Academic Journal
View in EDS

Surrogate modeling based on computational fluid dynamics for predicting the capsizing moment in a coupled shiplift system.

Bibliographic Details
Title: Surrogate modeling based on computational fluid dynamics for predicting the capsizing moment in a coupled shiplift system.
Authors: Tang T; Institute of Engineering and Technology, Hubei University of Science and Technology, Xianning, People's Republic of China., Yang J; Institute of Engineering and Technology, Hubei University of Science and Technology, Xianning, People's Republic of China., Hu Z; Institute of Engineering and Technology, Hubei University of Science and Technology, Xianning, People's Republic of China., You J; Institute of Engineering and Technology, Hubei University of Science and Technology, Xianning, People's Republic of China., Zhang Y; Institute of Engineering and Technology, Hubei University of Science and Technology, Xianning, People's Republic of China., Shi D; College of International Business and Economics, Wuhan Textile University, Wuhan, China.
Source: PloS one [PLoS One] 2026 Sep 11; Vol. 21 (9), pp. e0358034. Date of Electronic Publication: 2026 Sep 11 (Print Publication: 2026).
Publication Type: Journal Article
Language: English
Journal Info: Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE
Imprint Name(s): Original Publication: San Francisco, CA : Public Library of Science
MeSH Terms: Hydrodynamics* , Computer Simulation* , Ships* , Models, Theoretical*
Abstract: Accurate prediction of the capsizing moment in shiplift systems remains a significant challenge, primarily due to the strong coupled interactions among the chamber, water body, and ship. Conventional three-dimensional (3D) numerical simulations are associated with high computational costs, while commonly used two-dimensional (2D) simplified models neglect ship effects, potentially leading to underestimation of the actual capsizing moment. In this study, a computational fluid dynamics (CFD)-informed surrogate model is developed for one-step-ahead prediction of capsizing moment in a coupled chamber-water-ship shiplift system. First, 3D models covering 19 scales are established, and the corresponding capsizing moments are obtained via CFD simulations. The CFD methodology is further validated against published smoothed particle hydrodynamics (SPH) results, with a maximum deviation of 4.1%, demonstrating the capability of the numerical framework to capture the relevant hydrodynamic responses. Furthermore, under El-Centro excitation, the peak capsizing moments predicted by the 3D model are substantially higher than those obtained using the conventional 2D simplified model for both the 3000 t light-load and 1350 t full-load conditions, indicating that 2D simplification may underestimate the capsizing moment in the examined cases and that three-dimensional effects should be considered when evaluating extreme responses. Based on the numerically generated CFD dataset, a hybrid surrogate framework is constructed, integrating convolutional neural networks, bidirectional long short-term memory networks, and random forests. To enhance the predictive robustness of the framework, multi-window isolation forest preprocessing, CNN-based feature enhancement, and parameter tuning based on the Mapping Mountain Gazelle Optimizer are employed. Comparisons with seven benchmark models demonstrate that the proposed model achieves the better overall predictive performance, with a mean absolute error of 0.0761 ± 0.0024, a root mean squared error of 0.1408 ± 0.0128, and a coefficient of determination of 0.9466 ± 0.0065 on the test set. Additional engineering cases indicate good generalization under ship-presence operating conditions, with peak prediction deviations below 4.8%. These results suggest that, when current and recent response states are available from monitoring or state-estimation systems, the proposed framework may support short-horizon capsizing-moment estimation.
(Copyright: © 2026 Tang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
Competing Interests: The authors have declared that no competing interests exist.
References: Proc Math Phys Eng Sci. 2021 Jan;477(2245):20190897. (PMID: 33642920)
Sci Rep. 2025 Apr 24;15(1):14372. (PMID: 40274930)
Front Neurosci. 2024 Apr 04;18:1379495. (PMID: 38638692)
PLoS One. 2025 Oct 16;20(10):e0334494. (PMID: 41100480)
Sci Rep. 2025 Feb 22;15(1):6447. (PMID: 39987282)
Entry Date(s): Date Created: 20260911 Date Completed: 20260911 Latest Revision: 20260914
Update Code: 20260914
PubMed Central ID: PMC13567811
DOI: 10.1371/journal.pone.0358034
PMID: 42726757
Database: MEDLINE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:cmedm&genre=article&issn=19326203&ISBN=&volume=21&issue=9&date=20260911&spage=e0358034&pages=e0358034&title=PloS one&atitle=Surrogate%20modeling%20based%20on%20computational%20fluid%20dynamics%20for%20predicting%20the%20capsizing%20moment%20in%20a%20coupled%20shiplift%20system.&aulast=Tang%20T&id=DOI:10.1371/journal.pone.0358034
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: cmedm
DbLabel: MEDLINE
An: 42726757
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Surrogate modeling based on computational fluid dynamics for predicting the capsizing moment in a coupled shiplift system.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Tang+T%22">Tang T</searchLink>; Institute of Engineering and Technology, Hubei University of Science and Technology, Xianning, People's Republic of China.<br /><searchLink fieldCode="AU" term="%22Yang+J%22">Yang J</searchLink>; Institute of Engineering and Technology, Hubei University of Science and Technology, Xianning, People's Republic of China.<br /><searchLink fieldCode="AU" term="%22Hu+Z%22">Hu Z</searchLink>; Institute of Engineering and Technology, Hubei University of Science and Technology, Xianning, People's Republic of China.<br /><searchLink fieldCode="AU" term="%22You+J%22">You J</searchLink>; Institute of Engineering and Technology, Hubei University of Science and Technology, Xianning, People's Republic of China.<br /><searchLink fieldCode="AU" term="%22Zhang+Y%22">Zhang Y</searchLink>; Institute of Engineering and Technology, Hubei University of Science and Technology, Xianning, People's Republic of China.<br /><searchLink fieldCode="AU" term="%22Shi+D%22">Shi D</searchLink>; College of International Business and Economics, Wuhan Textile University, Wuhan, China.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22101285081%22">PloS one</searchLink> [PLoS One] 2026 Sep 11; Vol. 21 (9), pp. e0358034. <i>Date of Electronic Publication: </i>2026 Sep 11 (<i>Print Publication: </i>2026).
