Seagate Technology has bagged an award for its achievement in smart manufacturing from a group of its manufacturing peers—a national association of manufacturers with 14,000 company members.
The company won a 2022 Manufacturing Leadership Award for its outstanding innovation from the Manufacturing Leadership Council (MLC) at the National Association of Manufacturers (NAM).
The winning project provides a powerful foundation for high-volume AI analytics in the factory. Dubbed OPICA—Optical Inspection with Centralized Analysis—the novel strategy supports analytics at the factory edge. It is a no-code application of deep learning that identifies defects that can occur during production, and prevents them from escaping downstream.
“The judges who evaluated this entry noted that it pushes the envelope on inspection and demonstrated an advanced use of technology with strong, proven results,” said Penelope Brown, MLC’s senior content director.
Built with inclusivity in mind, the award-winning solution democratizes AI on the factory floor.
“Computer vision challenges are common in manufacturing,” said Gary Kunkel, an engineering director who helped develop Seagate’s solution. “Historically, solutions would be developed by specialized resources such as computer vision engineers. Early on it became apparent that with deep learning techniques we could develop no-code tools to train neural networks to identify defects and features in images. This allowed for democratized development and an exponential growth of solutions. Instead of 1 or 2 people that could solve these problems, the numbers grew to 10s and could enable 100s of people to solve these types of problems.”
Expertise in development of mathematical computer vision algorithms is no longer a requirement. Specialists who work in preventing defects can take images of their processes and devices, mark them up, and use the no-code software (graphical user interface) to train the model to identify contamination. The distributed knowledge opens the door to easy scalability.
Built using scalable and modular data engineering technologies such as Docker containers, Kubernetes container orchestration, RabbitMQ data messaging, edge line servers, human-in-the-loop model management dashboards, and high-speed Seagate storage, OPICA handles 3 million multi-class deep learning inferences per day.
“I’m proud of our cross-functional team’s collaborative ingenuity,” said Jeffrey Nygaard, Seagate’s executive vice president of operations and technology. “It will easily be scaled to handle 12+ million images per day with the plug-and-play addition of computational resources such as GPUs and servers.”
Applying the solution has a ROI of up to 300%. That is because, thanks to this application, inspection accuracy improved by at least 20%—and only 7 automated machines are needed to do the work of 150 operators using manual microscopes to inspect millions of parts daily.
“Seagate Technology is part of a high-performing contingent of award winners that serve as an example of what’s possible in manufacturing’s emerging digital era,” said MLC’s Penelope Brown.
The Seagate team will be recognized at the MLC’s Summit’s Awards Gala on June 29, 2022, at the JW Marriott in Marco Island, Florida.