Can the digital twin transform manufacturing

Until the beginning of the 21st century, the only way to gain detailed information about the status of any operating industrial equipment was to be in physically proximity and have the ability to inspect it. Today, increased computing power and connectivity are making it possible to virtualise this task by creating and maintaining a digital representation, or “digital twin”, of any piece of real equipment, and thus of any plant or engine.

“The ultimate vision for the digital twin is to create, test and build our equipment in a virtual environment. Only when we get it to where it performs to our requirements do we physically manufacture it. We then want that physical build to tie back to its digital twin through sensors so that the digital twin contains all the information that we could have by inspecting the physical build,” says John Vickers, NASA’s leading manufacturing expert and manager of NASA’s National Center for Advanced Manufacturing.

Some elements of this digital-twin concept are already present in industry. CAD 3D models, for example, are rich and accurate digital representations that can be used to ensure different parts fit together both statically and dynamically. Manufacturing simulations can also determine whether virtual designs can actually be built using the machines available. Last but not least, real-time data feeds from sensors in a physical operating asset are now used to know the exact state and condition of an operating-asset product, no matter where it is in the world.

The real advantage of the digital twin, however, materializes when all aspects, from design to real-time data feed, are brought together to optimize over the lifetime of the asset. An accurate digital description of a physical asset, for example, does not just cut prototyping or construction costs, it also enables to predict failure more easily once real-time data is fed into the model, thus reducing both maintenance costs and downtime.

In the same way, taking a digital approach for all critical parts of a production line enables the creation of a digital twin of the entire production system, opening new ways to improve productivity. GE, for instance, is currently piloting a “digital wind farm” concept, which it uses to inform the configuration of each wind turbine prior to procurement and construction. Once the farm is built, each virtual turbine is fed data from its physical equivalent, and software enables to optimize power production at the plant level by adjusting turbine-specific parameters, such as torque of the generator or speed of the blades. The hope is to generate 20% gains in efficiency. “For every physical asset in the world, we have a virtual copy running in the cloud that gets richer with every second of operational data,” says Ganesh Bell, chief digital officer and general manager of Software & Analytics at GE Power & Water.“The Digital Twin is not a generic model. It’s a collection of actual physics-based models reflecting the exact operating conditions, such as lifing, performance and failure modes, in the real world.” Similarly, Black & Decker—a manufacturer of power tools used worldwide—has equipped a factory with digital twins of assembly lines and materials. They are reporting labor utilization improvements of 12% and a 10% increase in throughput.

As if often the case with optimization opportunities, the more vertically integrated the actor, the easier it will be to capture all the benefits resulting from a system-wide digital-twin approach. While this puts large corporations in a strategic place to demonstrate proof of concept, it will not be enough to deliver economy-wide gains. For that to happen, a digital-twin approach is needed along entire supply chains, many of which are becoming more complex as a result of globalization, new manufacturing techniques and, in industries like power generation, liberalization policies.

Assisting and supporting small suppliers in adopting a digital approach is therefore key. With that in mind, the Digital Manufacturing and Design Innovation Institute (DMDII)—a US federally-funded research and development organization—has recently issued a project call to demonstrate technologies that can provide real-time, dynamic visibility (or digital twins) from all supply-chain participants, especially small manufacturers. Another important element will be to ensure that early adopters are able to accommodate new digital-twin models from their suppliers or partners as these become available. GE’s aforementioned digital wind farm, for example, is designed to accommodate and optimize the digital-twin turbines of other manufacturers.

The digital twin concept is not new; it was first introduced by Michael Grieves at the University of Michigan in 2001. What is new is that we are now at a stage where industrial connectivity and machine intelligence are advanced enough to demonstrate the large-scale advantages of the method. As pilots get deployed and results come in, interest in the technique is bound to increase.

This article is published in collaboration with GE Lookahead. Publication does not imply endorsement of views by the World Economic Forum.

To keep up with the Agenda subscribe to our weekly newsletter.

Author: Dr Michael Grieves is a writer at GE Lookahead. 

Image: An employee types on a computer keyboard. REUTERS/Stoyan Nenov.