GermanyManufacturing2025 – ongoingMasterflex
Machine learning for quality prediction in hose extrusion
Masterflex put a machine-learning system in its hose extrusion hall to predict quality and recommend process settings
Problem
Extruding high-performance plastic hose needs stable process parameters. Deviations create waste and slow down the start-up of production runs.
Approach
Masterflex developed the algorithms with a start-up in a long-term project. The system predicts quality parameters, flags early deviations in article- and system-specific process parameters and forecasts process stability, for example hose pitch. It also recommends adjustments such as screw speed, so operators get decision support in real time.
Results
No published figures
Takeaway
The company reported only a qualitative result. It gave no figures for waste or start-up time.
Categories
- Industry
- Manufacturing
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Partner co-development
- Evidence
- Company's own claim
Sources
Source summaries
Masterflex's news item describes the machine-learning system in its extrusion hall and what it predicts and recommends. The company called the forecasting accuracy in first results very good and said it expects less waste and faster start-up. It gave no numbers.
Full details are in the original sources.
