, and examines global research trends in this field. In this study, attention will be given to how AI-driven advancements could enhance the infrastructure management framework at Nelson Mandela University (NMU).

DESIGN / METHODOLOGY / APPROACH

A bibliometric analysis was conducted using DimensionAI and Web of Science databases, focusing on peer-reviewed journal articles and conference papers published between 2016 and 2025. VOSviewer was utilised to map co-authorship networks, keyword co-occurrences, and research clusters. The study also examined regional contributions and institutional linkages to identify global research leaders and collaborative patterns relevant to NMU’s context.

FINDINGS

The analysis shows that there has been a significant increase in research publications starting from 2018, with particularly sharp increases in 2020 and again in 2024. Key areas of focus include machine learning, the Internet of Things (IoT), digital twins, and ensuring infrastructure reliability. However, the findings also point out a significant gap in applied research within African universities. This suggests that there’s a real need for tailored AI implementation models that fit the local context. At Nelson Mandela University (NMU), there has been a fantastic opportunity to make a real impact through collaborative efforts across different disciplines, especially by launching pilot projects aimed at improving predictive maintenance of essential facilities.

PRACTICAL IMPLICATIONS

The study provides a valuable framework for policymakers, facilities managers, and researchers aiming to implement best practices in AI-driven predictive maintenance. By leveraging these insights, NMU can enhance asset management, reduce maintenance costs, and improve service reliability. This strategy not only promotes sustainability but also aligns with wider digital transformation initiatives.

ORIGINAL / VALUE

This study is the first of its kind to explore the current landscape of how artificial intelligence is being used for predictive maintenance, particularly within the context of higher education infrastructure in Africa. It aims to provide insight into how Nelson Mandela University (NMU) can benefit from AI’s ability to enhance the maintenance of infrastructure systems, combining it with global insights into the specific needs of the local environment.