More and more industry data is recorded. Data lakes are substantially growing, everywhere.
But, just having (BIG) data does not yet realize a significant improvement in industrial processes. Therefore, companies focus more and more on getting insight out of their (large) data pools – with the help of Predictive Intelligence, the self-learning Artificial Intelligence solution.
Part one focuses on predictive maintenance in production (automotive) for Siemens and operation (IT center) for NTT Facilities:
– Reliable machinery is critical for production and operation processes.
In car building, failure of critical machinery leads to the downtime of entire production lines. One minute of unplanned stand stills sums up to ca. 18,000€ in losses.
– In IT centers, climate is critical for the well-functioning of servers and, thus, for all business processes.
– Un-supervised, self-learning algorithms analyzed data from critical processes. Multi-layer Artificial Intelligence methods discovered highly complex data structures, in such a way, hat service technicians were informed about future failure in machinery.
– Damaged is fixed before it actually occurs. Unplanned down time is avoided.
Part two focuses on predictive quality (Automotive OEMs and their suppliers):
– An international automotive supplier manufactures ca. 11,000 transmissions/day in 700 variants. Every transmission consists of up to 600 parts.
– An AI project was started to get reliable + fast results on root cause discovery for bad quality. Speed is important because production runs 24/7.
– Complex root-cause findings can be reduced from several days to hours, using self-learning Predictive Intelligence. Complex data masses are analyzed to find reliable data patterns, giving transparency on disturbing factors.