Future Factories: How AI enables smart manufacturing

Today’s consumers are pickier than ever. They want customized, personalized, and unique products over standardized ones and prefer local, smaller producers over large-scale global manufacturers.

Factories, power plants, and manufacturing centers around the world must rely on automation, machine learning, computer vision, and other fields of AI to meet these rising demands and transform the way we make, move, and market things.

Since the industrial revolution, factories have been optimized to mass produce a few products rapidly and cheaply to satisfy global demand. “The largest inefficiency that most manufacturers face is inflexibility,” says Jim Lawton, Chief Product & Marketing Officer of Rethink Robotics, maker of collaborative industrial robots. “Traditional industrial automation requires hundreds of hours to reprogram, making it very impractical to change how the task is performed.”

Catering to finicky consumers is not the only challenge confronting modern factories. Costs of production in traditionally affordable countries like China and Mexico are rising. Oil and gas industries have been hit incredibly hard by historically low oil prices, driving the need for further efficiencies and cost reduction.

In virtually all factories, poor demand forecasting and capacity planning, unexpected equipment failures and downtimes, supply chain bottlenecks, and inefficient or unsafe workplace processes can lead to resource wastage, longer production periods, low yields on production inputs, and lost revenue. Manufacturers are also strapped for qualified labor, both skilled and unskilled, as older employees retire, younger generations lose interest in manufacturing jobs, and immigration policies tighten.

Prabir Chetia, Head of Business Research and Advisory at global analytics firm Aranca, details the current dilemma faced by many manufacturers around the world:

Innovative manufacturers already use artificial intelligence to tackle these many challenges. Here are the key ways that “Industry 4.0”, the latest trends in smart factories, leverage automation, data exchange, and emerging technologies:

Rethink Robotics, founded by robotics pioneer Rodney Brooks, advocates the “cobot” model where humans and robots work side by side for maximum effectiveness. While industrial robots have long performed heavy lifting and tedious work on assembly lines, they’re typically designed for a single tasks and require hours to reprogram. Baxter and Sawyer, Rethink’s smart collaborative robots, are able to learn a multitude of tasks from demonstrations, just like their human counterparts can.

“Training a robot is nearly as simple as training a human,” claims Chief Product & Marketing Officer Jim Lawton. “Companies that don’t have programming expertise on staff and can’t afford to spend hundreds of thousands of dollars on a traditional industrial robot can instead leverage more affordable, flexible automation and adapt to market changes.”

Industrial equipment is typically serviced on a fixed schedule, irrespective of actual operating condition, resulting in wasted labor and risk of unexpected and undiagnosed equipment failures. Once instrumented with sensors and networked with each other, devices can be monitored, analyzed, and modeled for improved performance and service. An industry leader in the space, GE enables manufacturers to create “Digital Twins”, or physics-based virtual models of large-scale machinery, on their industrial cloud platform, Predix.

“Twinning” a piece of equipment allows human operators to constantly monitor performance data and generate predictive analytics. According to Marc-Thomas Schmidt, Chief Architect of Predix, nearly 650,000 twins are currently deployed and range widely in complexity. Complex twins like those of gas turbines interpret data from hundreds of sensors, understand failure conditions, track anomalies, and can be used to regulate production based on real-time demand.