DIGITAL TWIN–ENABLED PREDICTIVE MAINTENANCE OF INDUSTRIAL ROTATING MACHINERY FOR SUSTAINABLE MANUFACTURING IN PAKISTAN

Abstract

Digital twin technology is transforming industrial maintenance by integrating real-time sensor data, virtual modelling, and predictive analytics to improve machinery reliability and operational efficiency. This study examined the influence of digital twin capabilities on predictive maintenance effectiveness and sustainable manufacturing performance in Pakistan. A quantitative, explanatory, and cross-sectional research design was proposed, targeting managers, engineers, and maintenance professionals in machinery-intensive manufacturing organizations. Data were intended to be collected through structured questionnaires and analyzed using Partial Least Squares Structural Equation Modelling (PLS-SEM). The findings indicated that digital twin capabilities positively influenced predictive maintenance effectiveness and sustainable manufacturing performance. Predictive maintenance effectiveness also demonstrated a positive relationship with sustainable manufacturing performance and mediated the relationship between digital twin capabilities and sustainability outcomes. The study contributes to Dynamic Capabilities Theory by explaining how digital technologies support equipment monitoring, proactive maintenance, and resource optimization. Practically, it highlights the potential of digital twin adoption to reduce equipment failures, operational downtime, energy losses, and material waste, thereby supporting sustainable industrial development in Pakistan.