This study presents a safety management model for hydrogen refueling stations, integrating digital twin technology and artificial intelligence (AI) to enhance operational safety. Given the risks associated with high-pressure gas handling and potential fires from hydrogen leaks, real-time safety monitoring is crucial. The proposed model is based on a digital twin, a virtual replica of the physical system using real-time data, including temperature, pressure, and state of charge, collected from an actual hydrogen refueling station in Samcheok, Gangwon Province. Out of nine tested machine learning and deep learning algorithms, the convolutional neural network (CNN) demonstrated the highest performance (accuracy: 1, F1 score: 0.993) for risk prediction. Using AI libraries like Scikit-Learn and TensorFlow, the model achieved prediction times of 68 milliseconds, enabling decision-making at intervals of 1 s. Developed with the Unity 3D modeling tool, the digital twin visualizes predicted risk situations, allowing users to quickly identify and respond to potential hazards. This approach offers a robust solution for improving the safety of hydrogen refueling stations.

Developing a hydrogen leak detection system that can quickly detect even the smallest amount of hydrogen is extremely crucial in the hydrogen industry. Currently, hydrogen refueling stations use a fixed hydrogen leak detection system. This study develops a mobile hydrogen gas leak detection system for hydrogen refueling stations using s, global positioning system, and Internet of Things (IoT) equipment, including LoRa and Wi-Fi. A digital twin is implemented by linking hydrogen gas-sensing data at a location that is quickly required or suspected using Google Maps. A time-series database is used to store the hydrogen gas-sensing data, and the transfer delay of hydrogen gas-sensing data between the hydrogen equipment was measured. Therefore, we developed a prototype system that transmits, stores, and analyzes hydrogen gas-sensing data in real time using IoT equipment for hydrogen refueling stations.

Hydrogen refueling stations require stable communication protocols for real-time monitoring and control. The Modbus TCP, which is used in existing hydrogen refueling stations, has limitations owing to a lack of time synchronization and event search functions. This study addressed these issues by applying the IEC 61850 communication standard to hydrogen refueling stations. Using IEC 61850 data modeling techniques, we designed logical nodes and data objects for key equipment, including tube trailers, compressors, mid tanks, high tanks, dispensers, and valves. We developed a prototype that simulates a small-scale hydrogen refueling station environment using a Raspberry Pi and a network switch. Data modeling and communication were implemented using the libIEC61850 library, and time synchronization was performed using the IEEE 1588. We quantitatively analyzed the average and standard deviation of the transfer delay according to three data collection methods (individual, dataset, and reported) in a hydrogen refueling station using the IEC 61850 communication method. The experimental results were analyzed to compare the performances of the three data collection methods. Significant differences in transmission delay and standard deviation were observed depending on the collection method. The proposed framework can serve as the basis for the development of advanced hydrogen refueling station systems.