Digital twin helps test AI safety controls before industrial use
Digital Twin for Pre-Deployment Validation of AI-Driven Safety-Critical Industrial Edge Control Loops
Networking and Internet ArchitectureRobotics
Summary
Managing safety in industrial settings requires making sure AI and machines work well with communication networks. The authors developed a digital twin, a computer model that copies an industrial robot, its wireless network, and its AI control software all together. This digital twin lets them test different ways to run the AI, such as nearby or in the cloud, and see how communication delays affect safety. Their tests show the digital twin's predictions match what happens in real life. This tool can help engineers check their AI safety setups before using them in factories.
What this means in practice
- •For industrial control engineers: Simulate and validate AI-driven control loops and network effects before deploying industrial automation systems to improve safety and reliability.
- •For network planners for manufacturing: Evaluate placements of AI applications across edge and cloud to optimize wireless network resource use for real-time industrial operations.
Authors
Sara Cavallero, Federico Tonini, Tony Chahoud, Giampaolo Cuozzo, Davide Borsatti, Walter Cerroni, Maurizio Fodrini, Riccardo Marini
Abstract
Industrial environments are increasingly characterized by the tight interaction among physical processes, communication infrastructures, and intelligent applications. In this context, Digital Twins (DTs) have emerged as a key technology for system analysis and optimization. However, existing DT solutions typically focus either on industrial processes or communication networks, while lacking an integrated and application-aware perspective. To fill this gap, this paper proposes a modular DT framework for industrial environments that jointly models physical processes, wireless communications, and application logic within a unified architecture. The feasibility of the proposed framework is experimentally validated through a real-world Proof-of-Concept (PoC) implemented in the BI-REX pilot line, involving a 5G-connected Autonomous Mobile Robot (AMR) transporting hazardous liquids and remotely controlled by an AI-driven application. The proposed DT is used to reproduce the behaviour of the real deployment and to investigate the impact of different placements of the AI application, including on-premise, edge, and remote cloud execution scenarios. Experimental results demonstrate a close agreement between DT predictions and PoC measurements in terms of both network-level metrics, such as Reference Signal Received Power (RSRP) and latency, and end- to-end application metrics, including application-level Round- Trip-Time (RTT). Moreover, the analysis shows how inaccuracies of network modeling can critically affect the feasibility of latency-sensitive industrial control loops, highlighting the potential of integrated DTs as tools for the pre-deployment design and validation of next-generation industrial systems.