Simplifying neural network based model for ship motion prediction: a comparative study of sensitivity analysis
This paper presents a comparative study of sensitivity analysis (SA) and simplification on artificial neural network (ANN) based model used for ship motion prediction. Considering traditional structural complexity of ANN usually results in slow convergence, SA, as an efficient tool for correlation a...
Published in: | Volume 1: Offshore Technology |
---|---|
Main Authors: | , , , , , |
Format: | Book Part |
Language: | English |
Published: |
American Society of Mechanical Engineers (ASME)
2017
|
Subjects: | |
Online Access: | http://hdl.handle.net/11250/2495409 https://doi.org/10.1115/OMAE2017-61474 |
id |
ftntnutrondheimi:oai:ntnuopen.ntnu.no:11250/2495409 |
---|---|
record_format |
openpolar |
spelling |
ftntnutrondheimi:oai:ntnuopen.ntnu.no:11250/2495409 2023-05-15T14:24:03+02:00 Simplifying neural network based model for ship motion prediction: a comparative study of sensitivity analysis Cheng, Xu Chen, Shengyong Diao, Chen Liu, Mengna Li, Guoyuan Zhang, Houxiang 2017 http://hdl.handle.net/11250/2495409 https://doi.org/10.1115/OMAE2017-61474 eng eng American Society of Mechanical Engineers (ASME) ASME 2017 36th International Conference on Ocean, Offshore and Arctic Engineering - Volume 1: Offshore Technology Norges forskningsråd: 256926 urn:isbn:978-0-7918-5763-2 http://hdl.handle.net/11250/2495409 https://doi.org/10.1115/OMAE2017-61474 cristin:1500498 Chapter 2017 ftntnutrondheimi https://doi.org/10.1115/OMAE2017-61474 2019-09-17T06:53:14Z This paper presents a comparative study of sensitivity analysis (SA) and simplification on artificial neural network (ANN) based model used for ship motion prediction. Considering traditional structural complexity of ANN usually results in slow convergence, SA, as an efficient tool for correlation analysis, can help to reconstruct the ANN model for ship motion prediction. An ANN-Garson method and an ANN-EFAST method are proposed, both of which utilize the ANN for modeling but select the input parameters in a local and a global fashion, respectively. Through the benchmark tests, ANN-EFAST exhibits superior performance in both linear and nonlinear systems. Further test on ANN-EFAST via a case study of ship heading prediction shows its cost-effective and timely in compacting the ANN based prediction model. publishedVersion Copyright © 2017 by ASME Book Part Arctic NTNU Open Archive (Norwegian University of Science and Technology) Volume 1: Offshore Technology |
institution |
Open Polar |
collection |
NTNU Open Archive (Norwegian University of Science and Technology) |
op_collection_id |
ftntnutrondheimi |
language |
English |
description |
This paper presents a comparative study of sensitivity analysis (SA) and simplification on artificial neural network (ANN) based model used for ship motion prediction. Considering traditional structural complexity of ANN usually results in slow convergence, SA, as an efficient tool for correlation analysis, can help to reconstruct the ANN model for ship motion prediction. An ANN-Garson method and an ANN-EFAST method are proposed, both of which utilize the ANN for modeling but select the input parameters in a local and a global fashion, respectively. Through the benchmark tests, ANN-EFAST exhibits superior performance in both linear and nonlinear systems. Further test on ANN-EFAST via a case study of ship heading prediction shows its cost-effective and timely in compacting the ANN based prediction model. publishedVersion Copyright © 2017 by ASME |
format |
Book Part |
author |
Cheng, Xu Chen, Shengyong Diao, Chen Liu, Mengna Li, Guoyuan Zhang, Houxiang |
spellingShingle |
Cheng, Xu Chen, Shengyong Diao, Chen Liu, Mengna Li, Guoyuan Zhang, Houxiang Simplifying neural network based model for ship motion prediction: a comparative study of sensitivity analysis |
author_facet |
Cheng, Xu Chen, Shengyong Diao, Chen Liu, Mengna Li, Guoyuan Zhang, Houxiang |
author_sort |
Cheng, Xu |
title |
Simplifying neural network based model for ship motion prediction: a comparative study of sensitivity analysis |
title_short |
Simplifying neural network based model for ship motion prediction: a comparative study of sensitivity analysis |
title_full |
Simplifying neural network based model for ship motion prediction: a comparative study of sensitivity analysis |
title_fullStr |
Simplifying neural network based model for ship motion prediction: a comparative study of sensitivity analysis |
title_full_unstemmed |
Simplifying neural network based model for ship motion prediction: a comparative study of sensitivity analysis |
title_sort |
simplifying neural network based model for ship motion prediction: a comparative study of sensitivity analysis |
publisher |
American Society of Mechanical Engineers (ASME) |
publishDate |
2017 |
url |
http://hdl.handle.net/11250/2495409 https://doi.org/10.1115/OMAE2017-61474 |
genre |
Arctic |
genre_facet |
Arctic |
op_relation |
ASME 2017 36th International Conference on Ocean, Offshore and Arctic Engineering - Volume 1: Offshore Technology Norges forskningsråd: 256926 urn:isbn:978-0-7918-5763-2 http://hdl.handle.net/11250/2495409 https://doi.org/10.1115/OMAE2017-61474 cristin:1500498 |
op_doi |
https://doi.org/10.1115/OMAE2017-61474 |
container_title |
Volume 1: Offshore Technology |
_version_ |
1766296516629102592 |