Photonics Spectra BioPhotonics Vision Spectra Photonics Showcase Photonics Buyers' Guide Photonics Handbook Photonics Dictionary Newsletters Bookstore
Latest News Latest Products Features All Things Photonics Podcast
Marketplace Supplier Search Product Search Career Center
Webinars Photonics Media Virtual Events Industry Events Calendar
White Papers Videos Contribute an Article Suggest a Webinar Submit a Press Release Subscribe Advertise Become a Member


Aetina, NVIDIA Software Pairs to Improve Automated Inspections

Aetina, an edge AI solutions provider, is using its SuperEdge AI platforms in combination with NVIDIA Metropolis for Factories to enable manufacturing-sector end users to reduce the workload of re-inspecting false rejects in automated optical inspection systems (AOIs). The AI solution is designed to enhance productivity, and it stems from a collaboration between Aetina and parent company Innodisk with NVIDIA. The collaborators seek to deploy the solution in Innodisk’s factories for advanced electronics manufacturing.

Although AOI is effective in reducing the risk of delivering defective units, there is a chance that the mechanism may misclassify flawless items as imperfect. This can lead to unnecessary re-evaluation during the assembly process. When nondefective items are mistakenly identified as defective, assembly line workers must spend additional time inspecting these items again. There is approximately a 20% chance that units under inspection will be identified as defective by AOI and, among the units marked as defective via AOI, some may actually be flawless.

The AI solution is based on NVIDIA Metropolis for Factories, which is a comprehensive collection of AI-powered workflows designed to enhance AOI in factory settings. The solution incorporates AI software from the NVIDIA AI Enterprise software suite, Siamese network-based AI models, and Aetina’s SuperEdge AI platforms powered by NVIDIA GPUs. It can help prevent factory workers from wasting time on items incorrectly identified as defective in printed circuit board assembly lines using AOI systems for product quality control, according to Aetina.

Once implemented, the AI solution identifies nondefective items among those that did not pass initial AOI inspection, which reduces the chance of misclassification. After implementation, the chance of units under inspection being marked as defective will be reduced to under 5%, without increasing the risk of misidentifying defectives as defect-free items, Aetina said.



Explore related content from Photonics Media




LATEST NEWS

Terms & Conditions Privacy Policy About Us Contact Us

©2024 Photonics Media