Translate 
Abstract
The rise of machine learning in predictive maintenance is redefining industrial strategies, and improving operational performance and business resilience in the face of disruptions. However, although this technology has demonstrated its potential in various sectors, the literature remains lacking regarding its precise impact in emerging economies, particularly in Morocco. This study proposes an innovative conceptual model, structuring the analysis of the links between the integration of machine learning, organizational factors, and industrial resilience. By mobilizing theoretical frameworks such as the theory of dynamic capabilities and that of complex adaptive systems, we highlight the mediating role of digital maturity, data diversity, and organizational flexibility in the optimization of predictive maintenance strategies. The proposed methodological approach is based on a mixed approach, combining a quantitative analysis using structural equation modeling (SEM), to empirically test the structural relationships, and a qualitative study using semi-structured interviews, aimed at contextualizing the dynamics underlying the adoption of machine learning. This methodological triangulation ensures robust validation of hypotheses and identifies the organizational and technological factors that determine the effectiveness of these tools. The expected results will contribute to a better understanding of the strategic levers that allow companies to fully exploit machine learning in predictive maintenance while proposing avenues for improvement for research and industrial practice. This study is thus part of an evolutionary perspective, paving the way for future empirical investigations on the optimal adoption of artificial intelligence technologies in Industry 4.0.
Published Version
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
