Scholarlink

<p>In this study, an innovative hybrid model for designing a green and resilient supply chain is presented by simultaneously utilizing fuzzy logic and neuromorphic architectures. The goal of this model is to face the challenges arising from uncertainty, environmental dynamics, and the need for adaptive decision-making in complex supply chain structures. In this framework, multiple objective functions, including minimizing total cost, reducing carbon emissions, and maximizing network resilience, are designed, and operational uncertainties in demand estimation, capacities, and logistics costs are modeled using fuzzy parameters. Next, the role of neuromorphic systems as a cognitive decision-making engine is investigated, which provides the ability to adapt in real time to environmental changes and learn from real-time flow data. To evaluate the effectiveness of the model, ten real-world scenarios from Bio10 company are selected as case studies, and the problem solving with three approaches—GAMS, Genetic Algorithm, and Wall’s Algorithm—is compared. Numerical results and performance analysis graphs show that the combination of neuromorphic and fuzzy systems can provide significant improvements in decision quality and response time.</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 Neuromorphic Intelligence with Fuzzy Multi-Objective Models in Resilient Green Supply Chain Design

  • 期刊论文

  • 发表日期：

    2025年10月20日

查看全文
  • Hamed Nozari

摘要

In this study, an innovative hybrid model for designing a green and resilient supply chain is presented by simultaneously utilizing fuzzy logic and neuromorphic architectures. The goal of this model is to face the challenges arising from uncertainty, environmental dynamics, and the need for adaptive decision-making in complex supply chain structures. In this framework, multiple objective functions, including minimizing total cost, reducing carbon emissions, and maximizing network resilience, are designed, and operational uncertainties in demand estimation, capacities, and logistics costs are modeled using fuzzy parameters. Next, the role of neuromorphic systems as a cognitive decision-making engine is investigated, which provides the ability to adapt in real time to environmental changes and learn from real-time flow data. To evaluate the effectiveness of the model, ten real-world scenarios from Bio10 company are selected as case studies, and the problem solving with three approaches—GAMS, Genetic Algorithm, and Wall’s Algorithm—is compared. Numerical results and performance analysis graphs show that the combination of neuromorphic and fuzzy systems can provide significant improvements in decision quality and response time.