Summary

Engineering Group, a global engineering firm and technology consultancy with a strong practice in simulation, worked with Pathmind to apply reinforcement learning to maximize factory output by making smarter decisions about order sequencing, reducing average processing time in a single plant by 16%.

The Pathmind policy resulted in a 16% reduction in processing time compared to the factory’s best heuristic.

Challenge

The factory being optimized had several production lines, each with different attributes and capacities. In addition, operators worked based on a set schedule, and they had different skill sets.

Every day, new orders came into the factory. Those orders had different processing requirements, batch sizes, and processing times. The factory faced persistent bottlenecks.

Why Pathmind Was Needed

The factory’s existing heuristic was designed to process an order as soon as the necessary resources — i.e. the right production line and operators — were available. But that heuristic was unable to reduce the bottlenecks or plan for them.

The factory needed a solution that would increase productivity and reduce processing time. A Pathmind policy had the potential to do that, as well as to generalize, so that it could be applied to orders it had never seen before.

Outcomes

Engineering Group’s team trained a reinforcement learning policy with Pathmind to control how orders were matched with production lines in the factory. The Pathmind policy resulted in a 16% reduction in processing time compared to the factory’s best heuristic. 

Contact us to learn more about using Pathmind reinforcement learning to maximize factory output and improve order sequencing.

 

About Engineering Group

With over 12,000 professionals in 65 global locations, Engineering Ingegneria Informatica S.p.A designs, develops and manages innovative solutions for the business areas where digitalization is having the biggest impact.

en_USEnglish