Case study
37% less unplanned downtime on a production line.
At a manufacturing plant, Shahar helped cut the lines' unplanned downtime by 37%, with a model that predicts failures and alerts the maintenance team before a machine stops. It was a project he led before founding Pele.
The challenge
Every unplanned stop on a production line costs production hours, delayed orders and a team running to put out fires. Maintenance worked reactively, fixing machines after they had already stopped.
What was done
A model that predicts failures from the data the plant was already collecting, and alerts the maintenance team before a machine stops.
The result
Unplanned downtime fell by 37%.
Why it worked
The model didn't replace the maintenance team, it gave them time to get there before the failure.
Related
- Predictive modelsA predictive model takes the history already sitting in your systems and turns it into an estimate of what's coming: how much will be ordered, which machine will stop, which customer is about to leave and which deal will close.
Tell us the process that costs you the most hours.
Twenty minutes with both of us. You'll leave knowing whether AI belongs in that process, including when the answer is no.