View in EDS HTML Full Text PDF Full Text

Dynamic Ensemble Learning with Transfer Learning for Fatigue Performance Prediction in Ni-Based Superalloys.

Saved in:
Bibliographic Details
Title: Dynamic Ensemble Learning with Transfer Learning for Fatigue Performance Prediction in Ni-Based Superalloys.
Authors: Yang, Jiaxing1 (AUTHOR), Du, Fenglou1 (AUTHOR), Lv, Haopeng1 (AUTHOR) lwang199110@163.com, Li, Wang1 (AUTHOR), Wu, Dayong1 (AUTHOR) wudayong_ysu@126.com
Source: Materials (1996-1944). Jun2026, Vol. 19 Issue 11, p2371. 18p.
Subjects: Ensemble learning, Knowledge transfer, Materials science, Heat resistant alloys, Machine learning, Fatigue limit, Tensile tests
Abstract: Accurate prediction of fatigue performance in Ni-based superalloys is hindered by scarce data and poor generalization of conventional machine learning. This study proposes a framework combining dynamic ensemble learning with transfer learning. A tensile prediction model using five base regressors (SVR, RFR, DTR, XGB, MLP) on 1025 tensile samples is first built. A dynamic weighted error feedback ensemble algorithm (DWELA) adjusts base model weights in real-time based on validation errors, improving tensile R2 from 0.90 (best single model) to 0.95. To transfer knowledge to fatigue prediction, a feature alignment transfer learning (FATL) strategy aligns shared features (composition and heat treatment) between source (tensile) and target (fatigue) domains while fine-tuning domain-specific strain features, adapting effectively to a limited fatigue dataset of 622 samples. The resulting ETFPM model evaluated on five independent samples achieves R2 of 0.93 (fatigue stress) and 0.81 (fatigue life), outperforming the best fatigue-trained single model (SVR: R2 = 0.89 and 0.72). Twenty candidate alloys are predicted for screening. The method offers a practical route for fatigue prediction under data-limited conditions. The main novelties are: (i) DWELA's real-time error-driven weight adaptation with hard constraints and early stopping, which improves tensile R2 from 0.90 (best single model) to 0.95; and (ii) FATL's explicit separation of frozen shared features and trainable exclusive features, enabling accurate fatigue prediction (R2 = 0.93 for FS, 0.81 for FL) using only 622 fatigue samples. However, the independent validation is limited to five samples, and the datasets are compiled from the literature with potential heterogeneity in testing protocols and imputation bias for missing values. Further experimental validation is required to confirm broader applicability. [ABSTRACT FROM AUTHOR]
Copyright of Materials (1996-1944) is the property of MDPI 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
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 194587282
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Dynamic Ensemble Learning with Transfer Learning for Fatigue Performance Prediction in Ni-Based Superalloys.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Yang%2C+Jiaxing%22">Yang, Jiaxing</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Du%2C+Fenglou%22">Du, Fenglou</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lv%2C+Haopeng%22">Lv, Haopeng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> lwang199110@163.com</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Wang%22">Li, Wang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wu%2C+Dayong%22">Wu, Dayong</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> wudayong_ysu@126.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Materials+%281996-1944%29%22">Materials (1996-1944)</searchLink>. Jun2026, Vol. 19 Issue 11, p2371. 18p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Ensemble+learning%22">Ensemble learning</searchLink><br /><searchLink fieldCode="DE" term="%22Knowledge+transfer%22">Knowledge transfer</searchLink><br /><searchLink fieldCode="DE" term="%22Materials+science%22">Materials science</searchLink><br /><searchLink fieldCode="DE" term="%22Heat+resistant+alloys%22">Heat resistant alloys</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Fatigue+limit%22">Fatigue limit</searchLink><br /><searchLink fieldCode="DE" term="%22Tensile+tests%22">Tensile tests</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Accurate prediction of fatigue performance in Ni-based superalloys is hindered by scarce data and poor generalization of conventional machine learning. This study proposes a framework combining dynamic ensemble learning with transfer learning. A tensile prediction model using five base regressors (SVR, RFR, DTR, XGB, MLP) on 1025 tensile samples is first built. A dynamic weighted error feedback ensemble algorithm (DWELA) adjusts base model weights in real-time based on validation errors, improving tensile R2 from 0.90 (best single model) to 0.95. To transfer knowledge to fatigue prediction, a feature alignment transfer learning (FATL) strategy aligns shared features (composition and heat treatment) between source (tensile) and target (fatigue) domains while fine-tuning domain-specific strain features, adapting effectively to a limited fatigue dataset of 622 samples. The resulting ETFPM model evaluated on five independent samples achieves R2 of 0.93 (fatigue stress) and 0.81 (fatigue life), outperforming the best fatigue-trained single model (SVR: R2 = 0.89 and 0.72). Twenty candidate alloys are predicted for screening. The method offers a practical route for fatigue prediction under data-limited conditions. The main novelties are: (i) DWELA's real-time error-driven weight adaptation with hard constraints and early stopping, which improves tensile R2 from 0.90 (best single model) to 0.95; and (ii) FATL's explicit separation of frozen shared features and trainable exclusive features, enabling accurate fatigue prediction (R2 = 0.93 for FS, 0.81 for FL) using only 622 fatigue samples. However, the independent validation is limited to five samples, and the datasets are compiled from the literature with potential heterogeneity in testing protocols and imputation bias for missing values. Further experimental validation is required to confirm broader applicability. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Materials (1996-1944) is the property of MDPI 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=194587282
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/ma19112371
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 18
        StartPage: 2371
    Subjects:
      – SubjectFull: Ensemble learning
        Type: general
      – SubjectFull: Knowledge transfer
        Type: general
      – SubjectFull: Materials science
        Type: general
      – SubjectFull: Heat resistant alloys
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Fatigue limit
        Type: general
      – SubjectFull: Tensile tests
        Type: general
    Titles:
      – TitleFull: Dynamic Ensemble Learning with Transfer Learning for Fatigue Performance Prediction in Ni-Based Superalloys.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Yang, Jiaxing
      – PersonEntity:
          Name:
            NameFull: Du, Fenglou
      – PersonEntity:
          Name:
            NameFull: Lv, Haopeng
      – PersonEntity:
          Name:
            NameFull: Li, Wang
      – PersonEntity:
          Name:
            NameFull: Wu, Dayong
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 19961944
          Numbering:
            – Type: volume
              Value: 19
            – Type: issue
              Value: 11
          Titles:
            – TitleFull: Materials (1996-1944)
              Type: main
ResultId 1