Nvidia eyes 10m electronics factories for AI tools

Nvidia eyes 10m electronics factories for AI tools

Feature articles |
By Nick Flaherty

Over 50 global electronics manufacturers are now adopting Nvidia’s AI Metropolis for Factories workflow for quality control.

The global electronics manufacturing industry spans more than 10 million factories worldwide, where much is at stake in producing defect-free products, spending $6 trillion a year on quality control.

The manufacturing giants and industrial automation providers include Foxconn Industrial Internet, Pegatron, Quanta, Siemens and Wistron. They are using a collection of factory automation workflows that enables industrial technology companies and manufacturers to develop, deploy and manage customized quality-control systems.

Metropolis for Factories combines an AI platform and workflows for the development of more accurate inspection applications such as automated optical inspection.

Pegatron, based in Taipei’s Beitou district, is using Metropolis for Factories on its production lines for everything from motherboards to smartphones, laptops and game consoles. With a dozen manufacturing facilities handling more than 300 products and more than 5,000 parts per day, Pegatron has a lot of quality control to manage across its product portfolio. Further, frequent product updates require ongoing revisions to its AOI systems.

Pegatron is using the entire Metropolis for Factories workflow to support its printed circuit board (PCB) factories with simulation, robotics and automated production inspection. Metropolis for Factories enables the electronics manufacturing giant to quickly update its defect detection models and achieve 99.8% accuracy on its AOI systems, starting with small datasets.

Pegatron uses Isaac Sim, a robotic simulator, to program robotic arms in simulation and to model the performance of its fleets of mobile robots. Tapping into Omniverse Replicator provides synthetic data generation to simulate defects, helping build massive training datasets with domain randomization and other techniques.

In Metropolis, Nvidia’s TAO Toolkit allows Pegatron to access pretrained models and transfer learning to build its highly accurate defect detection models from its enhanced datasets. The DeepStream software development kit can then be used to develop optimized intelligent video applications that handle multiple video, image and audio streams. Using DeepStream, Pegatron was able to achieve a 10x improvement in throughput.

Omniverse enables Pegatron to run digital twins of its inspection equipment, so it can simulate future inspection processes, promising increased efficiencies to its production workflow.

Edge IoT systems maker Innodisk is also using Metropolis for a new smart factory.

Aetina, a subsidiary of Innodisk, works with Nvida for its GPU-powered SuperEdge AI Training Platforms for factory automation workflows.The traditional approach of AOI, relying on optical analysis for object detection, can sometimes lead to misjudgments. This, in turn, increases the time and labor costs associated with manual re-inspection. Nevertheless, in today’s era of rapid AI development, there is a strong potential for significant improvements in these outcomes.

Innodisk is deploying both platforms, from Nvidia and Aetina, for vision AI to enhance the steps of factory workflows. It provides an efficient re-inspection process within production line AOI systems to automate the inspection and optimize the operation. Innodisk expects adopting this in its new factory will allow it to introduce the next wave of industrial automation and bring additional value to Innodisk’s customers and partners across a wide range of industries.

The tool flow is also used by Quanta subsidiary Techman Robot, which taps Isaac Sim to optimize the inspection of robots by robots on their manufacturing line.

The tools can be deployed from the enterprise industrial edge to the cloud, and a large and growing ecosystem of partners is helping bring it to market. These include sensor makers, application partners, inspection equipment makers and integration partners.

Basler, a leading European maker of imaging sensors and systems, has partnered with Nvidia to help developers build AI-enabled inspection systems faster through tighter integration with the DeepStream SDK. Overview and Advantech — both Metropolis partners — are collaborating to build a real-time AI-based inspection system to support industrial inspection, product counting and assembly verification.

Metropolis partners Siemens and Data Monsters are working together to build industrial inspection systems, bringing together Omniverse Replicator synthetic data generation, Nvidia TAO training, DeepStream runtime and Siemens’ Nvidia Jetson-powered industrial personal computers.



If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :    eeNews on Google News


Linked Articles