<![CDATA[This study presents the development and implementation of an IoT-based Ship Maintenance Information System at PT. Sera Jaya Kesuma, designed to enhance maritime maintenance operations through real-time monitoring and predictive analytics. The system integrates industrial-grade sensors with edge-cloud architecture to monitor critical ship components, utilizing LSTM neural networks for anomaly detection. Results from a six-month trial demonstrated significant improvements, including 93.7% accuracy in fault prediction, a 35.9% reduction in unplanned downtime, and 28% lower maintenance costs ($12,500 monthly savings). Operational efficiencies were achieved through automated work orders (saving 17 hours/week) and prevented environmental incidents (100% oil spill prevention). Despite challenges in tropical marine conditions, the solution proved robust through adaptive data handling and durable sensor packaging. While currently limited to mechanical systems, the framework provides a scalable model for IoT adoption in mid-sized shipping companies, particularly in developing maritime economies. The study concludes that IoT-driven predictive maintenance transforms traditional reactive approaches, offering both immediate operational benefits and long-term strategic advantages for the maritime industry. Future work should expand monitoring scope to navigational systems and enhance edge computing capacity for fleet-wide deployment.]]>
