Scholarlink

<p>This study investigates how environmental policies influence production planning in environmentally sensitive manufacturing systems, particularly in the paper and pulp industry. Despite growing regulatory pressure and consumer awareness, existing research often overlooks the integration of environmental policies with operational uncertainty. To address this gap, we propose the Environmental Hedging Point Policy (EHPP) as a strategic framework that draws on optimal control theory to dynamically balance sustainability and operational performance under uncertainty. Our approach combines simulation-based optimization with multi-objective particle swarm optimization and K-means clustering to evaluate trade-offs between cost, customer satisfaction, and environmental impact. We model a dynamic demand environment shaped by eco-conscious customer preferences and test policy scenarios using data from a paper manufacturing system involving both recyclable and virgin paper inputs. The results provide actionable insights for policymakers and manufacturers, supporting sustainable production planning under uncertainty.</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

AI-enhanced simulation for sustainable production in pulp and paper industry

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月22日

查看全文
  • Seyed Mojtaba Sajadi,
  • Reza Behnamfar,
  • Mehrdad Sadeghi,
  • Mahshid Tootoonchy

摘要

This study investigates how environmental policies influence production planning in environmentally sensitive manufacturing systems, particularly in the paper and pulp industry. Despite growing regulatory pressure and consumer awareness, existing research often overlooks the integration of environmental policies with operational uncertainty. To address this gap, we propose the Environmental Hedging Point Policy (EHPP) as a strategic framework that draws on optimal control theory to dynamically balance sustainability and operational performance under uncertainty. Our approach combines simulation-based optimization with multi-objective particle swarm optimization and K-means clustering to evaluate trade-offs between cost, customer satisfaction, and environmental impact. We model a dynamic demand environment shaped by eco-conscious customer preferences and test policy scenarios using data from a paper manufacturing system involving both recyclable and virgin paper inputs. The results provide actionable insights for policymakers and manufacturers, supporting sustainable production planning under uncertainty.