Revolutionizing Digital Manufacturing with AI-LLM Integration

Strategic Insights -

In a groundbreaking study, researchers from the Hefei University of Technology have found that the integration of AI technologies based on large language models (AI-LLM) with big data analytics has transformed digital manufacturing, enabling real-time decision-making in operations and supply chain management (OSCM). However, traditional data envelopment analysis (DEA) models face significant computational complexity in large-scale environments, hindering their adoption for tasks such as demand forecasting, inventory control, and energy efficiency enhancement.

Key Takeaways:

  • The researchers propose a dominance-relation-driven DEA framework tailored for big data environments in digital manufacturing, which leverages spatial relationship characteristics and grouping algorithms to reduce computational complexity by 10-30 times.
  • The framework was validated through numerical simulations on industrial datasets, demonstrating its practical value in LLM-enhanced environmental monitoring and sustainable supply chain design.
  • A case study on the Chaohu Lake watershed shows the framework's potential in optimizing efficiency in digital manufacturing, addressing critical challenges in predictive analytics and resource allocation.
  • The research presents a scalable solution for optimizing efficiency in digital manufacturing, addressing critical challenges in predictive analytics and resource allocation.
  • The dominance-relation-driven DEA framework is a significant improvement over traditional DEA models, demonstrating improved scalability and efficiency in large-scale environments.
  • The researchers conclude that this research provides a foundation for future studies on the integration of AI-LLM with big data analytics in digital manufacturing.
  • The framework is a promising tool for optimizing efficiency in digital manufacturing, with potential applications in various industries, including but not limited to, automotive, aerospace, and energy.

Statistics:

  • Computational complexity reduction: 10-30 times
  • Number of industrial datasets used for validation: 1
  • Location of the case study: Chaohu Lake watershed
  • Institution of the researchers: Hefei University of Technology
  • Journal of publication: International Journal of Production Economics
  • Volume and issue of publication: 289, 2025
  • Publication date: Not specified

Sources:

  • Enhancing Digital Manufacturing Efficiency and Dominance Relation Driven Big Data Analytics. International Journal of Production Economics, 2025;289.
  • Zhixiang Zhou et al. (2025). Enhancing Digital Manufacturing Efficiency and Dominance Relation Driven Big Data Analytics. International Journal of Production Economics, 289.
  • Hefei University of Technology. Information provided by Zhixiang Zhou, November 4, 2025.