Academic Journal
View in EDS

An intelligent prediction method of gas concentration in coal mines based onimproved TCN-TimeGAN

Bibliographic Details
Title: An intelligent prediction method of gas concentration in coal mines based onimproved TCN-TimeGAN
Authors: Qingsong HU, Shuo ZHENG, Shiyin LI, Yanjing SUN
Source: Meitan kexue jishu, Vol 52, Iss S2, Pp 321-330 (2024)
Publisher Information: Editorial Department of Coal Science and Technology, 2024.
Publication Year: 2024
Collection: LCC:Mining engineering. Metallurgy
Subject Terms: gas concentration prediction, timegan, deep learning, artificial intelligence, coal mine intellectualization, Mining engineering. Metallurgy, TN1-997
More Details: The prediction of gas concentration is of great importantance to ensure the safety of mine production. The gas concentration data has the characteristics of small sample size and time dependence, and traditional machine learning methods are not effective. A time convolution improved time series Generative adversarial network (TCN-TimeGAN) is proposed. Based on the characteristics of generative adversarial network (GAN), the problem of over-fitting of small samples of gas data is improved, and the receptive field is enlarged based on TCN network to read long-term dimension features. In the design of loss function, Wasserstein distance is used to measure the distribution of gas data, and the gradient penalty term of adaptive weight is added to the identification network loss function, so as to solve the problems of data irregularity and gradient disappearance, and improve training stability and prediction accuracy. When conducting model training, the first step is to normalize the gas time series and process missing data values. The processing results are used as input sequences of the embedding network and recovery network to reduce reconstruction loss. Subsequently, the input sequences are also input into the supervised network to reduce supervision loss. Finally, joint training is conducted, and the total loss is the sum of the generated network loss and the discriminative network loss. The experiment results show that the data generated by the proposed model can cover the original data distribution more comprehensively, and the mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAE) of the results predicted from the generated data by the improved model are much smaller than those of the comparison model, and the prediction can be stable and accurate in all time periods.
Document Type: article
File Description: electronic resource
Language: Chinese
ISSN: 0253-2336
Relation: https://doaj.org/toc/0253-2336
DOI: 10.12438/cst.2023-1404
Access URL: https://doaj.org/article/33a6b05308e24872bacc9dcd32998f04
Accession Number: edsdoj.33a6b05308e24872bacc9dcd32998f04
Database: Directory of Open Access Journals
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsdoj&genre=article&issn=02532336&ISBN=&volume=52&issue=S2&date=20241201&spage=321&pages=321-330&title=Meitan kexue jishu&atitle=An%20intelligent%20prediction%20method%20of%20gas%20concentration%20in%20coal%20mines%20based%20onimproved%20TCN-TimeGAN&aulast=Qingsong%20HU&id=DOI:10.12438/cst.2023-1404
    Name: Full Text Finder (for New FTF UI) (s8985755)
    Category: fullText
    Text: Find It @ SCU Libraries
    MouseOverText: Find It @ SCU Libraries
  – Url: https://doaj.org/article/33a6b05308e24872bacc9dcd32998f04
    Name: EDS - DOAJ (s8985755)
    Category: fullText
    Text: View record from DOAJ
    MouseOverText: View record from DOAJ
Header DbId: edsdoj
DbLabel: Directory of Open Access Journals
An: edsdoj.33a6b05308e24872bacc9dcd32998f04
RelevancyScore: 1063
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1063.04321289063
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: An intelligent prediction method of gas concentration in coal mines based onimproved TCN-TimeGAN
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Qingsong+HU%22">Qingsong HU</searchLink><br /><searchLink fieldCode="AR" term="%22Shuo+ZHENG%22">Shuo ZHENG</searchLink><br /><searchLink fieldCode="AR" term="%22Shiyin+LI%22">Shiyin LI</searchLink><br /><searchLink fieldCode="AR" term="%22Yanjing+SUN%22">Yanjing SUN</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Meitan kexue jishu, Vol 52, Iss S2, Pp 321-330 (2024)
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: Editorial Department of Coal Science and Technology, 2024.
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2024
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: LCC:Mining engineering. Metallurgy
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22gas+concentration+prediction%22">gas concentration prediction</searchLink><br /><searchLink fieldCode="DE" term="%22timegan%22">timegan</searchLink><br /><searchLink fieldCode="DE" term="%22deep+learning%22">deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22artificial+intelligence%22">artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22coal+mine+intellectualization%22">coal mine intellectualization</searchLink><br /><searchLink fieldCode="DE" term="%22Mining+engineering%2E+Metallurgy%22">Mining engineering. Metallurgy</searchLink><br /><searchLink fieldCode="DE" term="%22TN1-997%22">TN1-997</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: The prediction of gas concentration is of great importantance to ensure the safety of mine production. The gas concentration data has the characteristics of small sample size and time dependence, and traditional machine learning methods are not effective. A time convolution improved time series Generative adversarial network (TCN-TimeGAN) is proposed. Based on the characteristics of generative adversarial network (GAN), the problem of over-fitting of small samples of gas data is improved, and the receptive field is enlarged based on TCN network to read long-term dimension features. In the design of loss function, Wasserstein distance is used to measure the distribution of gas data, and the gradient penalty term of adaptive weight is added to the identification network loss function, so as to solve the problems of data irregularity and gradient disappearance, and improve training stability and prediction accuracy. When conducting model training, the first step is to normalize the gas time series and process missing data values. The processing results are used as input sequences of the embedding network and recovery network to reduce reconstruction loss. Subsequently, the input sequences are also input into the supervised network to reduce supervision loss. Finally, joint training is conducted, and the total loss is the sum of the generated network loss and the discriminative network loss. The experiment results show that the data generated by the proposed model can cover the original data distribution more comprehensively, and the mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAE) of the results predicted from the generated data by the improved model are much smaller than those of the comparison model, and the prediction can be stable and accurate in all time periods.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: article
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: electronic resource
– Name: Language
  Label: Language
  Group: Lang
  Data: Chinese
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 0253-2336
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: https://doaj.org/toc/0253-2336
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.12438/cst.2023-1404
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://doaj.org/article/33a6b05308e24872bacc9dcd32998f04" linkWindow="_blank">https://doaj.org/article/33a6b05308e24872bacc9dcd32998f04</link>
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsdoj.33a6b05308e24872bacc9dcd32998f04
PLink https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsdoj&AN=edsdoj.33a6b05308e24872bacc9dcd32998f04
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.12438/cst.2023-1404
    Languages:
      – Text: Chinese
    PhysicalDescription:
      Pagination:
        PageCount: 10
        StartPage: 321
    Subjects:
      – SubjectFull: gas concentration prediction
        Type: general
      – SubjectFull: timegan
        Type: general
      – SubjectFull: deep learning
        Type: general
      – SubjectFull: artificial intelligence
        Type: general
      – SubjectFull: coal mine intellectualization
        Type: general
      – SubjectFull: Mining engineering. Metallurgy
        Type: general
      – SubjectFull: TN1-997
        Type: general
    Titles:
      – TitleFull: An intelligent prediction method of gas concentration in coal mines based onimproved TCN-TimeGAN
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Qingsong HU
      – PersonEntity:
          Name:
            NameFull: Shuo ZHENG
      – PersonEntity:
          Name:
            NameFull: Shiyin LI
      – PersonEntity:
          Name:
            NameFull: Yanjing SUN
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 02532336
          Numbering:
            – Type: volume
              Value: 52
            – Type: issue
              Value: S2
          Titles:
            – TitleFull: Meitan kexue jishu
              Type: main
ResultId 1