Digital Twin Models for Intelligent Manufacturing Systems

Abstract

Digital twin (DT) models are increasingly adopted in intelligent manufacturing systems to bridge physical operations and their virtual representations, enabling real-time monitoring, predictive analytics, and dynamic optimization. This study explores recent advances in DT modeling tailored for manufacturing environments, focusing on multi-dimensional integration—including interconnected twin networks, augmented reality interfaces, energy-efficiency control, and operator knowledge incorporation. We propose a comprehensive framework that amalgamates interconnected digital twins (IDTs) across lifecycle phases with adaptive manufacturing control, AR-enhanced data visualization, and energy-aware batch process optimization.

Grounded in findings from a Delphi study with 35 experts, DT evolution is forecasted to gravitate toward decentralized data exchange, AI-driven automation, and subscription-based outcomes supported by real-time bidirectional data flows. Case analyses from industry—such as Foxconn’s lights-off factories, Bosch/Munich Re offerings, and Airbus’s twinbased production simulation—highlight DT applicability. Augmented reality (AR) integration further enhances human-machine collaboration in data visualization and real-time monitoring, as evidenced in recent DT–AR implementations. For energy-intensive batch processes, we introduce a system-level DT that integrates Time-of-Use energy pricing into runtime decision algorithms, improving scheduling and reducing energy costs. The proposed model also emphasizes the infusion of operator expertise via generative-AI-supported design frameworks, enhancing trust and robustness.

We evaluate this hybrid model through simulated case studies and pilot implementations, demonstrating improvements in energy efficiency, real-time responsiveness, operator usability, and decision support. The integration of IDTs with AR and energy-aware control yields a versatile and scalable digital twin architecture for intelligent manufacturing. The framework advances current DT modeling paradigms by converging lifecycle interconnectivity, human–machine symbiosis, and sustainability-focused control.