Explainable Artificial Intelligence in Manufacturing Operations: A Bibliometric Analysis

This paper presents a bibliometric analysis of explainable artificial intelligence (XAI) within the manufacturing sector, with a focus on the critical areas of quality, maintenance, and production. Despite the increasing integration of XAI in industrial applications, a bibliometric exploration of its impact across these specific dimensions remains uncharted. Our study fills this gap by employing bibliometric methods to map the landscape of XAI research in manufacturing, analyzing publication patterns and thematic evolutions. Understanding this landscape is crucial, as it not only highlights the current state and trajectory of XAI applications in manufacturing but also identifies key areas where further innovation and investigation can significantly enhance efficiency, transparency, and decision-making processes in the industry. Utilizing the Bibliometrix R-package and data from the Scopus database, we analyze 107 publications from 2019 to 2024.We chart the intellectual trajectory of XAI, delving into predominant themes and observing a research progression from foundational machine learning to its sophisticated applications, culminating in Industry 4.0 innovations. The analysis reveals an academic landscape where explainability is increasingly intertwined with the technological advances of smart manufacturing, spotlighting key topics and their evolution that reflect the field’s dynamic nature. This investigation offers a novel lens on the bibliometric trends shaping the development of transparent, intelligent systems within the manufacturing sector.