Data-Driven Approach for Estimating Power and Fuel Consumption of Ship: A Case of Container Vessel

• DOI: 10.3390/math10224167
• Publication Date: 2022-11-08T17:45:47Z
• Authors: Tayfun Uyanık; Yunus Yalman; Özcan Kalenderli; Yasin Arslanoğlu; Yacine Terriche; Chun-Lien Su; Josep M. Guerrero
• Keywords: Kernel (algebra)

In recent years, shipborne emissions have become a growing environmental threat. The International Maritime Organization has implemented various rules and regulations to resolve this concern. Ship Energy Efficiency Management Plan, Design Index, Operational Indicator are examples of guidelines that increase energy efficiency reduce emissions. main engine shaft power (MESP) fuel consumption (FC) the critical components used in ship calculations. Errors calculation methodologies also caused by misinterpretation these values. This study aims predict MESP FC container with help data-driven utilizing actual voyage data assist process ship’s indexes appropriately. algorithms’ prediction success was measured using RMSE, MAE, R2 error metrics. When simulation results were analyzed, Deep Neural Network Bayes algorithms predicted best 0.000001 0.000002 0.000987 0.000991 0.999999 R2, respectively, while Multiple-Linear Regression Kernel Ridge estimated 0.000208 0.000216 0.001375 0.001471 respectively.