Interpretable, data-driven models for predicting shaft power, fuel consumption, and speed considering the effects of hull fouling and weather conditions

Abstract

In response to the global call for action to reduce CO2 emissions, operational measures such as speed, route optimization, and hull cleaning play a significant role in the maritime industry. These measures can be implemented immediately without significant investment in both newbuilding ships and existing ships. To make accurate decisions regarding operational measures, reliable and precise models of environmental conditions and effects of hull fouling are required. In this study, a data-driven approach using linear regression was applied to predict shaft power, fuel consumption, and speed after intensive data preparation and feature engineering. First, a shaft power prediction model was developed by combining three independent submodels: the RPM-power model, hull fouling model, and environmental effect model. Subsequently, fuel consumption and speed prediction models were developed based on the shaft power prediction model. Model validation was performed on a 174K LNG carrier, and the results showed good accuracy even in long-term ship operations of more than two years. The mean absolute percentage errors (MAPEs) of the prediction models were 1.60%, 1.70%, and 2.68% for the shaft power, fuel consumption, and speed, respectively. The validated models were applied to two LNG carriers, and satisfactory results were obtained. This study contributes to greenhouse gas (GHS) reduction by providing interpretable, flexible, and accurate models that can help make correct decisions regarding optimal operational measures.