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22Public+Library+of+Science%22">Public Library of Science </searchLink><i>Country of Publication: </i>United States <i>NLM ID: </i>101285081 <i>Publication Model: </i>eCollection <i>Cited Medium: </i>Internet <i>ISSN: </i>1932-6203 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2219326203%22">19326203 </searchLink><i>NLM ISO Abbreviation: </i>PLoS One <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Original Publication</i>: San Francisco, CA : Public Library of Science
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Hydrodynamics%22">Hydrodynamics*</searchLink> <br /><searchLink fieldCode="MM" term="%22Computer+Simulation%22">Computer Simulation*</searchLink> <br /><searchLink fieldCode="MM" term="%22Ships%22">Ships*</searchLink> <br /><searchLink fieldCode="MM" term="%22Models%2C+Theoretical%22">Models, Theoretical*</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Accurate prediction of the capsizing moment in shiplift systems remains a significant challenge, primarily due to the strong coupled interactions among the chamber, water body, and ship. Conventional three-dimensional (3D) numerical simulations are associated with high computational costs, while commonly used two-dimensional (2D) simplified models neglect ship effects, potentially leading to underestimation of the actual capsizing moment. In this study, a computational fluid dynamics (CFD)-informed surrogate model is developed for one-step-ahead prediction of capsizing moment in a coupled chamber-water-ship shiplift system. First, 3D models covering 19 scales are established, and the corresponding capsizing moments are obtained via CFD simulations. The CFD methodology is further validated against published smoothed particle hydrodynamics (SPH) results, with a maximum deviation of 4.1%, demonstrating the capability of the numerical framework to capture the relevant hydrodynamic responses. Furthermore, under El-Centro excitation, the peak capsizing moments predicted by the 3D model are substantially higher than those obtained using the conventional 2D simplified model for both the 3000 t light-load and 1350 t full-load conditions, indicating that 2D simplification may underestimate the capsizing moment in the examined cases and that three-dimensional effects should be considered when evaluating extreme responses. Based on the numerically generated CFD dataset, a hybrid surrogate framework is constructed, integrating convolutional neural networks, bidirectional long short-term memory networks, and random forests. To enhance the predictive robustness of the framework, multi-window isolation forest preprocessing, CNN-based feature enhancement, and parameter tuning based on the Mapping Mountain Gazelle Optimizer are employed. Comparisons with seven benchmark models demonstrate that the proposed model achieves the better overall predictive performance, with a mean absolute error of 0.0761 ± 0.0024, a root mean squared error of 0.1408 ± 0.0128, and a coefficient of determination of 0.9466 ± 0.0065 on the test set. Additional engineering cases indicate good generalization under ship-presence operating conditions, with peak prediction deviations below 4.8%. These results suggest that, when current and recent response states are available from monitoring or state-estimation systems, the proposed framework may support short-horizon capsizing-moment estimation.<br /> (Copyright: © 2026 Tang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
– Name: Abstract
  Label: Competing Interests
  Group: Ab
  Data: The authors have declared that no competing interests exist.
– Name: Ref
  Label: References
  Group: RefInfo
  Data: Proc Math Phys Eng Sci. 2021 Jan;477(2245):20190897. (PMID: <searchLink fieldCode="PM" term="%2233642920%22">33642920)</searchLink><br />Sci Rep. 2025 Apr 24;15(1):14372. (PMID: <searchLink fieldCode="PM" term="%2240274930%22">40274930)</searchLink><br />Front Neurosci. 2024 Apr 04;18:1379495. (PMID: <searchLink fieldCode="PM" term="%2238638692%22">38638692)</searchLink><br />PLoS One. 2025 Oct 16;20(10):e0334494. (PMID: <searchLink fieldCode="PM" term="%2241100480%22">41100480)</searchLink><br />Sci Rep. 2025 Feb 22;15(1):6447. (PMID: <searchLink fieldCode="PM" term="%2239987282%22">39987282)</searchLink>
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260911 <i>Date Completed: </i>20260911 <i>Latest Revision: </i>20260914
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260914
– Name: PubmedCentralID
  Label: PubMed Central ID
  Group: ID
  Data: PMC13567811
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1371/journal.pone.0358034
– Name: AN
  Label: PMID
  Group: ID
  Data: 42726757
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42726757
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1371/journal.pone.0358034
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: e0358034
    Subjects:
      – SubjectFull: Hydrodynamics
        Type: general
      – SubjectFull: Computer Simulation
        Type: general
      – SubjectFull: Ships
        Type: general
      – SubjectFull: Models, Theoretical
        Type: general
    Titles:
      – TitleFull: Surrogate modeling based on computational fluid dynamics for predicting the capsizing moment in a coupled shiplift system.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Tang T
      – PersonEntity:
          Name:
            NameFull: Yang J
      – PersonEntity:
          Name:
            NameFull: Hu Z
      – PersonEntity:
          Name:
            NameFull: You J
      – PersonEntity:
          Name:
            NameFull: Zhang Y
      – PersonEntity:
          Name:
            NameFull: Shi D
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 11
              M: 09
              Text: 2026 Sep 11
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1932-6203
          Numbering:
            – Type: volume
              Value: 21
            – Type: issue
              Value: 9
          Titles:
            – TitleFull: PloS one
              Type: main
ResultId 1