Almetra brings NVIDIA edge AI to assembly lines

It all started at Berlin’s Merantix venture studio in 2022, when Silviu Homoceanu and Max Fischer agreed AI could play a big role in improving manufacturing. So the two started Almetra, which runs NVIDIA Metropolis vision AI on NVIDIA Jetson AGX Orin modules to measure and help optimize assembly line processes. Almetra is proud to be an NVIDIA Metropolis partner. 

Boosting efficiencies on production lines using NVIDIA Metropolis for vision AI and Jetson platform for edge AI

‍

Hailing from AI backgrounds, Homoceanu previously led self-driving software at Volkswagen, while Fischer founded a startup that helped digitize more than 40 factories.

Today, the Almetra AI software platform provides as much as a 20% performance jump on production lines for our customers.

Customers using the Almetra platform include Viessman, a maker of heating pumps, and industrial electronics company ABB, among others. Viessman is running Almetra at 15 stations, and plans to add it to even more lines in the future. Once all lines are linked to Almetra, production managers say that they expect up to a 50% increase in overall productivity.

“We provide our users with a dashboard that is basically the Google Analytics of manufacturing,” says Almetra CTO Homoceanu. “We install these sensors, and two weeks later they get the keys to this dashboard, and the magic happens in the background.”

Capturing assembly line insights for digital transformations  

Once the cameras start gathering data on assembly lines, Almetra uses that information to train models on NVIDIA-accelerated computing that can monitor activities on the line. It then uses those models deployed on Jetson AGX Orin modules at the edge to gather operational insights.

These Jetson-based systems continuously monitor the camera streams and extract metadata. This metadata identifies the exact points in time when a product arrives at a specific station, when it is being worked on and when it leaves the station. This digital information is available to line managers and process improvement personnel via Almetra’s custom dashboard, helping to identify bottlenecks and accelerate line output.

“TensorRT helps us compress complex AI models to a level where we can serve, in an economical fashion, multiple stations with a single Jetson device,” says Homoceanu.

Tapping into Jetson Orin for edge AI-based customer insights 

Beyond identifying quick optimizations, Almetra’s analytics help visualize production flows hour-by-hour. This means that Almetra can send rapid alerts when production slips away from predicted target ranges, and it can continuously track output, cycle times and other critical key performance indicators.

It also helps map how processes flow throughout a factory floor, and it suggests improvements for things like walking routes and shop-floor layouts. One of Almetra’s customers used the platform to identify that materials shelves were too far from workers, which caused unnecessarily long cycle times and limited production. Once the shelves were moved, production went up more than 30%.

Almetra’s applications extend beyond process improvements. The platform can be used to help monitor machine states at a granular level, assisting to predict when machine parts are worn out and recommend preemptive replacements, saving time and money down the line. The platform can also suggest optimizations for energy usage, saving on operational costs and reducing maintenance expenses.

Validating the impact of vision models on production

“Our vision is to empower manufacturers with the tools to achieve unprecedented efficiency,” says Almetra CEO Fischer. “Seeing our customers experience as much as a 30% increase in productivity with our vision models running on NVIDIA Jetson Orin validates the transformative potential of our technology.”

Almetra is a member of the NVIDIA Inception program for cutting-edge startups.

Learn more about NVIDIA Metropolis and Jetson

Learn more about NVIDIA Metropolis and NVIDIA Jetson.