Data-Driven Lean Decision Model and Simulation Verification for Smart Manufacturing Supply Chains
Year: 2026
Type: conference-paper
Abstract: The complexity, dynamics, and uncertainty of supply chains in the context of smart manufacturing pose significant challenges to traditional lean management paradigms. To address the core issue of deeply integrating lean principles with intelligent decision-making in a data-driven environment, this paper constructs a lean decision-making framework for smart manufacturing supply chains based on digital twins. A four-stage model encompassing data perception, state identification, strategy optimization, and simulation verification is proposed. By integrating real-time production data, material flow information, and order fluctuation characteristics, a multi-objective lean decision optimization system comprising mathematical models is established. This system covers system state equations, inventory balance constraints, capacity matching mechanisms, multi-objective functions, and intelligent solving algorithms. An improved multi-objective grey wolf optimization algorithm is employed to collaboratively optimize inventory strategies, production scheduling. Furthermore, in supply disruption scenarios, the recovery speed is improved by 42% compared to traditional methods, significantly enhancing the lean level and resilience of the supply chain. This research provides a systematic theoretical foundation and methodological support for smart manufacturing enterprises seeking to build data-driven lean decision-making systems.
Language: English
Subfield: Industrial and Manufacturing Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7204169114