Technology 3 min read

New AI-Designed Heat Pumps Consume Less Energy

A novel technology developed by researchers from EPFL research institute in Switzerland could reduce the energy consumption of heat pumps by up to 25 percent.

Image courtesy of Pixabay

Image courtesy of Pixabay

Researchers have developed the next-generation heat-pump compressors using artificial intelligence. With this new method, we can cut the power requirement by as much as 25 percent.

Heat pumps have gotten better with advancements in technology. Not only do the current pumps work well, but they have become more environmentally friendly.

Still, there’s a substantial room for improvement.

For example, engineers can replace the conventional compression system with microturbocompressors. That way, the heat pumps’ energy requirement can be reduced by up to 25 percent, which helps the environment at the same time.

What makes microturbocompressors special, you ask? Well, aside from being more efficient than piston devices, they are also ten times smaller.

However, incorporating these mini components into heat pump designs had always been a challenge. Their tiny diameter, which is less than 20mm and fast rotation speed higher than 200,000 rpm, has raised several complications in the past.

Now, the researchers at EPFL’s Laboratory for Applied Mechanical Design on the Microcity campus have developed a new method of adding turbocompressors to a heat pump.

Using Artificial Intelligence to Create More Efficient Heat Pumps

The researchers used a machine learning process called symbolic regression to come up with some equations. Using these simple equations, the team could quickly calculate the optimal dimensions of a turbocompressor for a specific heat pump.

This new method simplifies the first step in designing turbochargers – knowing the ideal size and rotation speed for a pump. By understanding the initial estimate, engineers can shorten the design time.

Engineers currently use design charts to size their turbocompressors. Unfortunately, the charts’ accuracy reduces as the equipment gets smaller. Furthermore, it’s outdated, not managing to keep up with the latest technology.

That’s why two EPFL Ph.D. students, Cyril Picard, and Violette Mounier developed an alternative.

The researchers fed over 500,000 simulation results into machine-learning algorithms to generate equations which replicated the chart but with more advantages.

The equations prove to be more reliable, detailed, and about 1,500 times faster than the chart. Also, it enabled the engineers to skip some steps of the conventional design process.

With this new method, companies will find it easier to use the micro turbocharger technology in creating more efficient heat pumps.

In a statement, lead researcher of the project, Jürg Schiffmann said:

“We have already been contacted by several companies that are interested in using our method.”

The research recently won the Best Paper Award at the 2019 Turbo Expo Conference at the American Society of Mechanical Engineers.

Read More: New Portable Vacuum Gauge Gives Boost to Semiconductors

First AI Web Content Optimization Platform Just for Writers

Found this article interesting?

Let Sumbo Bello know how much you appreciate this article by clicking the heart icon and by sharing this article on social media.


Profile Image

Sumbo Bello

Sumbo Bello is a creative writer who enjoys creating data-driven content for news sites. In his spare time, he plays basketball and listens to Coldplay.

Comments (0)
Most Recent most recent
You
share Scroll to top

Link Copied Successfully

Sign in

Sign in to access your personalized homepage, follow authors and topics you love, and clap for stories that matter to you.

Sign in with Google Sign in with Facebook

By using our site you agree to our privacy policy.