View in EDS

Novel deep learning-based evaluation of neutron resonance cross sections.

Saved in:
Bibliographic Details
Title: Novel deep learning-based evaluation of neutron resonance cross sections.
Authors: Hu, Ze-Hua1 (AUTHOR) hu_zehua@iapcm.ac.cn, Xu, Rui-Rui2 (AUTHOR), Shang-Guan, Dan-Hua1 (AUTHOR), Ying, Yang-Jun1 (AUTHOR), Yong, Heng1 (AUTHOR) yong_heng@iapcm.ac.cn, Xing, Kang2 (AUTHOR), Sun, Xiao-Jun3 (AUTHOR)
Source: Physics Letters B. Oct2024, Vol. 857, pN.PAG-N.PAG. 1p.
Subjects: Artificial neural networks, Neutron resonance, Nuclear cross sections, Deep learning, Nuclear science
Abstract: Neutron resonance cross sections are essential in many nuclear science fields and applications. However, their evaluation and application are extremely complicated. Additionally, the high-frequency, super-wide spectral range of these cross sections cannot be readily approximated by a deep neural network (DNN). To address this issue, we propose a single phase-shift DNN (SPDNN) in which a phase-shift layer is added to a conventional DNN before the output layer to enable wideband processing. Compared with multinetwork algorithms, SPDNN represents a more compact and efficient network, with far fewer parameters. The proposed SPDNN is used to learn the neutron resonance cross sections of 235U fission from the evaluated and experimental libraries, and the results demonstrate its capability as an easy-to-implement, efficient method for approximating the evaluated resonance cross sections and evaluating the experimental data. This study represents the first application of deep learning to the evaluation of highly complex neutron resonance cross sections by adapting DNN. [ABSTRACT FROM AUTHOR]
Copyright of Physics Letters B is the property of Elsevier B.V. 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: 179630111
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Novel deep learning-based evaluation of neutron resonance cross sections.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Hu%2C+Ze-Hua%22">Hu, Ze-Hua</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> hu_zehua@iapcm.ac.cn</i><br /><searchLink fieldCode="AR" term="%22Xu%2C+Rui-Rui%22">Xu, Rui-Rui</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Shang-Guan%2C+Dan-Hua%22">Shang-Guan, Dan-Hua</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ying%2C+Yang-Jun%22">Ying, Yang-Jun</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yong%2C+Heng%22">Yong, Heng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> yong_heng@iapcm.ac.cn</i><br /><searchLink fieldCode="AR" term="%22Xing%2C+Kang%22">Xing, Kang</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sun%2C+Xiao-Jun%22">Sun, Xiao-Jun</searchLink><relatesTo>3</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Physics+Letters+B%22">Physics Letters B</searchLink>. Oct2024, Vol. 857, pN.PAG-N.PAG. 1p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Neutron+resonance%22">Neutron resonance</searchLink><br /><searchLink fieldCode="DE" term="%22Nuclear+cross+sections%22">Nuclear cross sections</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Nuclear+science%22">Nuclear science</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Neutron resonance cross sections are essential in many nuclear science fields and applications. However, their evaluation and application are extremely complicated. Additionally, the high-frequency, super-wide spectral range of these cross sections cannot be readily approximated by a deep neural network (DNN). To address this issue, we propose a single phase-shift DNN (SPDNN) in which a phase-shift layer is added to a conventional DNN before the output layer to enable wideband processing. Compared with multinetwork algorithms, SPDNN represents a more compact and efficient network, with far fewer parameters. The proposed SPDNN is used to learn the neutron resonance cross sections of 235U fission from the evaluated and experimental libraries, and the results demonstrate its capability as an easy-to-implement, efficient method for approximating the evaluated resonance cross sections and evaluating the experimental data. This study represents the first application of deep learning to the evaluation of highly complex neutron resonance cross sections by adapting DNN. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Physics Letters B is the property of Elsevier B.V. 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=179630111
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.physletb.2024.138978
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 1
        StartPage: N.PAG
    Subjects:
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Neutron resonance
        Type: general
      – SubjectFull: Nuclear cross sections
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Nuclear science
        Type: general
    Titles:
      – TitleFull: Novel deep learning-based evaluation of neutron resonance cross sections.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Hu, Ze-Hua
      – PersonEntity:
          Name:
            NameFull: Xu, Rui-Rui
      – PersonEntity:
          Name:
            NameFull: Shang-Guan, Dan-Hua
      – PersonEntity:
          Name:
            NameFull: Ying, Yang-Jun
      – PersonEntity:
          Name:
            NameFull: Yong, Heng
      – PersonEntity:
          Name:
            NameFull: Xing, Kang
      – PersonEntity:
          Name:
            NameFull: Sun, Xiao-Jun
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: Oct2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 03702693
          Numbering:
            – Type: volume
              Value: 857
          Titles:
            – TitleFull: Physics Letters B
              Type: main
ResultId 1