Kampf Schneid- und Windtechnik GmbH & Co. KG has been one of the most important international technology leaders in cutting and winding technology for 100 years. The company employs 650 people at 8 locations and has delivered more than 5,000 machines. Their machines process films made of various materials, e.g. plastic, aluminum, paper, and composites.
The project at a glance
- Technical feasibility demonstrated by setting up a proof of concept within a few weeks
- Efficient implementation of the AI use case with little effort
Initial situation
Kampf Schneid- und Windtechnik GmbH machines are often part of a production line, for example in the production of plastic films from granules to the finished film. Kampf's equipment is used for cutting and winding the films during the production process.
A tear of the film in the machines – what is known as a web break – leads to a stoppage of the entire production line and thus to high defect costs for customers. A web break can often be attributed to poor quality of the intermediate product or incorrect machine parameters. In order to minimize costs for its customers, Kampf Schneid- und Wickeltechnik wants to be able to predict a web break automatically and at an early stage so that countermeasures can be initiated in good time.
As part of a research and development project with codecentric, the technical feasibility of this web break prediction was to be demonstrated in a proof of concept. The project built on the Kampf’s in-house developed Industry 4.0 platform "the@vanced".
Solution
Basis for early web break detection: Industry 4.0 platform "the@vanced"
Kampf Schneid- und Wickeltechnik GmbH machines are delivered with the integrative Industry 4.0 platform “the@vanced”. The platform provides real-time data from the machine’s PLC (programmable logic controller) as well as additional data from an external edge unit developed by Kampf itself. This data is used for optimizing production, for monitoring, and for retrospective analysis, for example in the event of complaints. It also collects production-relevant information such as the length of the end product already wound. Early web break detection is based on the capabilities of this platform.
Proof of concept within a few weeks
codecentric's consultants were able to create a proof of concept (PoC) within a few weeks thanks to its interdisciplinary expertise in machine learning, digital product development, product management, and organizational enablement, as well as the excellent cooperation with Kampf's software engineers. During development, we paid attention to sustainability, i.e. Kampf should be able to maintain the PoC with little additional effort and integrate it into the technology stack already in use.
Technology: Python backend with carefully selected algorithms
Python backend reads the data from the "the@vanced" database, selects the relevant subset of the sensor data and puts it into a defined format. By using PCA (principal component analysis) and DBSCAN (density-based spatial clustering of applications with noise)) algorithms, we can now predict the threat of web breaks at an early stage. We were therefore able to dispense with the time-consuming and costly development of deep learning methods. Model prediction was performed in the PoC in a batch at regular intervals and can be performed in real time in a production environment.
Result
The project demonstrated that it is basically possible to predict a web break. We were able to set up a PoC in just a few weeks thanks to our interdisciplinary expertise and the close cooperation with Kampf. The existing data infrastructure of “the@vanced”, which codecentric had helped to develop, was used effectively and was a prerequisite for the rapid success of the project.
The focus of development was on sustainability: when selecting the algorithms, preference was given to the solution with the lowest complexity. Attention was paid to easy integration into the existing technology environment and preparations were already made for the future enablement of the customer.
Dr. Donatus Weber
Managing Director, Jagenberg Digital Solutions
codecentric consultants very skillfully guided us through this unknown field. We are very satisfied with the result, we can estimate the potential, and will continue with codecentric.
Dr. Donatus Weber
Managing Director, Jagenberg Digital Solutions
Do you have more questions about the project?
Would you like to learn more about the project? Are you interested in an custom solution for your company? Let's meet and talk
Service Lead GenAI
Other codecentric AG projects
Find out about other successful projects that we have completed with our clients. Perhaps you will find ideas here for a use case in your own organization.
Niklas Haas
Service Lead GenAI