Data-driven Ship Performance Models - - Emphasis on Energy Efficiency and Fatigue Safety
Doctoral thesis, 2023

Due to digitalization in the maritime industry, a huge amount of ship operation-related data has been collected. The main objective of this thesis is to exploit machine learning/big data analytics to build data-driven ship performance models, focusing on speed-power relationship modeling, and fatigue accumulation assessment during a ship’s operation at sea.

The speed-power performance models are established in three different ways: 1) semi-empirical white-box models, 2) machine learning black-box methods, and 3) physics-informed grey-box models. The white-box models include improved semi-empirical formulas for ship added resistance due to head waves, and further developed formulas in arbitrary wave headings. Validation studies using three case study ships show good agreement between the speed predictions by the white-box models and the long-term averages of full-scale measurements. Different supervised machine learning methods’ capabilities have been compared for black-box modeling. The XGBoost algorithm is found to have the most reliable predictive ability, with the highest efficiency suitable for onboard devices. The novel grey-box models are proposed by considering the physical principles in model tests and big data information from real sailing. It has been demonstrated that the proposed grey-box models can improve prediction accuracy by approximately 30% for ship speed estimation and provides 50% less cumulative error of sailing time than the black-box methods.

The impact of voyage optimization-aided operations on the encountered wave conditions and ship fatigue damage is investigated in this thesis. By recommending appropriate routes, voyage optimization can greatly extend the fatigue life of a ship by at least 50%. The machine learning techniques are also applied to a ship’s fatigue assessment. The results indicate that the proposed data-driven fatigue assessment model could increase accuracy by approximately 70% for the case study vessel compared to other prominent spectral methods.

semi-empirical

energy efficiency

fatigue assessment

grey-box

full-scale measurements

speed-power relationship

added resistance due to waves

ship performance

machine learning

Lecture hall KB in the Kemi building, Chalmers University of Technology, Kemigården 4, Göteborg.
Opponent: Professor Giles Thomas, University College London (UCL), London, UK.

Author

Xiao Lang

Chalmers, Mechanics and Maritime Sciences (M2), Marine Technology

A Practical Speed Loss Prediction Model at Arbitrary Wave Heading for Ship Voyage Optimization

Journal of Marine Science and Application,; Vol. 20(2021)p. 410-425

Journal article

Impact of ship operations aided by voyage optimization on a ship’s fatigue assessment

Journal of Marine Science and Technology,; Vol. 26(2021)p. 750-771

Journal article

Physics-informed machine learning models for ship speed prediction

Machine learning methods for ship fatigue assessment

Shipping is the backbone of international trade in the global economy, contributing to about 80% of global trade by volume. One of the most significant challenges in the maritime industry is developing measures to reduce fuel costs and air pollutant emissions of ships, as well as enhance their safety. However, the benefits of those measures have not been fully realized due to large uncertainties in the ship performance models, which are the key components for all the energy efficiency/safety measures. Driven by today’s digital transformation in the shipping industry, large amounts of ship operation data are being collected. They can be exploited to improve ship performance models and further energy efficiency/safety measures.

This thesis exploits machine learning/big data analytics to build data-driven ship performance models, focusing on speed-power relationship modeling, and fatigue accumulation assessment. Those models show good agreement with the model test results and full-scale measurements. The output of this work can contribute to the maritime industry with improved tools and methodologies to account for ship performance during ship operations at sea. By embedding the data-driven models in energy efficiency/safety measures, the ship can be operated wisely, reducing emissions and maintenance costs, extending service life, and enhancing onboard crew/cargo safety.

EcoSail - Eco-friendly and customer-driven Sail plan optimisation service

European Commission (EC) (EC/H2020/820593), 2018-11-01 -- 2021-04-30.

How do you realize the most energy-efficient ship trip in practice?

Swedish Transport Administration, 2020-10-01 -- 2022-09-30.

AI-enhanced energy efficiency measures for optimal ship operations to reduce GHG emissions

VINNOVA (2021-02768), 2021-10-15 -- 2024-06-30.

Driving Forces

Sustainable development

Areas of Advance

Transport

Subject Categories

Transport Systems and Logistics

Marine Engineering

Signal Processing

ISBN

978-91-7905-794-7

Doktorsavhandlingar vid Chalmers tekniska högskola. Ny serie: 5260

Publisher

Chalmers

Lecture hall KB in the Kemi building, Chalmers University of Technology, Kemigården 4, Göteborg.

Online

Opponent: Professor Giles Thomas, University College London (UCL), London, UK.

More information

Latest update

1/25/2023