Ship Performance Monitoring using Machine-learning

TL;DR

This paper demonstrates the use of machine learning models to monitor and predict the hydrodynamic performance of ships over time using onboard data, aiding maintenance and operational planning.

Contribution

It introduces and calibrates three ML models for estimating ship performance changes due to fouling, showing that simple models can be effective with domain knowledge.

Findings

Probabilistic ANN outperforms other models in accuracy.

ML models effectively track performance degradation over time.

Simple models can be sufficient with proper calibration.

Abstract

The hydrodynamic performance of a sea-going ship varies over its lifespan due to factors like marine fouling and the condition of the anti-fouling paint system. In order to accurately estimate the power demand and fuel consumption for a planned voyage, it is important to assess the hydrodynamic performance of the ship. The current work uses machine-learning (ML) methods to estimate the hydrodynamic performance of a ship using the onboard recorded in-service data. Three ML methods, NL-PCR, NL-PLSR and probabilistic ANN, are calibrated using the data from two sister ships. The calibrated models are used to extract the varying trend in ship's hydrodynamic performance over time and predict the change in performance through several propeller and hull cleaning events. The predicted change in performance is compared with the corresponding values estimated using the fouling friction coefficient ($\Delta C_F$). The ML methods are found to be performing well while modelling the hydrodynamic state variables of the ships with probabilistic ANN model performing the best, but the results from NL-PCR and NL-PLSR are not far behind, indicating that it may be possible to use simple methods to solve such problems with the help of domain knowledge.