Improving Energy Efficiency through Material Flow Logistics: A Machine Learning Decision-Support Framework for Saudi Furniture Manufacturing Plants

Improving industrial energy efficiency is essential for sustainable manufacturing and carbon-emission reduction. While logistics practices are widely recognized for improving operational performance, their contribution to energy efficiency remains insufficiently quantified. This study investigates the impact of Material Flow Logistics (MFL), represented by reducing material handling, on industrial energy efficiency and proposes a data-driven engineering framework for interpreting this relationship.The framework was developed using field data from 23 manufacturing plants. A predictive model learned the relationship between MFL applicability and expected energy-efficiency improvement, after which an AI-based response curve was generated and analyzed to extract interpretable engineering indicators.The results show measurable but nonlinear energy-efficiency gains. A preliminary diminishing-returns point was identified at approximately 63% applicability, while the maximum predicted improvement reached approximately 15% at 92% applicability. No adaptive saturation point was detected within the observed range. Given the limited sample size and predictive generalizability, the derived indicators are interpreted as sample-specific exploratory estimates rather than universal thresholds.The framework transforms industrial observations into interpretable decision-support knowledge for exploratory energy-efficiency planning, prioritization of improvement initiatives, and estimation of expected energy-efficiency improvement for new manufacturing plants based on their MFL applicability level and future industrial validation efforts.