In the heart of Paris, a short walk from the city’s storied opera, GE engineers are busy coding software that will allow them to create “digital twins” of machines. These virtual representations of the real machines live in the cloud and use as their lifeblood data captured from their parts. The engineers are partnering with Ansys, a leader in engineering simulation software, to digitally play out different scenarios, such as running an aircraft engine longer and in a hotter or wetter environment. They the use the insights gained from these tests to maximize output and minimize downtime by spotting problems before they lead to an unplanned outage.
This predictive maintenance is not only about using physical sensors on the machines. It is also about using virtual sensors, especially in places where you can’t use a physical sensor. A virtual sensor results from the ability to guess fairly precisely a value (such as temperature or pressure) by using other data from sensors and smart algorithms based on historical data or models.
For instance, GE engineers have developed a digital twin of the Haliade 150-6 wind turbine’s yaw motors, which enable the 6-megawatt turbine to rotate and position itself into the wind. This digital twin simulates, through virtual sensors, the temperature at various parts of the motors.
Why is that so important? “The better you monitor the temperature, the better you know the impact of the way you are using it,” says Hervé Sabot, engineering director at GE’s Digital Foundry in Paris. “The challenge here is to boost the capacity of our customer’s assets to avoid outages and have them perform as fast as possible.”
One way to keep tabs on the motors involves continuously checking their internal temperature, which is difficult to estimate.
For Sabot and his team, tracking the temperature was an exciting challenge. They decided to use Ansys simulation tools to compute the motor’s internal temperature from a model. They accomplished this by tracking the electrical current feeding into the wind turbine motors.
Using algorithms built on Predix, GE’s software platform for the industrial internet, and a modelling approach developed by Ansys, they can now estimate the motor temperature at any given moment. At the Foundry, they can also monitor how the motors perform under different strains over time and learn more about operating them at peak efficiency. In the field, engineers are able to use an app with a dashboard connected to the twin to monitor the motors’ temperature and decide whether to pull back on the power or push the motors a little harder. “For the simulation, thanks to the digital twin we only need to know the current to understand the temperature and optimize the use of the motor,” Sabot says.
Right now, engineers are using simulated data at the Foundry to perfect the app before moving it into the field, where some 1.2 million GE digital twins of jet engines, gas turbines and locomotives are already working. As with these wind turbines, any industrial assets could benefit from digital twins and virtual sensors. That will mean not only even more efficient and sustainable assets but also a safer, more comfortable experience for the crews who are tasked with keeping them healthy.