Lasers

4Maas

Dynamic laser beam shaping and digital technologies for flexible, sustainable, and data-driven manufacturing processes.

Contact person

Volkher Onuseit, B.S. in Engineering

Institute for Beam Tools (IFSW),
University of Stuttgart

Contact person

Pasquale Franciosa

Professor and Head of the “Laser Beam Welding” Research Group;
WMG, University of Warwick

Laser Technology Meets Digital Manufacturing

Lasers4MaaS is developing new approaches to flexible and sustainable manufacturing. The focus is on dynamic laser beam shaping, AI-supported manufacturing, and digital platform technologies. The project combines laser processes with real-time data, digital twins, and intelligent decision-support systems to make manufacturing processes more flexible, efficient, and resource-efficient.

Flexible Laser Manufacturing Through Dynamic Beam Shaping and Digital Technologies

Lasers4MaaS focuses on the further development of laser manufacturing processes, particularly laser welding. A key approach is the dynamic shaping of the laser beam. This allows the properties of the laser beam to be adapted in real time to different materials and applications.

In addition, the project combines laser processes with digital manufacturing technologies. A cloud-based, AI-supported platform is designed to connect manufacturing systems and integrate data streams. Real-time data can be used for process monitoring, quality control, and optimization.

Digital twins and data- and physics-based machine learning methods support the selection, optimization, and control of processes. Predictive maintenance approaches are also designed to monitor the condition of equipment and detect potential failures early on.

Lasers4MaaS takes a "Lasers-as-a-Service" approach. This is intended to enable more flexible and scalable access to advanced laser systems. The approaches developed are being considered for applications in the automotive, aerospace, food packaging, and renewable energy sectors, among others.

Making Manufacturing More Flexible, Smart, and Sustainable

Lasers4MaaS aims to combine laser manufacturing and digital technologies to create a more flexible and highly interconnected manufacturing approach. To achieve this, manufacturing technologies will become more reconfigurable, and data will be exchanged quickly and securely between different systems.

Another key focus is on intelligent process control. Sensors, digital twins, and AI-based methods are intended to enable real-time monitoring and optimization of manufacturing processes. At the same time, new tools are designed to support the selection of suitable processes and their optimization.

In addition to productivity and quality, the project also takes sustainability and circularity into account. Decision support based on life-cycle assessment is intended to help incorporate environmental and economic aspects into manufacturing decisions. The development of digital product passports is also part of this approach.

Lasers4MaaS is intended to help enable flexible and scalable manufacturing models and to drive the adoption of advanced laser and digital technologies across various industrial sectors.

An Overview of the Project Structure:

Dynamic Laser Beam Shaping

Dynamic beam-shaping technology enables real-time adjustment of the laser beam's properties. This is intended to tailor the energy distribution specifically to different materials and applications and to improve the precision of laser processes.

AI-Powered Manufacturing

Real-time data, as well as data- and physics-based machine learning methods, are used to monitor, optimize, and control manufacturing processes. AI-based decision support is intended to improve process and operational efficiency.

Digital Manufacturing Platform

A cloud-based platform connects manufacturing equipment and data streams. It enables the integration of production data and its use for real-time monitoring, quality control, and predictive maintenance.

Digital Twins

Digital twins support the analysis and control of manufacturing processes. Together with production data and predictive methods, they are intended to contribute to process optimization and quality assurance.

Technologies Used

The project combines the RadarImager, 3D data acquisition, industrial image processing, and AI-based data analysis. This is complemented by AGV technologies, fleet management, industrial communication interfaces, and concepts for integrating inspection data into existing logistics, automation, and quality assurance processes.

Sustainability and Circularity

Decision support based on life-cycle assessment takes sustainability and recyclability into account. Another component is the development of digital product passports.