Scholarlink

<p>Additive Manufacturing (AM) is increasingly recognized as a transformative technology for ensuring reliable, sustainable, and human-centered production within the emerging Industry 5.0 paradigm. This study develops and empirically validates an integrated analytical framework to strengthen system assurance in government-linked enterprises by examining the interplay of reliability, human–machine interaction, and sustainability alignment. Using survey data from 267 respondents, a three-pronged methodology was adopted: (i) Structural Equation Modeling (SEM) to test hypothesized causal associations among latent constructs, (ii) Artificial Neural Networks (ANN) with SHAP-based explainability to enhance predictive accuracy and interpretability of system reliability, and (iii) the Best Worst Method (BWM) to rank and prioritize enablers from a system assurance perspective. The measurement model demonstrated strong reliability and convergent validity, while the structural model indicated excellent fit (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\({\upchi }^{2}\)</EquationSource> </InlineEquation>= 292.93, p = 0.13; CFI = 0.99; TLI = 0.98; RMSEA = 0.019). Findings revealed that strategic orientation and sustainability alignment are the most influential drivers of AM system reliability, whereas human–machine interaction and organizational readiness play important but comparatively moderate roles. The proposed hybrid framework offers risk-informed, assurance-driven insights for policymakers and engineering managers, enabling the development of reliable, resilient, and sustainable AM systems in complex public-sector manufacturing contexts.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integrating reliability, human–machine ınteraction, and sustainability for assured additive manufacturing in government-linked enterprises

  • 期刊论文

  • 发表日期：

    2026年3月19日

查看全文
  • Jitendra Kumar,
  • Vinay Singh

摘要

Additive Manufacturing (AM) is increasingly recognized as a transformative technology for ensuring reliable, sustainable, and human-centered production within the emerging Industry 5.0 paradigm. This study develops and empirically validates an integrated analytical framework to strengthen system assurance in government-linked enterprises by examining the interplay of reliability, human–machine interaction, and sustainability alignment. Using survey data from 267 respondents, a three-pronged methodology was adopted: (i) Structural Equation Modeling (SEM) to test hypothesized causal associations among latent constructs, (ii) Artificial Neural Networks (ANN) with SHAP-based explainability to enhance predictive accuracy and interpretability of system reliability, and (iii) the Best Worst Method (BWM) to rank and prioritize enablers from a system assurance perspective. The measurement model demonstrated strong reliability and convergent validity, while the structural model indicated excellent fit ( \({\upchi }^{2}\) = 292.93, p = 0.13; CFI = 0.99; TLI = 0.98; RMSEA = 0.019). Findings revealed that strategic orientation and sustainability alignment are the most influential drivers of AM system reliability, whereas human–machine interaction and organizational readiness play important but comparatively moderate roles. The proposed hybrid framework offers risk-informed, assurance-driven insights for policymakers and engineering managers, enabling the development of reliable, resilient, and sustainable AM systems in complex public-sector manufacturing contexts.