Physics-Informed Machine Learning for Vessel Shaft Power and Fuel Consumption Prediction: Interpretable KAN-based Approach

• URL: http://arxiv.org/abs/2602.22055v1
• Date: Wed, 25 Feb 2026 16:06:28 GMT
• Title: Physics-Informed Machine Learning for Vessel Shaft Power and Fuel Consumption Prediction: Interpretable KAN-based Approach
• Authors: Hamza Haruna Mohammed, Dusica Marijan, Arnbjørn Maressa,
• Abstract summary: This paper introduces a Physics-Informed Kolmogorov-Arnold Network (PI-KAN) to predict shaft rotational speed, shaft power, and fuel consumption.<n>Using operational environmental data from five cargo vessels, PI-KAN consistently outperforms the traditional prediction method and neural network baselines.<n>These results demonstrate that PI-KAN achieves both predictive accuracy and interpretability, offering a robust tool for vessel performance monitoring and decision support in operational settings.
• Score: 1.1470070927586018
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate prediction of shaft rotational speed, shaft power, and fuel consumption is crucial for enhancing operational efficiency and sustainability in maritime transportation. Conventional physics-based models provide interpretability but struggle with real-world variability, while purely data-driven approaches achieve accuracy at the expense of physical plausibility. This paper introduces a Physics-Informed Kolmogorov-Arnold Network (PI-KAN), a hybrid method that integrates interpretable univariate feature transformations with a physics-informed loss function and a leakage-free chained prediction pipeline. Using operational and environmental data from five cargo vessels, PI-KAN consistently outperforms the traditional polynomial method and neural network baselines. The model achieves the lowest mean absolute error (MAE) and root mean squared error (RMSE), and the highest coefficient of determination (R^2) for shaft power and fuel consumption across all vessels, while maintaining physically consistent behavior. Interpretability analysis reveals rediscovery of domain-consistent dependencies, such as cubic-like speed-power relationships and cosine-like wave and wind effects. These results demonstrate that PI-KAN achieves both predictive accuracy and interpretability, offering a robust tool for vessel performance monitoring and decision support in operational settings.

Related papers

• Scientific Knowledge-Guided Machine Learning for Vessel Power Prediction: A Comparative Study [0.0]
  This study introduces a hybrid modeling framework that integrates physics-based knowledge from sea trials with data-driven residual learning.<n>The proposed framework provides a practical and computationally efficient tool for vessel performance monitoring, with applications in weather routing, trim optimization, and energy efficiency planning.
  arXiv  Detail & Related papers  (2026-02-20T18:12:14Z)
• FuelCast: Benchmarking Tabular and Temporal Models for Ship Fuel Consumption [40.66746563566378]
  In the shipping industry, fuel consumption and emissions are critical factors due to their significant impact on economic efficiency and environmental sustainability.<n> Accurate prediction of ship fuel consumption is essential for further optimization of maritime operations.
  arXiv  Detail & Related papers  (2025-10-09T13:38:46Z)
• CausalKANs: interpretable treatment effect estimation with Kolmogorov-Arnold networks [42.852654951995426]
  causalKANs is a framework that transforms neural estimators of conditional average treatment effects (CATEs) into Kolmogorov--Arnold Networks (KANs)<n>By incorporating pruning and symbolic simplification, causalKANs yields interpretable closed-form formulas while preserving predictive accuracy.
  arXiv  Detail & Related papers  (2025-09-26T15:16:06Z)
• From Physics to Machine Learning and Back: Part II - Learning and Observational Bias in PHM [52.64097278841485]
  Review examines how incorporating learning and observational biases through physics-informed modeling and data strategies can guide models toward physically consistent and reliable predictions.<n>Fast adaptation methods including meta-learning and few-shot learning are reviewed alongside domain generalization techniques.
  arXiv  Detail & Related papers  (2025-09-25T14:15:43Z)
• Physics-Informed Multimodal Bearing Fault Classification under Variable Operating Conditions using Transfer Learning [0.46085106405479537]
  This study proposes a physics-informed multimodal convolutional neural network (CNN) with a late fusion architecture.<n>The model incorporates a novel physics-informed loss function that penalizes physically implausible predictions.<n>Experiments on the Paderborn University dataset demonstrate that the proposed physics-informed approach consistently outperforms a non-physics-informed baseline.
  arXiv  Detail & Related papers  (2025-08-11T01:32:09Z)
• Learnable-Differentiable Finite Volume Solver for Accelerated Simulation of Flows [40.06403338393609]
  We propose a learnable and differentiable finite volume solver, called LDr, for efficient and accurate simulation of fluid flows on coarse grids.<n>Experiments show that LDr achieves efficiency, surpassing baseline models with notable margins.
  arXiv  Detail & Related papers  (2025-06-23T14:22:27Z)
• Physics-Informed Neural Networks for Vessel Trajectory Prediction: Learning Time-Discretized Kinematic Dynamics via Finite Differences [1.740114131842074]
  Accurate vessel trajectory prediction is crucial for navigational safety, route optimization, traffic management, search and rescue operations, and autonomous navigation.<n>Traditional data-driven models lack real-world physical constraints, leading to forecasts that disobey vessel motion dynamics.<n>We propose a Physics-Informed Neural Network (PINN) approach for trajectory prediction that integrates a streamlined kinematic model for vessel motion into the neural network training process.
  arXiv  Detail & Related papers  (2025-05-22T15:09:25Z)
• Towards Precision in Bolted Joint Design: A Preliminary Machine Learning-Based Parameter Prediction [0.0]
  Bolted joints are critical in engineering for maintaining structural integrity and reliability.<n>Traditional methods often fail to capture the non-linear behavior of bolted joints.<n>This study combines empirical data with a feed-forward neural network to predict load capacity and friction coefficients.
  arXiv  Detail & Related papers  (2024-12-11T11:00:39Z)
• Physics-guided Active Sample Reweighting for Urban Flow Prediction [75.24539704456791]
  Urban flow prediction is a nuanced-temporal modeling that estimates the throughput of transportation services like buses, taxis and ride-driven models. Some recent prediction solutions bring remedies with the notion of physics-guided machine learning (PGML) We develop a atized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR)
  arXiv  Detail & Related papers  (2024-07-18T15:44:23Z)
• Towards Improved Prediction of Ship Performance: A Comparative Analysis on In-service Ship Monitoring Data for Modeling the Speed-Power Relation [0.0]
  We compare the accuracy of data-driven machine learning algorithms to traditional methods for assessing ship performance. Our results showed that a simple neural network outperformed established semi-empirical formulas following first principles. These findings suggest that data-driven algorithms may be more effective for predicting ship performance in practical applications.
  arXiv  Detail & Related papers  (2022-12-26T09:39:33Z)
• Probabilistic electric load forecasting through Bayesian Mixture Density Networks [70.50488907591463]
  Probabilistic load forecasting (PLF) is a key component in the extended tool-chain required for efficient management of smart energy grids. We propose a novel PLF approach, framed on Bayesian Mixture Density Networks. To achieve reliable and computationally scalable estimators of the posterior distributions, both Mean Field variational inference and deep ensembles are integrated.
  arXiv  Detail & Related papers  (2020-12-23T16:21:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.