Optimizing smart manufacturing system: a digital twin approach utilizing teaching–learning-based optimization

Abstract

This article introduces an innovative method for optimizing smart manufacturing system (SMS) by combining digital twin technology (DTT) with teaching–learning-based optimization (TBLO). It creates a simulated model of the physical manufacturing environment, enabling real-time monitoring, simulation and analysis. By leveraging the TLBO algorithm, the system enhances the decision-making process for complex manufacturing tasks, facilitating continuous improvement and adaptation to dynamic production demands. The proposed framework aims to minimize production costs, reduce downtime and improve overall efficiency by optimizing key parameters such as resource allocation, production scheduling and machine performance. Experimental results demonstrate that the DT-TLBO approach can reduce production costs by up to 20%, decrease downtime by 30% and improve overall system efficiency by 25%. This innovative combination of advanced technologies offers a promising solution for modern manufacturing challenges, paving the way for smarter, more responsive production environments.

Keywords

• Digital twin
• smart manufacturing system
• optimization
• teaching–learning-based optimization
• efficiency and Industry
• innovation