Breaking News

Practical Use of AI/ML in Edge Manufacturing Applications

Manufacturers are moving from reliance on proprietary operational technology systems to open-sourced solutions that accelerate adoption of artificial intelligence (AI) and machine learning (ML) in edge manufacturing applications.

But that’s not necessarily an easy step for an industry that has long been dependent on proprietary components. “The industrial world still inhabits an environment of proprietary systems and vendor lock-in long since abandoned by the IT sector,” Sneider Electric’s Mike Hughes writes in his Forbes blog. “This is throttling innovation and progress.”

The manufacturing industry as a whole has been focused on the transition to Industry 4.0, which builds on the digital advances of the 3rd industrial revolution to create new products and processes. These rely heavily on advanced technologies to drive smart factories and smart devices.

A leap too far?

Many manufacturers are struggling to make the leap, though, as McKinsey analysts observe: “Although all of the manufacturers we assessed are transitioning to digital manufacturing, they are not deploying these technologies at the same rate. In fact, most organizations find themselves stuck in ‘pilot purgatory,’ with no clear approach for quickly scaling up innovations across the manufacturing network.”

AI is seen as key to achieving edge computing goals, and leveraging the capabilities of the cloud and edge is vital to achieving Industry 4.0 goals. “AI processing can be done locally for latency-sensitive applications, or sent to the cloud to get the best of both the edge and cloud worlds,” says Network World.

Rethinking proprietary tendencies

Open hybrid cloud technology has a key role to play. “To achieve manufacturers’ goals, factory systems should mirror the best practices of a modern IT environment based on containers, Kubernetes, agile development, AI/ML, and automation,” explain Frank Zdarsky and Stefan Bergstein of Red Hat. “All of these technologies, coincidentally, are components of open hybrid cloud, an IT footprint that can be used to accommodate these manufacturing technologies, from the edge of the network to the factory floor.”

Meeting Industry 4.0 goals is going to require a radical rethinking of manufacturing systems. “Unlike the factory systems of the past that were custom-built and managed by operations technology (OT), the desired approach to support use cases that not only collect, analyze and act on machine, plant, and factory floor data in real-time is to do so in a standardized manner,” Zdarsky and Bergstein point out.

As more and more manufacturing applications focus on edge deployment, manufacturers must break away from reliance on proprietary technology in order to speed up innovation and increase agility. Open source makes it easier to develop the compact, cost-constrained hardware needed to make edge systems and the use of AI and ML a practical reality.

Red Hat sees edge differently. See how: