Peripheral computing: 5 use cases for manufacturing

Here’s how a lay person – me – explains what manufacturing is: it means taking raw materials and turning them into finished products.

If you want a more formal definition, here’s one from US Bureau of Labor StatisticsThe manufacturing sector includes establishments engaged in the mechanical, physical or chemical transformation of materials or components into new products.

It sounds like old school and high physical — and it probably isn’t exactly a breeding ground for computational innovation. After manufacturing, just like general industrial sectornaturally suitable for edge computing and related trends such as the Internet of Things, artificial intelligence, and machine learning.

automation It’s a big deal in manufacturing and it’s been eons since. (The industry has a full Trade publications dedicated to this topic.) when the broader business world talks about how people and machines – or people and symbols, in the case of technologies like RPA And Artificial Intelligence/Machine Learning – they will work hand in hand now and in the future, to make CIOs smile and gestures knowingly.

There are tons of machines, robots, sensors and other devices that generate massive amounts of data. To maximize the value of that data, manufacturing companies need maximum flexibility in their IT infrastructure. For reasons similar to the industrial sector, edge computing engineering is not an unlikely option in manufacturing settings – it is a natural choice.

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

Says Brian Sathyanathan, Chief Technology Officer at my opinion. “There is no doubt that edge computing is, and will continue to be, extremely important to this industry. Despite this, the challenge for CIOs in this industry is how to put the power of cutting-edge systems in place while ensuring that cutting-edge applications always remain up and running and don’t disrupt chaos in their networks.”

Edge computing gives manufacturing IT managers a model for making strategic decisions about what to run, say, in a warehouse or on an assembly line — what to run in a central cloud or data center, and what to flow from the cloud to the edge and vice versa.

as such red hat Technology evangelist Gordon Half told us recently, “The idea is that you often want to centralize if possible, but maintain decentralization as needed.” Technical Evangelist colleague Ishu Verma points out edge geometry IT leaders were also able to standardize their evolving operations on the same practices and tools used in their central environment(s).

“This approach allows companies to extend emerging technology best practices to the edge – microservices, GitOps, security, etc,” Verma says. “This enables edge systems to be managed and operated using the same processes, tools, and resources as with centralized sites or the cloud.”

While it is likely to be true for any industry, this is especially important in a sector such as manufacturing, where an organization can have thousands (or more) terminal nodes operating in highly diverse and challenging settings.

5 Examples of Edge Computing in Manufacturing

With that in mind, below are five examples of manufacturing organizations that can use edge computing.

1. Quality control automation

Again, automation is usually considered important in manufacturing, although how it appears can vary greatly.

“Manufacturing facilities can have minimal automation all the way to a fully automated production line,” says Andrew Nelson, Principal Engineer at Insight.

Edge/IoT applications can become increasingly useful as the environment moves toward the “fully automated” end of the spectrum.

Edge/IoT applications could become increasingly useful as the environment moves toward the “fully automated” end of the spectrum.

Automation of 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 a bottling process in food or agricultural business settings.

A combination of computer vision, sensors, and other devices can detect aberrations or other problems; Being able to act quickly on that data requires keeping it as close to the process as possible.

2. Warehouse automation

A similar but separate automation use case exists in the warehouse, where functions such as inventory management are rich in data and opportunities for increased efficiency.

“Some manufacturers run warehouses next to production lines,” says Nelson. Computer vision can be used to manage inventory levels and aid in product selection. RFID /please Earlier can also be tapped for item locations and quantity levels. Smart shelves can be equipped with sensors as another data point.”

Sending all of this data back to the cloud or a central data center probably isn’t the most effective option from a cost or performance point of view. Deployments to Edge create the flexibility to make more optimal decisions about what needs to be run locally in the repository, whether that is due to latency, cost, security, or any other reason.

3. Production line diagnostics

We hear a lot about “predictive analytics” these days, but it’s a broad term – its actual value depends on business or industry-specific applications, and manufacturing is of great importance: using machine data to closely monitor and predict how many moving parts and parts in a manufacturing environment will break down or require maintenance.

“The [production] The line itself can be used to predict problems with bearings, belts, motors, etc.,” says Nelson. “In many cases, a downtime of the line for maintenance can cost the company a lot. If you can anticipate or sort issues quickly, you can reduce downtime and “potentially save significant ongoing costs.”

In this context, response time becomes costly. Processing this data locally can produce a tangible financial return on investment. This ROI can be amplified by combining this type of predictive analytics with the Nelson QC/QA automation described above.

“This can be combined with Q/A operations into one landscape with multiple benefits and greater ROI,” says Nelson.

4. Products Logistics and Tracking

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

RFID and Bluetooth Low Emission [technologies] They can be used to track products as they go through the line and out of production to boxes and pallets and even when moving into shipping containers,” says Nelson. “Trucks can be checked on their way to or out of the warehouse to process I/O product levels.”

It’s a reminder that, like edge servers and apps, the boundaries of “the edge” may constantly expand.

5. The ‘Golden’ Use Case: AI/Machine Learning Applications

if Reduce latency As the most common driver of cutting-edge computing strategies, AI/machine learning workloads are likely to become the golden use case, at least in manufacturing.

“More robust manufacturing deployments rely on the power of AI that feeds them, but making smart devices run smoothly at the edge requires a lot of data,” says Sathianathan. my opinion Executive Director.

The problem isn’t the lack of available data – all of the use cases mentioned above reflect the fact that manufacturing CIOs are overwhelmed with information. In fact, Satyanathan says manufacturing has an advantage over some other industries when it comes to AI/machine learning because a lot of enterprise data is generated automatically.

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

“Unlike data in other sectors with more bias and noise, manufacturing system data is particularly relevant and valuable ‘golden data’,” he says.

Challenges occur when trying to send all that data back from the manufacturing site to the cloud or data center. As Satyanathan recently told us, there can be something like “a lot of data” to pass from the factory floor or warehouse over the local network, to the cloud, and back again.

This is not good, says Satyanathan, because, as manufacturing CIOs know, decisions must be made immediately in order to be effective. “And while some downtime is typically acceptable in standard IT environments, this is simply not the case in manufacturing. Costs to shut down production lines due to faltering high-end applications can run into hundreds of thousands of dollars per minute — and there is no room for error. “.

As cutting edge computing and artificial intelligence/machine learning technologies mature, both in terms of infrastructure and in terms of developing lighter weight applications (via low code and other tools), becomes a match made in IT heaven.

“Advances in AI and edge servers with GPU-centric architectures are now available, and for manufacturing technology managers, it is a much better solution to start putting AI applications to the edge,” says Satyanathan.

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

Leave a Comment