Efficient vessel power prediction in operational conditions using machine learning
Efficient vessel power prediction in operational conditions using machine learning
It is important to reduce CO 2 emissions. Accurate power prediction of vessels allows evaluation of performance which is essential for this. Neural networks have been shown to accurately predict powering of vessels in weather, which is not straightforward using traditional methods. In previous applications only 6 intuitively relevant variables are used to predict powering with neural networks, including wave height, which is expensive and time consuming to collect. This study investigates the influence of the wave height variable on prediction, concluding that it increases accuracy of prediction by 0.5%. A high frequency dataset from a merchant vessel containing 100 variables is statistically analysed and a maximal subset of variables is derived. This subset is used for principal component analysis, focussing on redundancy. Investigation into the inclusion of non-intuitively relevant variables to increase prediction accuracy for power prediction with a neural network is performed.
power prediction, principal component analysis, artificial neural networks, wave height influence
International Symposium on Practical Design of Ships and Other Floating Structures
Parkes, A.I.
9fbc0481-7bcf-4d15-8474-4df77d4338ef
Savasta, T.D.
8aea0b48-47bd-4504-bbaa-8e130bd3c42d
Sobey, A.J.
e850606f-aa79-4c99-8682-2cfffda3cd28
Hudson, D.A.
3814e08b-1993-4e78-b5a4-2598c40af8e7
September 2019
Parkes, A.I.
9fbc0481-7bcf-4d15-8474-4df77d4338ef
Savasta, T.D.
8aea0b48-47bd-4504-bbaa-8e130bd3c42d
Sobey, A.J.
e850606f-aa79-4c99-8682-2cfffda3cd28
Hudson, D.A.
3814e08b-1993-4e78-b5a4-2598c40af8e7
Parkes, A.I., Savasta, T.D., Sobey, A.J. and Hudson, D.A.
(2019)
Efficient vessel power prediction in operational conditions using machine learning.
In The 14th International Symposium on Practical Design of Ships and Other Floating Structures.
International Symposium on Practical Design of Ships and Other Floating Structures..
Record type:
Conference or Workshop Item
(Paper)
Abstract
It is important to reduce CO 2 emissions. Accurate power prediction of vessels allows evaluation of performance which is essential for this. Neural networks have been shown to accurately predict powering of vessels in weather, which is not straightforward using traditional methods. In previous applications only 6 intuitively relevant variables are used to predict powering with neural networks, including wave height, which is expensive and time consuming to collect. This study investigates the influence of the wave height variable on prediction, concluding that it increases accuracy of prediction by 0.5%. A high frequency dataset from a merchant vessel containing 100 variables is statistically analysed and a maximal subset of variables is derived. This subset is used for principal component analysis, focussing on redundancy. Investigation into the inclusion of non-intuitively relevant variables to increase prediction accuracy for power prediction with a neural network is performed.
Text
EfficientVesselPowerPred
Restricted to Repository staff only
Request a copy
More information
Published date: September 2019
Keywords:
power prediction, principal component analysis, artificial neural networks, wave height influence
Identifiers
Local EPrints ID: 436026
URI: http://eprints.soton.ac.uk/id/eprint/436026
PURE UUID: 13fcb35f-0e7e-4808-83a5-f1fae2d64cd1
Catalogue record
Date deposited: 26 Nov 2019 17:30
Last modified: 14 Mar 2024 02:52
Export record
Contributors
Author:
A.I. Parkes
Author:
T.D. Savasta
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
