Integrating Machine Learning and Internet of Things for Predictive Maintenance Enhancing Operational Efficiency and Maritime Digitalization

This study explores the implementation of Machine Learning (ML) and the Internet of Things (IoT) in predictive maintenance to enhance the operational efficiency of ships. The primary goal is to evaluate the effectiveness of these technologies in reducing maintenance costs, minimizing unexpected machinery failures, and improving fuel efficiency. The research is based on previous studies on AI-driven predictive maintenance and IoT-based real-time monitoring. It builds upon the work of Kim & Park (2021) and Li et al. (2019), who demonstrated the advantages of deep learning and IoT in improving maritime asset management. A comparative analysis was conducted using multiple ML algorithms, including Random Forest, Support Vector Machine (SVM), K-Means Clustering, and Long Short-Term Memory (LSTM). Data from IoT-enabled sensors on ship machinery were used to evaluate model accuracy, downtime reduction, and cost efficiency improvements. LSTM outperformed other models with an accuracy of 89.1%. Predictive maintenance reduced downtime by 30%, extended machinery lifespan by 20%, and decreased operational costs by 15%. Challenges include IoT infrastructure limitations, data security concerns, and the need for extensive historical data. This study highlights the necessity for shipping companies to invest in IoT infrastructure, cybersecurity measures, and workforce training to optimize predictive maintenance. The research contributes to maritime digitalization by demonstrating how ML and IoT integration can transform maintenance strategies, leading to a more efficient and cost-effective shipping industry.