Industry 4.0 research

Research grant for Industry 4.0 research

In the course of Industry 4.0, the customizability of products up to batch size 1 at minimum cost is considered one of the main goals. For many companies in the German mechanical engineering sector involved in small batch and single-part production, this requirement is already part of everyday life in order to remain internationally competitive in the face of ever-increasing competition.

Small batch and single part production is characterized in particular by a high level of complexity of the manufacturing processes as well as high quality requirements for the products. The required degree of flexibility of the machines and the constantly changing conditions make it difficult to use conventional systems for process and machine monitoring. This makes reliable forecasts, for example with regard to residual tool life, which can contribute significantly to cost reduction and quality assurance, de facto impossible.

Against this background, the Fraunhofer IMS is researching predictive maintenance solutions for the manufacturing industry that, through the use of smart sensor systems and embedded artificial intelligence (AI), meet even the most stringent requirements, such as those for small batch and single-part production, and can be used where conventional systems fail.

In the course of this research, master's student Zero Liß has been receiving a research scholarship from the Industrial Research Foundation since November 2021. The scholarship supports high-achieving students whose work contributes to central research questions of medium-sized industrial companies in Germany. In her final thesis, the mechanical engineering student with a focus on digital engineering is working on the development and implementation of an edge computing-based architecture concept for process and tool monitoring in CNC machining centers using the milling process as an example. The goal is to provide application-oriented sensor data recorded at high sampling rates using distributed embedded systems and to enable the use of sensor-related signal processing and embedded AI. The thesis is part of a cooperation between the Fraunhofer IMS and the Department of Mechanical Engineering at the Ruhr-West University of Applied Sciences, which is supported by industrial partners. 

Our technologies - Innovations for your products

Distributed Learning

Distributed learning enables training of complex tasks on multiple small embedded systems.

Hybrid Learning and PGNNs

In case of insufficient training data simulations based on physical models help to improve the data base.

Feature Extraction for Smart Sensors

By means of adapted feature extraction the size of a neural network can be reduced.

Embedded AI for LiDAR

Embedded AI can be used to accelerate and improve the quality of distance measurement by LiDAR sensors.

Our technology areas - Our technologies for your development

Communication and Networking

Communication interfaces allow data exchange with other devices and connection to networks

User Interfaces

User interfaces as interface between device and user allow the configuration and operation of a product

Machine Learning for Embedded Systems

Artificial intelligence on resource-limited systems can be used to extract higher quality information from raw sensor data

Computer Vision

Computer Vision methods extract the maximum amount of information from image data


Embedded Software and Artificial Intelligence (Home)

Here you can get back to the overview page of the core competence Embedded Software and Artificial Intelligence (ESA).