AI-assisted Producibility Analysis





The initial set-up process of profile wrapping systems is still carried out by the wrapper.





A self-learning AI cycle around the machine’s digital twin always provides recommendations for optimal machine settings.




Added Value

Recommendations on the manufacturability of new products and on parameters of future wrapping processes.

Düspohl is considered the world’s most innovative company when it comes to developing and manufacturing profile wrapping technologies, as well as surface laminating and peripheral machines for the wood and plastics industries. At Düspohl Maschinenbau GmbH, the wrapping of wooden, metal or plastic profiles by means of so-called pressure rollers takes place fully automatically and intelligently with the help of the “RoboWrap”. In the AI Marketplace, the setup process of the manufacturing plant is now to be optimised and recommendations on the feasibility of products are to be determined with the help of a digital twin.

Profile-wrapping is a process by which a decorative surface is laminated onto a substrate. The wrapping is done on a profile-wrapping machine with the help of pressure rollers. The RoboWrap system positions them fully automatically. At present, an employee still carries out the positioning
himself when first adjusting the pressure rollers to a profile geometry: he “teaches” them in. The combination that produces the optimum wrapping result is saved at the end and can be recalled at a later time. The robots then reproduce the positions of the pressure rollers automatically.


As part of the AI Marketplace, experts from Fraunhofer IEM are working together with Düspohl to complete the automation and to replace the previously unautomated “teaching in”. In addition, the feasibility of new product specifications will be able to be assessed automatically. To this end, an algorithm for extracting features is first developed, with the help of which all types of profiles at Düspohl can be examined for their properties. These characteristics are assigned to individual RoboWrap robots in the next step. For each robot, the third step is to determine with which roller geometry it can best process its assigned feature and where exactly the roller must be positioned.

With the help of a self-learning AI cycle around the digital twin of the machine, Düspohl will always receive recommendations for optimal machine settings in the future. At the same time, Düspohl’s customers receive recommendations on the manufacturability of new products and on the parameters of future coating processes. For them, this means not only process optimisation but also a further increase in efficiency. The findings from the project will be generalised for the AI Marketplace to derive an application for the platform.

In a nutshell

Subtitles in English are available.


Nikunj Dobariya
Düspohl Maschinenbau GmbH, +49 5207 92 91 248, n.dobariya@duespohl.com
Steven Koppert
Fraunhofer IEM, +49 5251 5465 402, steven.koppert@iem.fraunhofer.de


Claas Logo

Integration of AI in Computer Aided Design (CAx)

Artificial Intelligence has the potential to fundamentally change the way we work and operate. CLAAS GmbH & Co. KGaA, an internationally active manufacturer of agricultural machinery, has recognised this potential and is testing a special use case for the integration of AI in Computer Aided Design (CAx) in the AI marketplace together with the Fraunhofer Institutes IEM and IPK.

Learn more

AI-assisted Production Planning

The project of Westaflex in cooperation with the Fraunhofer IEM focuses on an AI application that helps to optimize the sequence planning of production orders. For this purpose, real-time data from production control as well as from machines are to be evaluated in order to extract hints for optimal machine allocations.

Learn more

AI-assisted Diagnosis

At present, vehicle diagnosis in a workshop requires comprehensive automotive knowledge and involves a great deal of work. Hella Gutmann’s aim is therefore to develop an AI application for AI-supported diagnosis and identification of potentially defective vehicle components on the basis of historical vehicle data (e.g. fault codes or sensor readings) and to integrate a further variety of data sources (e.g. invoice data, repair information etc.).

Learn more

AI-assisted Service Engineering

How can service technicians be optimally supported? A pilot project by Diebold Nixdorf Systems together with Fraunhofer IOSB-INA is dedicated to this question. The aim is to develop an AI application that reads and analyzes service and sensor data from ATMs in the field. Based on this, differentiated repair instructions for service technicians are to be generated. An existing service platform will serve as a database.

Learn more

Intelligent Product Monitoring

The goal of Ubermetrics’ project is an AI application that extracts relevant information from unstructured or semi-structured texts (e.g. online ratings, complaint emails, service reports, complaint reports), analyzes it and makes it systematically available to a developer. The application can be used, for example, in the context of targeted optimization of system components.

Learn more