Forecasting Automated Guided Vehicle Malfunctioning with Deep Learning in a 5G-Based Industry 4.0 Scenario

Abstract

Industry 4.0 proposes the use of 5G networks to support intra-factory communications in replacement of current communication practices. 5G networks offer high availability, ultra-low latency, and high bandwidth, and allow the allocation of computational resources closer to the factories for reducing latency and response time. In addition, artificial intelligence can help in making smart decisions to improve the industrial and logistic processes. This work presents an interesting use case that combines Industry 4.0, 5G networks, and deep learning techniques for predicting the malfunctioning of an automatic guided vehicle (AGV) by exclusively using network traffic information and without needing to deploy any meter in the end-us-er equipment AGV and programmable logic controller (PLC). The AGV is connected through a 5G access to its PLC, which is deployed and virtualized in a multi-access edge computing infrastructure. A complete set of intensive experiments with a real 5G network and an industrial AGV were carried out in the 5TONIC environment, validating the effectiveness of this solution.