Digital twin-driven management strategies for logistics transportation systems

Area of Science:

• Logistics and Supply Chain Management
• Artificial Intelligence
• Industrial Engineering

Background:

• Industry 5.0 necessitates advanced logistics solutions.
• Current logistics face data fragmentation and integration challenges.
• Real-time monitoring and predictive capabilities are crucial for modern transportation.

Purpose of the Study:

• To introduce Digital Twin (DT) technology for logistics management.
• To propose a DT-driven methodology for optimizing unmanned vehicle operations.
• To enhance prediction and management of transportation behavior.

Main Methods:

• Leveraging DT to integrate multi-source heterogeneous data.
• Developing a digital model of unmanned vehicles.
• Utilizing LSTM neural networks for time-series forecasting of transportation behaviors.
• Dynamically adjusting the digital model based on prediction results.

Main Results:

• DT-based management significantly improves prediction accuracy for unmanned vehicle behavior.
• Demonstrated superior performance in decision support and fault tolerance.
• Validated through a case study on unmanned vehicle transportation.

Conclusions:

• DT technology effectively addresses data fragmentation and monitoring challenges in logistics.
• The proposed DT-driven strategy optimizes management and enhances operational efficiency.
• The methodology provides a reliable reference for intelligent modern logistics systems.