AI Case Study

Deschutes Brewery decreases beer fermentation cycle time using machine learning to optimise scheduling and monitoring of brewing processes

Deschutes Brewery uses real-time data and machine learning to predict outcomes for its beer brewing processes and recommend scheduling accordingly. This is done by using data from different processes collected by software which is then used by Microsoft's Intelligence Suite to make predictions.

Industry

Consumer Goods And Services

Food Beverage And Drugs

Project Overview

According to Microsoft, "Deschutes uses a solution called PI System, which ingests real-time data on temperature, pressure, flow rate, fermentation and other information in the brewery. Developed by software company OSIsoft, the system delivers data to Microsoft Cortana Intelligence Suite for predictive analytics that saves time and increases fermentation capacity. The intelligent solution accommodates natural variations in hops and barley, needed adjustments for taste and aroma, and different brewing requirements for each beer." The system is used on a daily basis to make decisions about moving from one stage of the brewing process to the next.

Reported Results

While specifics are unavailable, Fast Company reports that the system "allowed Deschutes to begin predicting the optimum time to raise the temperature, eliminating the need for the density-measuring step and shaving a couple of days off the 12-day fermentation cycle." The system has also detected anomalies such as temperature deviations which were causing a batch of beer not to ferment during brewing, thus avoiding supply loss.

Technology

Function

Operations

General Operations

Background

Per Microsoft: "Founded in 1988, Deschutes is one of the largest craft breweries in the United States and known for its diverse beer offerings". Fast Company reports that "the brewery has been logging stats about its production process for years. Making suds is all about controlling fermentation, which breweries do by adjusting temperature. They know when it’s time to do so by extracting liquid samples from tanks and measuring their density—a cumbersome, inexact procedure."

Benefits

Data

Real-time data on temperature, pressure, flow rate, fermentation