Anaheim, Calif. — IBM's expert on the Internet of Things says cognitive computing, using sensors and controllers, can give factory technicians accurate predictions of coming problems by giving them probabilities of what could go wrong.

Krish Dharma said that level of technology is in the early stages of adoption, but the pace has picked up significantly. He thinks it will be five to 10 years before it becomes widely used.

"It's going to enable the technician to make the best decision," Dharma said. But the computer system is not going to make all the decisions, he added.

Krish is director of industry solutions for IBM's U.S. industrial market, focusing on automotive and aerospace, and defense. He spoke at an Industry 4.0 conference held May 10 at Antec in Anaheim.

Officials from machinery makers joined information technology gurus at the conference to describe a fully connected manufacturing world. They said many innovations, such as smart molds and remote analysis by an equipment company's experts anywhere around the world, will become standard features on new machines, not just options.

Bruce Catoen, chief technology officer at Milacron Holdings Corp., made an analogy with intermittent windshield wipers: Nobody is going to pay extra for that feature.

The term Industry 4.0 is more commonly used in Europe than the United States, so some speakers also used the Internet of Things moniker. "The IOT is a journey, it's not an event. So you will see continuous improvement on that," Catoen said.

Jurgen Giesow, director of engineering and technology at Arburg Inc. in Rocky Hill, Conn., said the concept of an Internet of Things may be different for each company.

"We need a combination of complexity and flexibility, that's really what Industry 4.0 is giving us," he said.

IBM made history with Watson, a supercomputer with artificial intelligence that won on "Jeopardy." So computers can be "smart" and can use reasoning skills. Dharma painted a future of computer systems helping humans run factory networks better — from manufacturing and the supply chain to marketing to closely teaming with customers.

Dharma, who is based in Costa Mesa, Calif., said the big problem with manufacturing is "tribal knowledge," or the knowhow of company veterans, when it doesn't get passed down to others. "Most often you don't capture the solutions from prior problems," he said.

And skilled veterans can leave a company at any time, taking the knowledge with them. Dharma said cognitive computing systems can hold onto the knowledge, after being "trained" by experienced workers. "You're also creating machine learning modules," he said.

For example, if the molding machine is running too hot, the cognitive system can analyze the data and say there is a 90 percent chance that the one issue is the cause, then list some other possible reasons.

Catoen Sensors everywhere

The price of "big data" is coming down. Sensors are everywhere. Cloud computing common. "The prices of these things have dropped significantly, and that's what has enabled the IOT to become pervasive everywhere you see it," Dharma said. "That's what's really driving the IOT explosion."

Another Industry 4.0 executive, Tom Craven, said the difficulty of figuring a return on investment makes some companies shy away from adopting a fully interconnected operation. "There has to be a tangible financial benefit to this," he said.

Craven is vice president of product strategy at RRAMAC Connected Systems, a company in Plymouth, Minn., that provides remote monitoring, analytics and mobile apps. Before that, he spent 20- years at GE Intelligent Platforms, helping interface factory hardware and software.

He suggested starting small, then define measurable revenue and cost savings figures, before adding more capabilities. "You want to limit the scope of phase one," Craven said.

Craven said a good, cloud-based network for companies is more secure for remote connectivity than the VPN (virtual private network). VPN opens your company up to other people to get into it and start browsing the network, he said.

Alex Utracki, director of process technology at compounding extruder maker Coperion Corp. said that, for plastics machinery, the devices are not new: feeders, weigh scales, pressure and temperature measurements. It is connecting them and making decisions based on the data elevates it to smart-factory status.

In the compounding plant of 2010, he said, information flow was slow, and companies did not share between plants. Workers did physical tasks. Operators placed orders for materials, then manually loaded them; at the end, operators would create a barcode, stick it on, then weigh them and ship it out.

Right now, Utracki said, there's an operator on each line, tasked with monitoring the process. But what if he or she can go to the warehouse to get more material? That's possible through integrating the system. No duplicating of efforts.

