Frito Lays is applying Machine Learning for ‘fitter’ chips (9/18)

List item
Submitted to "Future of Food"

While making potato chips may not be ‘rocket science’ to most of us, it is surely ‘computer-science’ for many at Frito Lays.

Frito Lays has been using Machine Learning in it’s potato and chips processing plants in several ways.

A machine learning model is deployed with a vision system to calculate the weight of potatoes being processed. 

A vision system is also used to gather data on the size and number of potatoes being processed.

“We have a vision system that looks at every potato going through our peeling process, where we abrasively peel our potatoes. An algorithm that can tell us what our percent peel is; that is, how peeled a potato is after going through the process versus how unpeeled it is. With this information, we can optimize our peeling so we don’t over-abrate the potato and peel away some of its flesh.”