Cloud-based HPC processing for knowledge generation in camshaft manufacture
- /
- POC
- /
- Cloud-based HPC processing for...
EPC manufactures more than half a million camshafts every year. Monitoring of the manufacturing process generates a massive amount of data which could be used to improve the production process. A prediction model can be implemented to correct the production process in real time.
Start date: 01/11/2015
Duration in months: 18
Problem Description
EPC manufactures more than half a million camshafts every year. Monitoring of the manufacturing process generates a massive amount of data which could be used as a basis for machine learning to improve the production process.
Goals
Reduce time to solution
Challenges
Current software solutions are not able to fully process the data fast enough to give an instrument that can correct the production in real time. To do this the instrument requires significant computational power, together with the application of novel machine learning technologies.
Innovation results
TRIMEK developed a metrological module of its M3 software, which enables the use of big data resources for data analysis. The new module is able to analyse scanning and measurement data faster by using cloud-based HPC. The production process is therefore more time-efficient.
Business impact
TRIMEK software module, gives a 20% increase in new license sales. EPC tested M3 capacities, reducing defective parts and cost by 1.5M€ over five years. CESGA will use the results in its big data platform, creating a white paper to showcase its capabilities.