Brueckner Maschinenbau, a German maker of film stretching lines for packaging and technical films, kept a growing database of more than 500,000 parts. Material master data came from external sources such as supplier libraries, certificates and specifications and was often incomplete, inconsistent and heterogeneous. Duplicates, varied nomenclature and missing change logs made data management error-prone, and engineers spent time searching for the right materials or missed change notices for components. The goal was to improve data consistency and retrieval through automated harmonisation so that engineers could focus on higher-value work.
The consultancy Zuehlke started with user interviews and data exploration, then designed and built a bespoke GenAI application using customised large language models. Data managers upload data into the app, review and correct it with LLM-assisted suggestions, and reintegrate the refined records into the master database. The team ran continuous technical and user acceptance testing to fit the tool into Brueckner's workflow, and the minimum viable product reached highly promising levels of accuracy. "The collaboration with Zuehlke was a natural choice, given their proven track record in AI and industry-specific solutions," said Thomas Gruenaeugl of Engineering Electric, Material Planning at Brueckner.
According to Zuehlke, the MVP saved Brueckner several hours per week, and the system corrected hundreds of data entries within its first week of use. The work led to further AI projects, including predictive models for packaging film quality: explainable AI models that capture key physical mechanisms to predict product quality from dozens of material types and hundreds of machine parameters before production, intended as the basis for future AI-based predictive assistants. "Zuehlke's role was pivotal," said Wolfgang Zintz, Head of AI at Brueckner Maschinenbau.
Details
- City
- Siegsdorf
- Organization
- Brückner Maschinenbau
- Continent
- Europe
- Country