Ericsson. AWS. Hitachi America R&D.
Three big names. Three big winners.
Here’s what’s taken place:
Ericsson, AWS, and Hitachi America R&D officially joined forces to enable a private 5G infrastructure trial at Hitachi Astemo Americas' electric vehicle manufacturing plant in Berea, Kentucky. This collaboration focused on AI, real-time digital video, and edge-to-cloud innovations across an already-available private 5G wireless network.
For smart IoT/IIoT, these details are juicy.
By leveraging Ericsson Private 5G in a side-by-side way with the AWS Snow Family, the three-org team was able to provide the private cellular networks necessary to establish cutting-edge machine learning (ML) models for Hitachi’s manufacturing. The goal was to build, train and apply said models to enhance operations on the manufacturing floor (including product quality, worker productivity, supply chain optimization, etcetera). In doing so (and by using Hitachi video analytics), real-time video of Hitachi’s component assembly operation was fed across Ericsson’s private 5G to proactively detect defects, reduce wasted materials and lost production, and intelligently assess a myriad of other factory-centric processes.
Essentially, an application of multiple innovative solutions from big industry names in order to ensure next-level efficiencies in productivity, cost, and energy usage.
The team responsible set up cameras on a live production assembly line that currently produces motor components for EVs. The real-time video was fed across Ericsson 5G to an AWS Snowball Edge device running the aforementioned Hitachi video analytics. By using 5G wireless, the trial installation was a win in just three days, completion-wise. It also demonstrated that, according to the announcement, “computer vision running on a private 5G network could simultaneously inspect 24 assembly components,” which is quite the boon when compared to one-by-one manual inspection approaches. Using high-def 4K cameras, this configuration was able to observe defects at a sub-millimeter level; much better than our human eyes can, and better than other technologies aimed at achieving this same thing. Moreover, the high throughput and low latency of 5G was instrumental for the upload of huge volumes of video data, streamlining operational decisions.
"The best news about this collaboration,” said Thomas Noren, Head of PCN Commercial and Operations, Ericsson, “is that it’s not about abstract capabilities that will be made available at some distant point in the future. Solutions like this can be deployed today in manufacturing and enterprise environments to deliver a range of advantages for early adopters.”
Chris McKenna, Global Lead, Private Wireless at AWS, stated, "While it's long been anticipated that technologies such as 5G and video analytics could drive innovation in manufacturing, one of the challenges has been how to securely and reliably process that data to drive outcomes. By using the Ericsson Private 5G Network product and running AI and ML models on an AWS Snow Family device, we were successfully able to demonstrate a reliable and secure connection to run machine vision inferences at the site to help detect defects earlier."
Sudhanshu Gaur, Vice President of R&D for Hitachi America and Chief Architect at the Hitachi Astemo Americas plant, also made clear this shared satisfaction.
“We explored and validated new use cases enabled by private 5G to show how smart factories can already function. The combination of private 5G, cloud and automated technologies via AI/ML has the collective potential to truly revolutionize the way we manufacture products, and we’re very excited to be at the forefront of this innovation."
Edited by
Greg Tavarez
