September 8, 2021
Jeffrey Hagen

Accolade Wines

Saving 1 million litres of wine per year with AI

Computer Vision
Structured Data

Impact

ML6 helped Accolade Wines to implement a ML process to capture real time insights during the manufacturing process and prevent wine loss from happening with predictive analytics, enabling all 3 bottling lines to further reduce losses and saving another 1 million litres of wine per year or the consumption of 50 000 people per year. A 200% ROI for Accolade Wines.

Intro to the customer

Accolade Wines is the largest wine manufacturer inthe UK. They are a global wine producer who own andrun The Park, the largest wine bottling facility in GreatBritain. Bottling over 250 million bottles of wine eachyear, The Park is a Carbon Neutral facility, and 4 timeswinner of the UK’s Sustainable Manufacturer of theYear.

Accolade Wines is saving another 1 million litres of wine per year with an intelligent solution.

The challenge

Accolade Wines with an impressively low margin of waste, still had ambitions to reduce wine loss even further but had no way of tracking live wine flow during the bottling process. Therefore, they decided to seek a strategic partner in machine learning to investigate how a self learning and adaptive wine management system could be used to monitor and improve wine yield to unprecedented levels

The solution

Together with Accolade Wines, ML6 built a solution for wine loss detection by implementing sensors in place for the process & having a realtime dashboard for individual components. The idea was to prevent wine loss from happening on time using rule based and ML alerts. We created a real-time Grafana dashboard that visualizes the end-to-end process and helps identify when the wine loss occurs so operators can directly act on it.

The solution was built on Google Cloud to iterate quickly and scale up the solutions to multiple lines and/or countries.

Machine learning company ML6 created a Grafana dashboard to monitor bottling operations for Accolade Wines

The new rule-based alert system shown in the main dashboard (above) monitors for big discrepancies in volume during the bottling process. So when there is a sizable difference in the amount of wine going in and coming out of any part of the manufacturing line, an alert is fired so that operators can investigate what’s causing the loss and make changes instantly.

Machine learning company ML6 created a Grafana dashboard to monitor bottling facility for Accolade Wines

We then mapped out information collected on a macro and a micro level. Operators can see the total wine volume in the system over time (top left) and the difference in the amount of wine that comes in and out of the facility (top right). For digging into the details, there are also graphs for flow rates (bottom) that measure the amount of liters per second that flow at certain times during the bottling process.

Resulting in a 200% ROI for Accolade Wines.

The results

Beverage packing businesses typically quote a wine process loss of2%. Accolade wines had already driven the average loss down significantly below this level by using standard process improvement techniques. However the extra process insights provided by ML6, enabled all 3 bottling lines to further reduce losses by over half of that. Resulting in saving another 1 million litres of wine per year.

Stay up to date
Sign up for our newsletter
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.