The $46 trillion world electronics manufacturing business spans greater than 10 million factories worldwide, the place a lot is at stake in producing defect-free merchandise. To drive product excellence, main electronics producers are adopting NVIDIA Metropolis for Factories.
Greater than 50 manufacturing giants and industrial automation suppliers — together with Foxconn Industrial Web, Pegatron, Quanta, Siemens and Wistron — are implementing Metropolis for Factories, NVIDIA founder and CEO Jensen Huang introduced throughout his keynote tackle on the COMPUTEX expertise convention in Taipei.
NVIDIA Metropolis for Factories is a group of manufacturing facility automation workflows that permits industrial expertise firms and producers to develop, deploy and handle custom-made quality-control methods that provide a aggressive benefit.
Producers globally spend greater than $6 trillion a yr in pursuit of high quality management, they usually apply defect detection on almost each product line. However handbook inspections can’t sustain with the calls for.
Many producers have automated optical inspection (AOI) methods that may assist, however usually these have excessive false detection charges, requiring labor-intensive and expensive secondary handbook inspections in an already difficult labor market, lowering their worth.
NVIDIA Metropolis for Factories now provides a state-of-the-art AI platform and workflows for the event of extremely correct inspection functions akin to AOI.
Pegatron Drives AOI With Metropolis for Factories
Main producer Pegatron, primarily based in Taipei’s Beitou district, is utilizing NVIDIA Metropolis for Factories on its manufacturing strains.
Pegatron manufactures every thing from motherboards to smartphones, laptops and recreation consoles. With a dozen manufacturing amenities dealing with greater than 300 merchandise and greater than 5,000 elements per day, Pegatron has loads of high quality management to handle throughout its product portfolio. Additional, frequent product updates require ongoing revisions to its AOI methods.
Pegatron is utilizing your entire Metropolis for Factories workflow to help its printed circuit board (PCB) factories with simulation, robotics and automatic manufacturing inspection. Metropolis for Factories allows the electronics manufacturing big to rapidly replace its defect detection fashions and obtain 99.8% accuracy on its AOI methods, beginning with small datasets.
Pegatron makes use of NVIDIA Isaac Sim, a robotic simulator, to program robotic arms in simulation and to mannequin the efficiency of its fleets of cell robots.
Tapping into NVIDIA Omniverse Replicator supplies artificial knowledge technology to simulate defects, serving to construct huge coaching datasets with area randomization and different methods.
In Metropolis, NVIDIA TAO Toolkit permits Pegatron to entry pretrained fashions and switch studying to construct its extremely correct defect detection fashions from its enhanced datasets.
The NVIDIA DeepStream software program improvement equipment can be utilized to develop optimized clever video functions that deal with a number of video, picture and audio streams. Utilizing DeepStream, Pegatron was capable of obtain a 10x enchancment in throughput.
Furthermore, Omniverse allows Pegatron to run digital twins of its inspection tools, so it may well simulate future inspection processes, promising elevated efficiencies to its manufacturing workflow.
It’s additionally utilized by Quanta subsidiary Techman Robotic, which faucets Isaac Sim to optimize the inspection of robots by robots on their manufacturing line.
Metropolis for Factories helps producers like Pegatron to extend manufacturing line throughput, cut back prices and enhance manufacturing high quality.
Rising Companion Ecosystem Helps Metropolis
Metropolis for Factories will be deployed from the enterprise industrial edge to the cloud, and a big and rising ecosystem of companions helps deliver it to market.
A bunch of specialists are becoming a member of forces on this effort together with sensor makers, utility companions, inspection tools makers and integration companions.
Basler, a number one maker of imaging sensors and methods, has partnered with NVIDIA to assist builders construct AI-enabled inspection methods sooner by way of tighter integration with the NVIDIA DeepStream SDK.
Quantiphi, a Metropolis companion, is working with one of many world’s largest beverage producers to automate inspections of totally packed pallets with GPU-powered imaginative and prescient AI.
Overview and Advantech — each NVIDIA Metropolis companions — are collaborating to construct a real-time AI-based inspection system to help industrial inspection, product counting and meeting verification.
Metropolis companions Siemens and Knowledge Monsters are working collectively to construct industrial inspection methods, bringing collectively Omniverse Replicator artificial knowledge technology, NVIDIA TAO coaching, DeepStream runtime and Siemens’ NVIDIA Jetson-powered industrial private computer systems.
Be taught extra about NVIDIA Metropolis for Factories.
