Introduction
The manufacturing sector is facing rising energy costs, creating a pressing need to reduce energy consumption while maintaining throughput.
At the same time, technological solutions are required to support an aging workforce. One promising approach is to augment workers with digital twin (DT) technology. This project therefore proposes a human-centric digital twin framework to address these challenges.
The research focuses on two questions:
How can a digital twin be developed as an augmentation tool for manufacturing workers?
How can the effectiveness of the digital twin be evaluated?
Onggo et al. (2021) outline key components of simulation-based digital twins relevant to this project. A simulation model of a production line will be developed using Python libraries such as SimPy or Salabim and integrated with an optimisation model to suggest optimal production sequences.
Research Challenges and Approaches
A major challenge of hybrid simulation–optimisation for real-time decision-making is computation time. Two approaches may address this: (i) simheuristics, combining simulation with fast heuristics (see Onggo et al., 2025), or (ii) multi-fidelity modelling (e.g., Cao et al., 2021; Rhodes-Leader et al., 2022), where a low-fidelity metamodel (such as a feedforward neural network) approximates a high-fidelity simulation.
The expected output is a digital twin capable of generating optimal production schedules and supporting workers through interactive what-if experimentation. To evaluate effectiveness, performance indicators will combine production metrics (e.g., throughput, rework rates) with human-centric metrics (e.g., situational awareness, digital stress). Few studies evaluate digital twins from this perspective; this research aims to fill that gap.
References:
References
Onggo BS, Martin XA, Corlu CG, Panadero J, Juan AA (2025). Stochastic Capacitated Dispersion Problems in Disaster Preparedness for Mass Casualty Incident. Journal of Heuristics 31:31. https://doi.org/10.1007/s10732-025-09566-1
Rhodes-Leader L, Nelson BL, Onggo BS, Worthington DJ (2022). A multi-fidelity modelling approach for airline disruption management using simulation. Journal of the Operational Research Society, 73(10):2228-2241. https://doi.org/10.1080/01605682.2021.1971574
Onggo BS, Corlu CG, Juan AA, Monks T, and de la Torre R (2021). Combining Symbiotic Simulation Systems with Enterprise Data Storage Systems for Real-Time Decision Making. Enterprise Information Systems, 15(2):230-247. https://doi.org/10.1080/17517575.2020.1777587
Cao Y-y, Currie CSM, Onggo BS, Higgins M (2021). Simulation Optimization for a Digital Twin using a Multi-Fidelity Framework. In Proceedings of the 2021 Winter Simulation Conference, pp. 1-12. 10.1109/WSC52266.2021.9715498