Research project integrating AI into laser cutting & welding
A collaborative project currently underway is looking to increase the autonomy and functionality of laser machines to ‘an unprecedented degree’ through the application of artificial intelligence (AI) and machine learning (ML).
The DIPOOL project (digital process online optimiser for intelligent laser machines), launched last year, will run until 30 June 2024, and is exploring the advantages of integrating AI + ML into laser cutting and welding.
The partners include four industrial companies and two research institutes
The project seeks to address the issue that while many small- and medium-sized enterprises (SMEs) can now afford lasers, they often lack the capacity and know-how to optimally fine tune them, especially when applications change frequently.
“We are therefore combining one of the unique characteristics of laser tools – that they can be programmed and controlled temporally and spatially – with AI + ML,” said Dr Dirk Petring, Group Leader of Macro Joining and Cutting at Fraunhofer ILT and scientific coordinator of the joint project DIPOOL. “Specifically, our work is about automatic and robust monitoring, quality assurance and optimisation of laser machines for changing manufacturing tasks.”
AI that has been well-trained by experts can detect system deviations, errors and quality defects faster and more reliably than classic monitoring and control systems. It can analyse sensor signals for more extensive pattern characteristics and even those previously unrecognised by experts.
The process monitoring equipment being used within the project includes a completely new, multispectral sensor system from 4D Photonics, for laser welding, and a laser cutting head from Precitec equipped with sensor technology and data interfaces developed specifically for the AI software and the DIPOOL approach.
Related article: AI-based quality monitoring of auto-body weld joints in real time
The partners estimate that the integration of AI + ML into laser cutting and welding systems will increase their overall efficiency by approximately 25 per cent. Such systems will be deployable in SMEs due to the prices of laser and computing power both having fallen significantly in recent years.
“Virtually all manufacturing companies are now under constant pressure to innovate – not least from competitors in China,” said Petring. “This increases the willingness to invest in innovative technology. In addition, the process understanding for AI systems is also growing among medium-sized companies.”
The project partners already have an end-user in mind for the conclusion of the project in 2024, with automotive repair entity ‘Bilstein Group’ having set up its own subsidiary ‘Bilcut GmbH’ in Hagen, Germany specifically for this purpose. The new firm will use the new equipment to cut shaped blanks for the automotive industry at high speed, starting in 2025.
“DIPOOL project partner Dreher will build a laser cutting system based on the technology we have developed. This will enable Bilcut GmbH to supply individually designed blanks with excellent economic and ecological performance,” said Petring.