Scholarlink

<p>Sustainable Supplier Selection is increasingly vital as modern supply chains must balance economic, environmental, and social goals. Traditional decision-making methods face difficulties due to uncertainty, vague linguistic evaluations, and multiple complex criteria—especially within digitally driven SCOR 4.0 environments. To overcome these issues, this research proposes an Integrated SCOR 4.0-driven Framework for Sustainable Supplier Selection using a Reinforced Fuzzy Rule-based Neural Network combined with the Fuzzy Best Worst decision-making Method (RFRbNN + FBWdmM). The evaluation model is structured around the six SCOR 4.0 Level 1 attributes: Plan, Source, Make, Deliver, Return, and Enable. Supplier data is collected and processed through a Fuzzy Min–Max Neural Network (FM-MN) for effective fuzzification. The Fuzzy Best Worst decision-making Method (FBWdmM) computes optimal fuzzy weights, while the Reinforced Fuzzy Rule-based Neural Network (RFRbNN) learns adaptive rf-rules for supplier evaluation. Final rankings are optimized with the Quantum-based Avian Navigation Optimization Algorithm (QANOA). Tests on 28 suppliers achieved 99.12% accuracy and a 99.00% f1 score, validated through ANOVA (F = 28.53, p = 0.004). Results confirm strong robustness and unbiased rankings, proving the framework’s reliability in Industry 4.0.</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

An Integrated SCOR 4.0-Driven Framework for Sustainable Supplier Selection Using a Reinforced Fuzzy Rule-Based Neural Network with the Fuzzy Best Worst Decision-Making Method

  • 期刊论文

  • 发表日期：

    2026年1月14日

查看全文
  • M. Zulaiha Maryam,
  • Sindhu J. Kumaar

摘要

Sustainable Supplier Selection is increasingly vital as modern supply chains must balance economic, environmental, and social goals. Traditional decision-making methods face difficulties due to uncertainty, vague linguistic evaluations, and multiple complex criteria—especially within digitally driven SCOR 4.0 environments. To overcome these issues, this research proposes an Integrated SCOR 4.0-driven Framework for Sustainable Supplier Selection using a Reinforced Fuzzy Rule-based Neural Network combined with the Fuzzy Best Worst decision-making Method (RFRbNN + FBWdmM). The evaluation model is structured around the six SCOR 4.0 Level 1 attributes: Plan, Source, Make, Deliver, Return, and Enable. Supplier data is collected and processed through a Fuzzy Min–Max Neural Network (FM-MN) for effective fuzzification. The Fuzzy Best Worst decision-making Method (FBWdmM) computes optimal fuzzy weights, while the Reinforced Fuzzy Rule-based Neural Network (RFRbNN) learns adaptive rf-rules for supplier evaluation. Final rankings are optimized with the Quantum-based Avian Navigation Optimization Algorithm (QANOA). Tests on 28 suppliers achieved 99.12% accuracy and a 99.00% f1 score, validated through ANOVA (F = 28.53, p = 0.004). Results confirm strong robustness and unbiased rankings, proving the framework’s reliability in Industry 4.0.