Articles, IIoT, Industrial IT

Industrial Analytics for IoT Is Transforming Manufacturing Processes

This post was guest-authored by Kayla Matthews, technology writer and the editor of Productivity Bytes.

The Internet of Things (IoT) refers to the network of connected equipment, devices and workstations used throughout the business world today. Industrial analytics is a natural extension of this “Industry 4.0” architecture: It allows the collection and study of process data so decision-makers can plot the most fruitful way forward or so automation can take on some of the heavy lifting.

Making wise use of data is especially important in manufacturing and other sectors with many stakeholders and moving parts.

So how exactly does industrial analytics for IoT improve manufacturing processes? We’re not talking about planning for the future — manufacturers everywhere are using this technology today, in the real world, to add value to their operations. Here’s how they’re doing it.

1. Sensors Make Equipment Maintenance More Proactive

In some industries, like automotive manufacturing, the cost of equipment downtime can be as high as $22,000 for every minute a critical machine is offline. Making sure equipment doesn’t fail at a critical moment is a labor- and time-intensive job. At least, that’s how things were before the IoT.

Using equipment built for the IoT, retrofit kits for legacy machines, or a combination of both, manufacturers can leverage sensor data and internet connectivity to make their assembly line equipment proactive about flagging maintenance issues before they stop production in its tracks.

Having access to metrics like operating temperature, vibrations, and mechanical sounds means machine operators have advanced warning of failures. It also makes it easier to see and react to energy use over time, including identifying when machines are using more energy than they should to do the same amount of work.

Findings like these make it easy to spot trouble equipment ahead of time or inform decisions about buying more energy-efficient machines.

2. Artificial Intelligence Improves Quality Control

Quality control is another area where data mobility and analytics makes a real difference to the modern manufacturer. With the right automation tools, manufacturing companies can see a sharp decline in their defect rates and their risk of product recalls. Even better, they can do it without shedding loyal personnel.

One company in Illinois, Kay Manufacturing, has been introducing more and more intelligent automation tools into its facility for decades and still hasn’t lost a single employee in the bargain. Even better, the workers who used to carry out repetitive, time-intensive product inspections are now doing more challenging, more varied and higher-paying work.

Visual inspection technology with artificial intelligence gets better over time at spotting defects as it accumulates data about visual and other cues that can lead to dissatisfied customers, product returns and even full recalls.

In addition to Kay’s successes with automated inspection, another company specializing in glass products realized quarterly savings of $1 million after making the switch to AI-based inspection across their production lines. Computers can perform inspections without AI, but it means “training” them first with thousands and thousands of points of data manually. Machine learning is much more adaptive and capable of improvement over time.

3. Industrial Analytics Makes Enterprise Planning a Snap

It bears repeating: There are lots of moving parts in the manufacturing sector. The introduction of analytics tools and connected infrastructure makes it easy to track these moving parts and reach informed predictions about future trends in business.

When industrial analytics and IoT data come together with powerful enterprise resource planning platforms, the result is a company that can peer into the future of every variable under their roof and beyond. That includes:

  • Outside risks to the supply chain, like social and climate disruption
  • Current and likely future demand for different products and services
  • Factors that compromise workplace safety and may lead to injuries and incidents
  • Current and future fuel and energy consumption throughout the organization
  • Signs of unethical behavior, including security intrusions and in-house malfeasance
  • Material waste and the “health” of current inventory and the raw material supply chain

All of these factors fall under the banner of what many call social sustainability. Social sustainability involves using resources conscientiously and working to reduce one’s business footprint. But it also means collecting enough data and insights that business can go on uninterrupted even when events conspire to slow you down. There’s more than one kind of “sustainable.”

Here are just a few examples of how the IoT supports more proactive enterprise planning through the smarter use of data:

  • Incorporating data about construction and traffic events to avoid delayed shipments
  • Predicting when stores of raw manufacturing materials will run out so there’s time to find a new vendor or another source
  • Identifying wasted effort and energy in-house and helping supply chain partners make their own processes more efficient

For proof that this works, consider findings from McKinsey which indicate that 75% of customers are likely to become repeat customers when companies use big data analytics to predict future purchases and deliver real-time alerts to them.

4. Data Mobility Makes for a Circular Economy

Ultimately, each of these separate pieces contributes to a larger mission: The construction of a more circular economy. This concept means different things in different contexts.

For Philips, a manufacturer of household electronics and industrial products, achieving a circular economy requires better and longer-lasting product designs that can be reused and recycled instead of thrown away. It all starts with data.

You can surface critical data about product failure rates and causes, for example, and use this to bring about design changes that are meaningful for your customers and helps reduce material usage.

Manufacturers of heavy equipment or vehicles, including Caterpillar, receive telemetry in real-time on how their equipment is being used or modified after the point of sale or in the field during a lease, leading to further improvements in design and efficiency.

Industrial Analytics and the Lean Economy

Making manufacturing operations leaner and able to turn out quality products consistently is practically what industrial analytics were invented for. With the “eyes” and “ears” of the Internet of Things, manufacturing companies’ ability to gather and process data will only grow more impressive and more critical in bringing about a leaner, cleaner economy.