View in EDS

Supercritical carbon dioxide critical flow model based on a physics-informed neural network.

Saved in:
Bibliographic Details
Title: Supercritical carbon dioxide critical flow model based on a physics-informed neural network.
Authors: Chen, Tiansheng1 (AUTHOR), Kang, Yanjie1 (AUTHOR), Yan, Pengbo1 (AUTHOR), Yuan, Yuan1 (AUTHOR) yuanyuan21@scu.edu.cn, Feng, Haoyang1 (AUTHOR), Wang, Junhao1 (AUTHOR), Zhai, Houzhong1 (AUTHOR), Zha, Yuting1 (AUTHOR), Zhou, Yuan1 (AUTHOR), Tian, Gengyuan1 (AUTHOR), Wang, Yangle1 (AUTHOR)
Source: Energy. Dec2024, Vol. 313, pN.PAG-N.PAG. 1p.
Subjects: Recurrent neural networks, Problem solving, Generalization, Data modeling
Abstract: The venting of supercritical carbon dioxide (SCO2) involves trans-critical depressurization and multiphase phenomena, challenging the development of accurate and efficient critical flow models with limited data. Physics-informed Neural Networks (PINNs) incorporate physical constraints to solve complex problems with sparse data while retaining the efficiency of traditional neural networks. However, their application to SCO2 critical flow prediction remains unexplored, and an effective constraint paradigm is undefined. This study develops a high-precision PINN model for SCO2 critical flow prediction within an optimized physical constraint framework. Starting with a purely data-driven Recurrent Neural Network (RNN) model, the study examines two physical constraint types (P1 and P2) and different integration methods: embedding constraints in the loss function as soft constraints (M1) and incorporating them into the grid structure as hard constraints (M2). The optimal paradigm is identified by evaluating generalization, interpretability, and efficiency across datasets. The best PINN model, M1P1, reduces average prediction error by 48.67 %, 19.48 %, and 22.82 % compared to numerical, empirical, and data-driven models, respectively. M1P1 maintains comparable computational efficiency to empirical and data-driven models while surpassing numerical methods by four orders of magnitude, offering a precise and efficient SCO2 critical flow solution based on sparse data. • A high-precision and efficient critical flow model for SCO2 was developed using PINNs for the first time. • The effects of two physical constraint types, along with soft and hard constraints, on model accuracy were examined. • An optimal paradigm for constructing the SCO2 critical flow model was proposed. • The PINN model outperformed existing models in terms of generalization and interpretability. [ABSTRACT FROM AUTHOR]
Copyright of Energy is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 181726487
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Supercritical carbon dioxide critical flow model based on a physics-informed neural network.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Chen%2C+Tiansheng%22">Chen, Tiansheng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Kang%2C+Yanjie%22">Kang, Yanjie</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yan%2C+Pengbo%22">Yan, Pengbo</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yuan%2C+Yuan%22">Yuan, Yuan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> yuanyuan21@scu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Feng%2C+Haoyang%22">Feng, Haoyang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Junhao%22">Wang, Junhao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhai%2C+Houzhong%22">Zhai, Houzhong</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zha%2C+Yuting%22">Zha, Yuting</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhou%2C+Yuan%22">Zhou, Yuan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Tian%2C+Gengyuan%22">Tian, Gengyuan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Yangle%22">Wang, Yangle</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Energy%22">Energy</searchLink>. Dec2024, Vol. 313, pN.PAG-N.PAG. 1p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Recurrent+neural+networks%22">Recurrent neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Problem+solving%22">Problem solving</searchLink><br /><searchLink fieldCode="DE" term="%22Generalization%22">Generalization</searchLink><br /><searchLink fieldCode="DE" term="%22Data+modeling%22">Data modeling</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The venting of supercritical carbon dioxide (SCO2) involves trans-critical depressurization and multiphase phenomena, challenging the development of accurate and efficient critical flow models with limited data. Physics-informed Neural Networks (PINNs) incorporate physical constraints to solve complex problems with sparse data while retaining the efficiency of traditional neural networks. However, their application to SCO2 critical flow prediction remains unexplored, and an effective constraint paradigm is undefined. This study develops a high-precision PINN model for SCO2 critical flow prediction within an optimized physical constraint framework. Starting with a purely data-driven Recurrent Neural Network (RNN) model, the study examines two physical constraint types (P1 and P2) and different integration methods: embedding constraints in the loss function as soft constraints (M1) and incorporating them into the grid structure as hard constraints (M2). The optimal paradigm is identified by evaluating generalization, interpretability, and efficiency across datasets. The best PINN model, M1P1, reduces average prediction error by 48.67 %, 19.48 %, and 22.82 % compared to numerical, empirical, and data-driven models, respectively. M1P1 maintains comparable computational efficiency to empirical and data-driven models while surpassing numerical methods by four orders of magnitude, offering a precise and efficient SCO2 critical flow solution based on sparse data. • A high-precision and efficient critical flow model for SCO2 was developed using PINNs for the first time. • The effects of two physical constraint types, along with soft and hard constraints, on model accuracy were examined. • An optimal paradigm for constructing the SCO2 critical flow model was proposed. • The PINN model outperformed existing models in terms of generalization and interpretability. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Energy is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=181726487
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.energy.2024.133863
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 1
        StartPage: N.PAG
    Subjects:
      – SubjectFull: Recurrent neural networks
        Type: general
      – SubjectFull: Problem solving
        Type: general
      – SubjectFull: Generalization
        Type: general
      – SubjectFull: Data modeling
        Type: general
    Titles:
      – TitleFull: Supercritical carbon dioxide critical flow model based on a physics-informed neural network.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Chen, Tiansheng
      – PersonEntity:
          Name:
            NameFull: Kang, Yanjie
      – PersonEntity:
          Name:
            NameFull: Yan, Pengbo
      – PersonEntity:
          Name:
            NameFull: Yuan, Yuan
      – PersonEntity:
          Name:
            NameFull: Feng, Haoyang
      – PersonEntity:
          Name:
            NameFull: Wang, Junhao
      – PersonEntity:
          Name:
            NameFull: Zhai, Houzhong
      – PersonEntity:
          Name:
            NameFull: Zha, Yuting
      – PersonEntity:
          Name:
            NameFull: Zhou, Yuan
      – PersonEntity:
          Name:
            NameFull: Tian, Gengyuan
      – PersonEntity:
          Name:
            NameFull: Wang, Yangle
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 30
              M: 12
              Text: Dec2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 03605442
          Numbering:
            – Type: volume
              Value: 313
          Titles:
            – TitleFull: Energy
              Type: main
ResultId 1