Small- to medium-sized manufacturing industries are challenged by insufficient production systems and resources, leading them to adopt a run-to-failure maintenance strategy. This run-to-failure maintenance strategy was adopted by factory “A” due to higher production output demands, resulting in inefficiencies in preventive maintenance activities. In return, the inefficiencies in preventive maintenance have led to higher frequencies and longer production downtimes, negatively affecting production output. The use of Factory “A” historical downtime data extracted from the Overall Equipment Effectiveness (OEE) software connected to Factory “A” production lines was analysed using FTA to assess failure causes and identify gaps in existing maintenance approaches. The research adopted the Markov processes as a model to extend equipment lifespan and reduce maintenance costs. This research focused on the adoption of Condition-Based Maintenance (CM) strategies in factory “A. The research optimised CM using the Markov processes and models to predict equipment reliability and optimise maintenance schedules. The optimised CM have improved factory “A” operational Key Performance Indicators (KPIs), by lowering Systems Average Interruption Duration Index (SAIDI) and Systems Average Interruption Frequency Index (SAIFI), resulting in a 58.11% reduction in downtime (102.9 hours) and a 28.04% decrease in downtime frequency (60 occurrences) respectively. The improved CM strategy balanced investment, operational, and maintenance costs by enhancing production efficiency and profitability. By incorporating Markov models for reliability predictions, the study demonstrated how CM have optimised maintenance strategies, extended equipment lifespan, and improved cost-effectiveness in manufacturing factory “A”.