Industry 4.0 also can help second- and third-shift employees, who may not have technical support people, Utracki said. These people are "flying blind," he said. Meanwhile, bad product is getting made.

At Coperion, Utracki's team handles a new process laboratory in Pitman, N.J., and provides training and process expertise for customers.

He said augmented reality is next, where machinery makers can take instructions about how to do a complex operation, such as disassembling a pelletizer head, and superimpose it onto a tablet in the field.

Milacron's Catoen called the Industry 4.0 era "exciting times because they're challenging times for us." He said there have not been big machinery changes for some time. However, he said: "We're seeing a huge change in the complexity of making parts."

A 'more complex' work cell

Catoen said molding parts, like packaging, lighter, with thinner walls, has made major reductions in costs. At the same time, cavitation has increased over time, said Catoen, who worked at Mold-Masters Ltd. when Milacron bought the hot-runner specialist in 2013.

"And the work cell is getting more complex on top of that," he said, with more devices connected to the injection press. Catoen said it's not easy to control, and if the cell is not coordinated right, he said it's like a "bad high school band."

The machinery company can support what Catoen called "all of these profit levers" such as service support, predictive failure and maintenance and shipping, knowing out-of-spec yields, reducing energy consumption, balanced filling, lower labor costs on some parts and remote monitoring.

But the Internet of Things must be simple to use, Catoen said, and he said that is what machinery makers look at when developing products.

"We spend a lot more time serving machinery online now than we do in person," he said. "So it's absolutely key today that our machinery be connected."

Milacron is embedding sensors into its equipment right now, Catoen said. He said Milacron's Smart Mold takes the last remaining area of a fully connected work cell — the mold. "For us, we view the mold as the core of the work cell.," he said. The company has been working heavily on sensor technology in the tool, he added.

He said the Smart Mold can determine running time, cycle time, giving prompts for maintenance.

Cateon said the molder's big customers could use the technology to help locate molds when they run at lots of custom molders.

Jim Mitchell, national sales manager at Wittmann Battenfeld Inc.'s molding machines division, agreed that connecting up the mold is key.

He said the goal of his company's version, Witmann 4.0, is one single access point in the controller, then a central router and out to the cloud. "We can remotely access every single component in one spot," Mitchell said.

Wittmann Batttenfeld introduced the CMS (condition monitoring system) at K 2016. Sensors measure key injection press machine data, process it through special process control software, and analyze it using the new Unilog B8 controller.

Michell said the company also has technology for verifying a mold to make sure it fits in the right press, and has the right end-of-arm tooling.

Wittmann Battenfeld has vibration sensors on the injection unit that can "hear" harmonics and sense vibration, showing variation in check-ring or screw wear.

On the blown film side, Sebastian Hunnefeld, product manager at Windmoeller and Hoelscher Corp. in Lincoln, R.I., explained W&H's version, Packaging 4.0. A few years ago, he said, Germany-based W&H launched a major push to measure everything going into the system. European governments drove the effort and gave funding to machinery producers to make their equipment more efficient, he said.

"We learned that actually, maintenance was interested in the sensors on the machine," Hunnefeld said.

Sensors and measuring devices put onto W&P film machines monitor performance data. Every roll of film can be precisely identified. Plastic film and stretch wrap have become a commodity, he said — but one that plays a key role in commerce: Reducing food waste and bundling bulk goods for shipping.

"A lot things get impacted a little bit when you throw away a banana," Hunnefeld said. He showed Industry 4.0 attendees of a stretch-wrapped pallet of goods tilting over on a truck.

W&P machines cast film machines than can stretch film using just enough material so the film stays together in transit, he said. The entire production system, through the winders, must be tied together.

Joachim Kragl, director of advanced molding systems and processing at Engel North America in York, Pa., outlined Engel's Inject 4.0 smart-factory technology, through the iQ software products that he said can can give molders better parts, and less scrap.

It happens in real time, as you inject the plastic, Kragl said.

"It makes a more consistent process by making adjustments each and every shot," he said.