This article addresses the critical challenge of optimizing ship machinery maintenance systems by integrating digital strategies. It examines adaptive maintenance approaches that consider real-time equipment condition, predictive analytics, and cost efficiency. A comparative analysis of existing methodologies is presented, highlighting their advantages and limitations. The study introduces an enhanced framework that incorporates machine learning models, sensor-based monitoring, and an improved decision-making process for maintenance scheduling. Experimental results demonstrate the effectiveness of adaptive strategies in minimizing downtime, reducing operational costs, and extending the lifespan of ship machinery. Practical applications and long-term implications for maritime industry stakeholders are also discussed. Additionally, the article explores the economic and operational impacts of changes in technical conditions, emphasizing cost-effectiveness and time optimization in servicing practices. The findings advocate for adaptive maintenance approaches that ensure efficient ship operation, reduce downtime, and enhance the overall productivity of maritime transport.
Holovan et al. (Thu,) studied this question.