<?xml version="1.0" encoding="UTF-8"?>
<ArticleSet>
  <Article>
    <Journal>
      <PublisherName></PublisherName>
      <JournalTitle>Digital Transformation and Administration Innovation</JournalTitle>
      <Issn></Issn>
      <Volume></Volume>
      <Issue>In Press</Issue>
      <PubDate PubStatus="epublish">
        <Year>2027</Year>
        <Month>05</Month>
        <Day>01</Day>
      </PubDate>
    </Journal>
    <ArticleTitle>Identification and Causal Analysis of Artificial Intelligence Capabilities for Advancing Total Productive Maintenance toward World-Class Standards in the Automotive Industry</ArticleTitle>
    <VernacularTitle>Identification and Causal Analysis of Artificial Intelligence Capabilities for Advancing Total Productive Maintenance toward World-Class Standards in the Automotive Industry</VernacularTitle>
    <FirstPage>1</FirstPage>
    <LastPage>17</LastPage>
    <Language>EN</Language>
    <AuthorList>
      <Author>
        <FirstName></FirstName>
        <LastName></LastName>
        <Affiliation></Affiliation>
      </Author>
      <Author>
        <FirstName></FirstName>
        <LastName></LastName>
        <Affiliation></Affiliation>
      </Author>
      <Author>
        <FirstName></FirstName>
        <LastName></LastName>
        <Affiliation></Affiliation>
      </Author>
      <Author>
        <FirstName></FirstName>
        <LastName></LastName>
        <Affiliation></Affiliation>
      </Author>
    </AuthorList>
    <PublicationType>Journal Article</PublicationType>
    <History>
      <PubDate PubStatus="received">
        <Year>2026</Year>
        <Month>07</Month>
        <Day>26</Day>
      </PubDate>
    </History>
    <Abstract>&lt;p&gt;In the era of Industry 5.0, transforming Total Productive Maintenance (TPM) in the automotive industry requires moving beyond reactive and experience-based maintenance toward a data-driven, predictive, and artificial intelligence-based system. Although research on intelligent maintenance has expanded considerably, much of the existing literature focuses on isolated algorithms, prediction accuracy, or narrow technological applications, while insufficient attention has been paid to identifying which AI capabilities are valid for enabling World-Class TPM and how they operate within a causal influence network. This study aims to identify, validate, and causally analyze artificial intelligence capabilities for World-Class TPM in the automotive industry. First, initial capabilities were extracted through thematic analysis of expert data. A single-round fuzzy Delphi method, was then applied to screen and stabilize the core capabilities, while expert consensus was controlled through fuzzy distance, consensus percentage, and alpha-cut criteria. The AI tools corresponding to the selected capabilities were conceptually validated based on the literature. Finally, fuzzy DEMATEL was used to analyze the intensity and direction of causal relationships. The findings show that 9 out of 20 initial capabilities were stabilized as core AI capabilities. Dynamic failure prediction, preventive quality control, resilient supply chain, and intelligent continuous improvement emerged as the strongest causal and leverage capabilities. The study contributes by providing a validated and causally analyzed set of AI capabilities that can support managerial decision-making for prioritizing World-Class TPM investments in the automotive industry.&lt;/p&gt;</Abstract>
    <ObjectList>
      <Object Type="keyword">
        <Param Name="value">Automotive Industry</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">Total Productive Maintenance</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">Artificial Intelligence</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">World</Param>
      </Object>
      <Object Type="keyword">
        <Param Name="value">Class TPM</Param>
      </Object>
    </ObjectList>
    <ArchiveCopySource DocType="pdf">https://journaldtai.com/index.php/jdtai/article/download/343/312</ArchiveCopySource>
  </Article>
</ArticleSet>
