Automotive Manufacturer Highlights Use of 5G and AI

To demonstrate how available 5G, artificial intelligence (AI) and automation technologies can be used to improve manufacturing productivity, efficiency, sustainability and safety, while also reducing costs, Ericsson, Amazon Web Services (AWS) and Hitachi America R&D established a private 5G infrastructure trial at Hitachi Astemo Americas’ electric motor vehicle manufacturing plant in Kentucky. The goal of this trial was to build, train and apply machine learning (ML) models to enhance product quality on the manufacturing floor.

The infrastructure installed at the plant for this trial uses Ericsson Private 5G along with the AWS Snow Family to provide the private cellular networks for use in establishing machine learning (ML) models within the Hitachi manufacturing complex. The AWS Snow Family is a collection of purpose-built devices designed to move petabytes of data, offline. Real-time video of the component assembly operation at the plant was fed across the Ericsson private 5G network and assessed with Hitachi video analytics to detect defects earlier and reduce wasted material and lost production value.

Ericsson Private 5G is the company’s next-generation private network technology providing secure and reliable 4G and 5G connectivity through a single server dual mode core. Built for business operations, the product comes pre-integrated and is designed to keep sensitive data secured on-site.

Key results of the trial include:

• Higher performance and reliability for quality inspections. Used in defect detection, the trial demonstrated that computer vision running on a private 5G network could simultaneously inspect 24 assembly components compared with one-by-one inspection using conventional approaches. Using high-definition 4K cameras, the computer vision configuration was able to observe defects at the sub-millimeter level. The high throughput and low latency of 5G was key to uploading huge volumes of video data from the cameras to the AWS Snow Family device for analysis.

• Global scalability with 5G and cloud. According to the companies involved in this trial, the combination of 5G and cloud technologies can now make full-scale, global deployment of digital production line applications viable—from defect detection and quality inspection to robotics, real-time machine control and augmented reality applications.

• Rapid implementation with 5G wireless. The team set up cameras on a live production assembly line that produces motor components for electric vehicles. Real-time video of the component assembly operation was fed across the Ericsson private 5G network to an AWS Snowball Edge device running Hitachi video analytics. According to the companies, the use of 5G wireless enabled the trial installation to be completed in three days.

"The best news about this collaboration is that it is not about capabilities that will be available at some distant point in the future,” said Thomas Noren, head of PCN commercial and operations at Ericsson. “These solutions can be deployed today in manufacturing and enterprise environments to deliver a range of competitive advantages.”

“We explored and validated new use cases enabled by private 5G to show how smart factories can function today,” added Sudhanshu Gaur, vice president of R&D for Hitachi America and chief architect at Hitachi Astemo Americas.