To face the requirements of current and future industry and to push the digitalization of factories, an international consortium in the project 5G-SMART develops a versatile multi-sensor platform communicating via 5G. To achieve an adaptable and flexible system, the embedded device is designed in a modular approach, consisting of a local processing core, integrable field sensors and a 5G modem. This paper covers the concept and design of the elaborated versatile multi-sensor platform and therewith presents a system that overcomes the limitations of current sensor systems and enables an interconnected real-time monitoring for production industry.

In this paper, we introduce a 5G-based multi-sensor platform for monitoring workpieces and machines. The prototype is realized within the EU-funded 5G-SMART project, which aims to enable smart manufacturing through 5G, demonstrating and validating new generation network technology in industrial processes. There are already state-of-the-art solutions, but with drawbacks such as limited flexibility, brief real-time capability, and sensors aimed at single applications. The 5G-SMART multi-sensor platform is designed to overcome these points and meet the requirements of Industry 4.0. The device is equipped with different sensors to acquire multiple data from workpieces and machines of the shop floor, wirelessly connected by 5G to the factory cloud. A hardware design description of the prototype is provided, focusing on the electronic components and their interaction with the microcontroller. Verification of the correct functioning of the board is given, with a basic library for the main peripherals used as a basis for the final firmware.

Artificial Intelligence (AI) models are expected to have a great impact in the manufacturing industry, optimizing time and resource cost by enabling applications such as predictive maintenance (PM) of production machines. A necessary condition for this is the availability of high quality data collected as close as possible to the process in question. With the advent of 5G equipped multi sensor platforms (MSPs), high sampling rate data can be collected and transmitted for processing in real time. This poses a data security challenge, since this data may give valuable insight into confidential business information of companies. Federated learning (FL) enables the training of AI models with data from multiple sources without it leaving the shop floor, by utilizing distributed computing resources available on premise. This paper introduces an architecture of FL based on data collected from 5G MSPs for enabling PM in industrial environments and discusses its potential benefits and challenges.