Digital Twin for Automatic Transportation in Industry 4.0

Area of Science:

• Manufacturing Engineering
• Industrial Automation
• Computer Science

Background:

• Industry 4.0 drives the digitalization of manufacturing processes, with Smart Manufacturing (SM) encompassing key areas like real-time data acquisition and virtualization.
• Digital Twins (DT) are gaining research traction for simulating industrial plant dynamics, enabling cost reduction and problem prediction within SM.
• Automatic Guided Vehicles (AGVs) are increasingly adopted for material handling and Material Requirement Planning (MRP) in collaborative industrial environments.

Purpose of the Study:

• To propose a novel Digital Twin (DT) design concept for enhancing the transportation services of Automatic Guided Vehicles (AGVs).
• To validate the proposed DT model through real-world experimentation in a Smart Manufacturing (SM) context.
• To assess the accuracy and effectiveness of the DT in predicting AGV navigation performance.

Main Methods:

• Development of a new Digital Twin (DT) design focused on external services for AGV transportation.
• Implementation of an Industrial Ethernet platform for real-time data acquisition and system control.
• Conducting real-world experiments in two distinct industrial scenarios to validate the DT model.

Main Results:

• The Digital Twin (DT) model demonstrated a high correlation with real-world experiments.
• Validation results showed an accuracy of 97.95% and 98.82% in predicting the total mission time for AGVs.
• The proposed DT design effectively models and predicts AGV navigation within the industrial plant.

Conclusions:

• The developed Digital Twin (DT) model successfully validates AGV navigation in a Smart Manufacturing (SM) setting.
• The high accuracy achieved confirms the utility of the DT for simulating and optimizing AGV operations.
• This research contributes to the advancement of Industry 4.0 by providing a validated DT solution for intelligent logistics.