The advent of Industry 4.0 has revolutionized industrial operations by integrating advanced technologies such as the Internet of Things (IoT), artificial intelligence (AI), and big data analytics into manufacturing systems. Among its many applications, predictive maintenance emerges as a critical strategy to minimize downtime, reduce operational costs, and enhance asset longevity. This article presents a modelling approach to predictive maintenance tailored for Industry 4.0 environments. We explore how real-time data acquisition and machine learning algorithms can be integrated into a predictive maintenance framework, enabling early fault detection and optimal scheduling of maintenance activities. The study proposes a comprehensive model that incorporates sensor data analysis, failure prediction, and decision support systems. Simulations and case studies demonstrate the effectiveness of the proposed approach in increasing system reliability and efficiency. Our findings highlight the pivotal role of data-driven models in transforming traditional maintenance practices into proactive, intelligent maintenance strategies suitable for smart factories.