Edge computing: 5 use cases for manufacturing

This is how a layman – me – explains what manufacturing is: It means making finished products from raw materials.

If you want a more formal definition, here’s one from the US Bureau of Labor Statistics: “Manufacturing includes operations engaged in the mechanical, physical, or chemical transformation of materials, substances, or components into new products.”

It sounds dated and very physical – and perhaps not exactly fertile ground for computer innovation. But manufacturing, like the entire industrial sector, is a natural fit for edge computing and related trends like IoT, AI and machine learning.

Automation is a big thing in manufacturing and has been for eons. (The industry even dedicates entire trade publications to the topic.) As the broader business community talks about how humans and machines—or humans and code in the case of technologies like RPA and AI/ML—will work together from time to time, CIOs smile and nod in the future knowing about the production.

There are tons of machines, robots, sensors and other devices that generate massive amounts of data. In order to maximize the value of this data, manufacturing companies need maximum flexibility in their IT infrastructure. For reasons similar to those in the industrial sector, edge computing architecture in production environments is not an unlikely choice—it is a natural one.

[ Developing an edge strategy? Also read Edge computing: 4 pillars for CIOs and IT leaders. ]

“The manufacturing industry continues to push edge applications — from robots that scurry through the warehouse to acoustic calibrators to cameras that detect errors on the assembly line — to drive factory automation and efficiency,” said Brian Sathianathan, CTO at Iterate. hey “There is no question that edge computing is and will continue to be hugely important to the industry. However, the challenge for CIOs in this industry is to harness the power of edge systems while ensuring that edge applications remain always active and don’t wreak havoc on their networks.”

Edge computing provides manufacturing CIOs with a model to make strategic decisions about what should run, say, in a warehouse or on an assembly line—and what should run in a centralized cloud or data center, and what should flow from the cloud to the edge and vice versa .

As Red Hat technology evangelist Gordon Haff told us recently, “The idea is that you often want to centralize when possible, but decentralize when needed.” And Haff’s fellow technical evangelist Ishu Verma points out that the edge architecture allows IT It also enables executives to standardize their edge operations to the same practices and tools used in their centralized environments.

“This approach allows organizations to push the best practices to the edge for emerging technologies — microservices, GitOps, security, etc.,” says Verma. “This enables edge systems to be managed and operated using the same processes, tools and resources as with centralized locations or in the cloud.”

This may be true of any industry, but it’s especially important in a sector like manufacturing, where an organization may very well be running thousands of edge nodes (or more) in widely varying, challenging environments.

5 examples of edge computing in manufacturing

With that in mind, here are five examples of manufacturing companies that can leverage edge computing.

1. Automation of quality control

Again, automation in manufacturing usually plays a big part, although the way it manifests itself can vary significantly.

“Manufacturing facilities can range from minimal automation to a fully automated production line,” says Andrew Nelson, principal architect at Insight.

Edge/IoT implementations can become increasingly useful as an environment moves towards the “fully automated” end of the spectrum.

Edge/IoT implementations can become increasingly useful as an environment moves towards the “fully automated” end of the spectrum.

Automating quality control on a production line is a good example, according to Nelson, and is common in settings such as a canning line in the beverage industry or the packaging process in the food or agricultural industries.

A mix of computer vision, sensors and other instruments can detect anomalies or other problems; In order to be able to react quickly to this data, it must remain as close to the process as possible.

2. Warehouse automation

A similar but separate use case for automation is the warehouse, where functions like inventory management are rich with data and opportunities to increase efficiency.

“Some manufacturers operate warehouses next to the production lines,” says Nelson. “Computer vision can be used to manage inventory levels and help with product selection. RFID/BLE earlier can also be used for item location and quantity levels. Smart shelves can be instrumented with sensors as an additional data point.”

Sending all that data back to a cloud or centralized data center is probably not the most effective option from a cost or performance perspective. Edge deployments create the flexibility to make more optimal decisions about what to run locally in the warehouse, whether for latency, cost, security, or other reasons.

3. Diagnosis of production line

You hear a lot about “predictive analytics” these days, but it’s a broad term – its real value depends on business or industry-specific applications, and manufacturing has a big one: using machine data to more closely monitor the large numbers and predicted moving parts and parts in a production environment will fail or otherwise require maintenance.

“That [production] The line itself can be instrumented to predict problems with bearings, belts, motors, etc.,” says Nelsons. “In many cases, a line down for maintenance can cost a company a lot. If you can quickly predict or triage the problems, you can “minimize downtime” and potentially save significant ongoing costs.”

In this context, latency becomes expensive. Processing this data on-premises can result in tangible financial ROI. And that ROI can be increased by combining this type of predictive analytics with Nelson’s quality control/QA automation described above.

“This can be merged with the Q/A processes in a landscape with multiple benefits and greater ROI,” says Nelson.

4. Product Logistics and Tracking

This category extends the edge of the edge, allowing for inventory tracking and other uses even as products move from the manufacturing environment to other stages in the supply chain.

“RFID and Bluetooth Low Emission [technologies] can be used to track products as they move through the line and out of production into cases and pallets, and even as they are being transported into shipping containers,” says Nelson. “Trucks can be scanned en route to and from a warehouse to capture both the inbound and outbound product levels.”

It’s a reminder that the boundaries of “Edge” as edge servers and applications can be continually expanded.

5. The “golden” use case: AI/ML applications

If latency reduction is the most common driver of edge computing strategies, then AI/ML workloads seem likely to become the golden use case, at least in manufacturing.

“The best-performing manufacturing edge deployments depend on the power of the AI ​​powering them, but for smart machines to work seamlessly at the edge, a lot of data is required,” said Sathianathan, CEO of Iterate.ai.

The problem isn’t a lack of available data – all of the above use cases reflect the reality that CIOs are being overwhelmed with manufacturing. In fact, Sathianathan says that manufacturing has an advantage over some other industries when it comes to AI/ML because so much of a company’s data is machine-generated.

[ Related read: Edge infrastructure: 7 key facts CIOs should know about security. ]

“Unlike data in other sectors, which contains much more distortion and noise, manufacturing system data is ‘golden data’ that is particularly relevant and valuable,” he says.

The challenges arise when trying to get all that data back from the production site to the cloud or data center. As Sathianathan recently told us, there can be something like “too much data” to get from a factory or warehouse floor, through the local network and into the cloud and back again.

“That’s not good because, as manufacturing CIOs know, decisions need to be made immediately to be effective,” says Sathianathan. “And while some downtime is typically acceptable in standard IT environments, that’s simply not the case in manufacturing. The cost of stopping production lines because edge applications stall can be in the hundreds of thousands of dollars per minute—there’s just no room for error.”

As edge computing and AI/ML technologies mature, both in terms of infrastructure and in terms of building lighter applications (via low-code and other tools), they become a match made in IT heaven .

“Advancements in AI and edge servers with GPU-centric architectures are now becoming available, and for manufacturing CIOs, putting AI applications at the edge is a much better solution,” says Sathianathan.

[ Learn how leaders are embracing enterprise-wide IT automation: Taking the lead on IT Automation. ]