Duisburg, April 29, 2026 – As part of the GenSATIOn-Edge project, the Fraunhofer Institute for Microelectronic Circuits and Systems IMS is collaborating with partners to develop intelligent sensor systems for the continuous monitoring of industrial processes. AI models run directly on edge devices, enabling adaptive process monitoring without the cloud. Initial results show that processes can be analyzed in real time, quality deviations can be detected early, and maintenance can be planned as needed.

The focus of the work to date has been on analyzing real-world machining processes. Together with its partners, the project team conducted extensive test series on CNC milling machines, collecting sensor data under various production conditions. Based on this data, the researchers have already identified initial correlations between vibration signals, process parameters, and tool properties.

The data obtained forms the basis for AI models that, for example, detect tool wear or allow conclusions to be drawn about workpiece quality. Initial predictive models already show that tool wear can be reliably detected and chronologically classified based on sensor data. This allows critical conditions to be identified early on and maintenance measures to be planned in a targeted manner before quality losses or unplanned downtime occur.

Edge AI: Learning right at the machine

»AI needs to be where the data is generated—that is, directly on the production floor,« says Dr. Sebastian Wirtz, project manager at Fraunhofer IMS. »With GenSATIOn-Edge, we’re laying the groundwork for machines to understand their own status and respond to changes early on. This not only makes industrial processes more efficient but also significantly more robust.»

To this end, the project team established an initial software and data infrastructure that consolidates sensor data, machine information, and user inputs and stores them long-term. This creates a structured data foundation on which AI systems can continuously learn and adapt to new production conditions.

Smart sensors as the key

In parallel with data analysis, the project consortium is developing a novel IoT sensor node. This node captures relevant process signals directly at the machine and prepares them for AI evaluation. Fraunhofer IMS is contributing its expertise here, particularly in data processing and feature extraction. The goal is to implement the necessary analyses as efficiently as possible on resource-constrained hardware. This lays the foundation for future industrial deployment.

From the lab to production

In the coming project phases, the developed approaches will increasingly be tested under real-world production conditions. Further test series are planned, both in a laboratory setting and in industrial manufacturing. The focus here is particularly on the transferability of the AI models: they should not only function under controlled conditions but also deliver robust and reliable results in practice.

With this project, Fraunhofer IMS is making an important contribution to the digital transformation of industry. By combining intelligent sensor technology, edge AI, and self-learning systems, production processes can be made more efficient, transparent, and robust. At the same time, the approach reduces dependence on centralized IT infrastructures and lays the foundation for scalable, data-sovereign solutions in industrial manufacturing. 

GenSATIOn-Edge is supported by an interdisciplinary consortium. In addition to Fraunhofer IMS as project coordinator, the partners involved are GED Gesellschaft für Elektronik und Design mbH, Ruhr-West University of Applied Sciences, R&R Formentechnik GmbH, and Formtec GmbH. The project has a total budget of approximately 1.7 million euros and runs from July 1, 2024, to December 31, 2028. It is co-financed by the European Union and the State of North Rhine-Westphalia under the ERDF/JTF program (grant number: EFRE-20800495).

Further information is available on the IMS project website:

GenSATIOn-Edge - Fraunhofer IMS