Redefining vertical axis wind turbines through machine learning

WhatsApp Group Join Now
Telegram Group Join Now
Instagram Group Join Now

EPFL (École Polytechnique Fédérale de Lausanne) researchers have used a genetic learning algorithm to identify optimal pitch profiles for the blades of vertical axis wind turbines. Vertical axis wind turbines With their high energy capacity, have been prone to wind gusts until now.

A descriptive open access paper has been published. Nature Communications.


When you consider Today's industrial wind turbines, You probably picture a windmill design, technically called a horizontal axis wind turbine (HAWT). But the first wind turbines, developed in the Middle East around 8Th Century, vertical axis wind turbines (VAWT) were used for grinding grain, meaning they spin perpendicular to the wind rather than parallel.

Because of their slower rotation speed, VAWTs are less noisy than HAWTs and achieve higher wind energy density, meaning they require less space both on and offshore for the same output. Is. The blades are also friendlier to wildlife: because they rotate from the back instead of cutting from above, they are easier for birds to avoid.


With these advantages, why are VAWTs largely absent from today's wind energy market? As Sébastien Le Fouest, a researcher at the School of Engineering's Unsteady Flow Diagnostics Lab (UNFOLD), explains, it comes down to an engineering problem – controlling air flow – which he sees as sensor technology and machine learning. can be solved by a combination of . In a recently published paper Nature CommunicationsLe Fouest and Karen Mulleners, head of UNFOLD, describe two optimal pitch profiles for VAWT blades, which achieve a 200% increase in turbine efficiency and a 77% reduction in structurally hazardous vibrations.




EPFL's experimental VAWT blade Image credit: © UNFOLD EPFL CC BY SA. Click the press release link for more and larger images.

“Our study presents, to the best of our knowledge, the first experimental application of a genetic learning algorithm to determine the optimal pitch for a VAWT blade,” notes Le Fouest.

Turning an Achilles heel into an advantage

Le Faust explained that while Europe's installed wind energy capacity is growing by 19 gigawatts per year, this figure needs to be closer to 30 gigawatts to meet the UN's 2050 targets for carbon emissions. can be fulfilled.


“The barriers to achieving this are not financial but social and legislative – wind turbines have little public acceptance due to their size and noise,” he said.

Despite their advantages in this regard, VAWTs suffer from a serious drawback: they only work well with moderate, continuous airflow. A vertical axis of rotation means that the blades are constantly changing direction with respect to the wind. A strong gust increases the angle between the airflow and the blade, creating a vortex in a phenomenon called dynamic stall. These vortices create transient structural loads that the blades cannot carry.

To combat this lack of gust resistance, the researchers mounted sensors on an actuating blade shaft to measure the air forces acting on it. By moving the blade back and forth at different angles, speeds and amplitudes, they produced a series of 'pitch profiles'. Next, they used a computer to run the genetic algorithm, which performed more than 3,500 experimental iterations. Like an evolutionary process, the algorithm selected for the most efficient and robust pitch profiles, and recombined their traits to produce new and better 'offspring'.

This approach allowed the researchers to not only identify two pitch profile series that significantly increase turbine efficiency and robustness, but also turn VAWTs' biggest weakness into a strength.

“Dynamic stall – the same phenomenon that destroys wind turbines – can drive the blade forward on a small scale. Here, we'd really use dynamic stall to our advantage by moving the pitch of the blade forward to generate power. are,” LeFoist explained. “Most wind turbines angle the force produced by the blades upwards, which doesn't help the rotation. Changing the angle not only creates a smaller vortex – it simultaneously pushes it away at the right time. is, resulting in a second region of downstream power generation.”

gave Nature Communications The paper represents Le Fouest's PhD work in the UNFOLD lab. Now, it has received a BRIDGE grant from the Swiss National Science Foundation (SNSF) and Innosuisse to build a proof-of-concept VAWT. The goal is to install it outdoors, so it can be tested as it responds to real-world conditions in real time.

“We hope that this method of controlling airflow can bring efficient and reliable VAWT technology to maturity so that it can eventually be made commercially available,” LeFoust said.

**

One certainly hopes that this development will have room to replace many of the dangerously ugly and noisy HAWTs. While wind is a notoriously intermittent source of electricity, there is a lot of momentum in the industry that sucks up huge amounts of ratepayers and taxpayers. Stamping out rent-seeking projects like wind turbines can serve as an example of how politically enforced rent-seeking schemes have harmed the economy and its citizens.

It would be great if the developers could say that the technology could stand on its own economically. But no such comment has been made in the press release. The reality is that they can only accomplish a little when the winds blow.

By Brian Westenhaus New Energy and Fuels

Read more top from Oilprice.com:

WhatsApp Group Join Now
Telegram Group Join Now
Instagram Group Join Now

Leave a Comment