This research presents a comparative analysis of AI-driven predictive maintenance and traditional
maintenance approaches, including reactive and preventive maintenance, within the manufacturing
sector. Reactive maintenance, a run-to-failure strategy, often leads to significant downtime and costly
repairs, while preventive maintenance schedules regular checks to reduce breakdowns but can result
in over-maintenance and inefficiencies. Predictive maintenance, enhanced by AI, uses real-time sensor
data, machine learning algorithms, and cloud-edge computing to predict equipment failures before they
occur. Experimental results show that predictive maintenance outperforms both reactive and preventive
methods in key metrics such as downtime, maintenance cost, repair frequency, and mean time between
failures (MTBF). By leveraging AI to analyze equipment conditions, predictive maintenance ensures
timely interventions, optimizing operational efficiency and reducing overall costs. These findings
demonstrate the superiority of predictive maintenance in enhancing equipment reliability and cost-effectiveness
in manufacturing environments.
