A Digital Twin Framework for Proactive Enterprise Management: Research on Operational Decision-making Integrating IoT...

Area of Science:

• Cyber-Physical Systems
• Enterprise Management
• Industrial IoT

Background:

• Complex enterprise systems require advanced management strategies.
• Digital twin technology offers a computational approach for real-time integration and predictive analytics.
• Existing methods often lack proactive risk assessment and control.

Purpose of the Study:

• To develop and demonstrate a reproducible protocol for an IoT-enabled digital twin.
• To enable proactive, data-driven enterprise management through a unified cyber-physical decision framework.
• To integrate nonlinear dynamic modeling, state estimation, uncertainty propagation, risk quantification, and stochastic model predictive control.

Main Methods:

• A state estimator synchronizes the digital twin with the enterprise system using simulated sensor data.
• Uncertainty and risk measures are propagated through the dynamic model to identify instabilities.
• A predictive control layer optimizes multi-objective performance by generating risk-reducing control actions.

Main Results:

• The digital twin-driven method demonstrated smoother operational trajectories compared to reactive strategies.
• Lower cumulative risk, reduced uncertainty, and improved control efficiency were observed in simulations.
• The proof-of-concept showed potential advantages for enterprise decision support.

Conclusions:

• The developed protocol provides a scalable, data-driven, and risk-aware digital twin framework.
• Further validation with real operational datasets and large-scale studies is needed for industrial deployment.
• The framework is adaptable to various enterprise domains like manufacturing, logistics, and energy systems.