A Plan For Building Agility Into Industrial Automation


Industrial automation has come a long way since the days of programmable logic controllers and minicomputer-powered distributed control systems. But now, with the immense possibilities of big data and the Industrial Internet of Things, or IIOT, the future of automation seems less linear and more open to wide-ranging possibilities than ever before.

That’s a point made by automation expert Jim Pinto, writing for Automation.com:
“Automation software has had its day, and can’t go much further,” he says. “In the future, software will embed within products and systems…The plethora of manufacturing software solutions and services will yield significant results, but all as part of other systems.”

His point is well taken. The key to success will be communication of production systems via intelligent networks. This will deliver a manufacturer’s dream where “Customers order online, with electronic transactions that negotiate batch size (in some cases as low as one), price, size and color; intelligent robots and sophisticated machines smoothly and rapidly fabricate a variety of customized products on demand.”

Clearly, this level of interconnectedness wouldn’t apply to all manufacturers. But the vision contains a truth that will be shared by most all successful manufacturers – the value of, and the need for, organizational agility. It also shows how this agility will be needed not just on the production floor, but throughout the business and its ecosystem.

Real-Time Analytics Key To Communication

In the context of Industry 4.0 and the pervasiveness of data-driven intelligent processes, the meaning of “communication” rises well above simple concepts of peer-to-peer networking. With the numbers and varieties of sensor-laden machines and control systems available, today’s factories are capable of generating massive data streams every minute.

The value of communications, then, comes not just in data transmitted, but in finding the meaning of that data. This is where real-time analytics come in. As Deloitte says, “Data are the lifeblood of the smart factory. Through the power of algorithmic analysis, data drive all processes, detect operational errors, provide user feedback, and, when gathered in enough scale and scope, can be used to predict operational and asset inefficiencies or fluctuations in sourcing and demand.”

Similarly, the sweep of automation is today extended well beyond the hard-wired controllers or the past. Tomorrow’s automation will increasingly depend on intelligence gathered through analytics, and it will encompass automated processes throughout the organization’s ecosystem.

For the majority of manufacturers, then, planning for Industry 4.0 should begin at the center of the company’s livelihood, the production floor, then move outward to operations, customers, and suppliers.

Upgrading Production Analytics

Think of production analytics as including not just the factory, but field service as well. That’s largely because of the advances in product instrumentation, where many of today’s products are instrumented to deliver information directly back to service and production personnel.

In the factory itself, real-time analytics can take in up-to-the-second performance, temperature, vibration and other details to determine if and when a machine is likely to fail. Real-time analytics can combine the intelligence from an incoming data stream with contextual models – performance histories and repair standards, for instance – to raise an alarm in time for service personnel to carry out proactive repairs or maintenance.

Similarly, analytics from working products can alert field service to unusual conditions, either in the environment or the machine itself. The analytics can then recommend proactive service, even to the point of automating field service work orders.

Tying In Operations

An important but necessary leap is then to tie in operations. And that’s where analytics can be especially helpful. Operational systems range from ERP and logistics systems to marketing and customer sales processes. The challenge, as Manufacuring.net says, involves inter-process communications:

“Often the data sits in different information silos, typically in place to run operations — incoming materials and component data, manufacturing process parameters, laboratory analyses, testing results and customer experience data.

“These disparate and eclectic data sources are often in different formats, include different genealogical reference points and are owned by different parts of the organization.”

Rather than trying to navigate the various file types and access methods of the operational systems, real-time analytics can create an overlaying framework that collects and prioritizes real-time data coming from production and operational systems. It then ties in to the various departmental data stores, extracts the information it needs, and builds the contextual models to apply to the incoming data streams.

It thus gives all parties, from process and manufacturing engineers to IT, networking and operations managers, real-time views into the workings of the organization. To this, the organization can now add analytics applications. These can tell, for instance, if a problem in an ERP system might cause a slowdown in production, and how that might affect customer deliveries.

This same analytics overlay can work in reverse, too, watching customer behavior and using that to adjust production, inventory levels or logistics strategies.

Bringing In Suppliers

The next likely step in bringing agility to operations involves expanding analytics coverage to suppliers by merging supplier data, including related data such as weather analysis for global shipments, with inventory requirements and other data collected by the manufacturer. The analytics framework can then create customer-to-supplier visibility that will serve as a base for sophisticated predictive analytics.

None of this happens overnight, of course, but the basic frameworks are now available to get started. The new analytics frameworks are cloud-based to deliver elasticity for the fast performance ramp-ups needed to take in large data streams in real time. And they feature user-friendly development environments and dashboard displays, to help non-data-scientist users navigate the increasing data volumes that will be coming in the future.

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>