Ship Performance Monitoring using Machine-learning

@article{Gupta2021ShipPM,
  title={Ship Performance Monitoring using Machine-learning},
  author={Prateek Gupta and Adil Rasheed and Sverre Steen},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.03594}
}

Data Processing Framework for Ship Performance Analysis

Ship’s hydrodynamic performance can be assessed using the data from ship-in-service, and a standardized data processing framework for preparing the data is developed.

Towards Improved Prediction of Ship Performance: A Comparative Analysis on In-service Ship Monitoring Data for Modeling the Speed-Power Relation

In-service monitoring data from multiple vessels with different hull shapes is used to compare the accuracy of data-driven machine learning algorithms to traditional methods for assessing ship performance, and shows that a simple neural network outperformed established semi-empirical formulas following first principles.

References

SHOWING 1-10 OF 42 REFERENCES

Using a Ship's Propeller for Hull Condition Monitoring

As a ship’s hull condition degrades due to marine fouling, more power and fuel are needed to maintain service speeds. A by-product of the increased fuel consumption is increased Green House Gas

Fuel Conservation through Managing Hull Resistance

There are many good reasons for reducing marine fuel oil consumption. First and foremost is that fuel prices are rising beyond what analysts have predicted as recently as a year ago ($315 USD per ton

New approach to monitoring hull condition of ships as objective for selecting optimal docking period

Proposed approach to data analysis as well as calculation of energy efficiencies losses, caused by hull and propeller fouling, can be used as an acceptable method for shipping companies to make decision on the most optimal docking period.

Modeling of Ship Propulsion Performance

Full scale measurements of the propulsion power, ship speed, wind speed and direction, sea and air temperature, from four different loading conditions has been used to train a neural network for

Big Data Analytics As a Tool to Monitor Hydrodynamic Performance of a Ship

This paper presents a simple data processing framework based on big data analytics that uses Principal Component Analysis (PCA) as a tool to process data gathered through in-service measurements onboard a ship during various operational conditions.