Environment

Wind turbines that use human-like learning to improve efficiency

Wind turbines that use human-like learning to improve efficiency
Chinese researchers have developed a biologically inspired control system for wind turbines (Photo: Gizmag)
Chinese researchers have developed a biologically inspired control system for wind turbines (Photo: Gizmag)
View 2 Images
Chinese researchers have developed a biologically inspired control system for wind turbines (Photo: Gizmag)
1/2
Chinese researchers have developed a biologically inspired control system for wind turbines (Photo: Gizmag)
Chinese researchers have developed a biologically inspired control system for wind turbines
2/2
Chinese researchers have developed a biologically inspired control system for wind turbines

Wind turbines are exposed to a wide variety of wind conditions, from zephyrs to gales, and ensuring the maximum amount of power is extracted from the turbine across a range of wind speeds is a difficult task. Chinese researchers have now developed a biologically inspired control system that uses “memory” of past experience to learn how to best adapt to changing conditions.

Wind turbines are designed with a rated power and a rated speed, which is the wind speed at which the turbine will produce its rated power. For example, a 10 kW wind turbine with the most common rated speed of 25 to 35 mph (40 to 56 km/h) will only generate the designated 10 kW at those speeds.

When the wind falls below or exceeds this ideal range, control systems kick in to alter the turbine system to help keep power efficiency high in low winds and protect the turbine from damage in high winds. These changes can include altering the angle of the blades, modifying the electromagnetic torque of the generator.

Turbine control systems are comprised of three basic elements – sensors to gather data, actuators to carry out changes to the turbine system, and algorithms to coordinate the actuators based on the data supplied by the sensors. While these control system algorithms often rely on complex computation models of the turbine’s behavior, a group of Chinese researchers have developed a control system inspired by human learning models.

The new control system, which is described in the Journal of Renewable and Sustainable Energy uses memory of past control experiences and their results to generate new actions. While simulations of the system produced poor initial results, it quickly learned how to improve to match the performance of a traditional control system, while being much simpler.

The researchers claim their “human-memory-based method holds great promise for enhancing the efficiency of wind power conversion.”

Source: Journal of Renewable and Sustainable Energy

3 comments
3 comments
Island Architect
Here we go again, wind energy guys talking in platitudes about efficiency or more efficiency without ever giving us a number.
This one of the most disgusting displays of pathetic enginering in the history of man. Typically Engineers will kill to get a .5% but with these 3 bladed flyers no one ever produced valid numbers. They just beat around the bush.
Bill Allison carefully determined the efficiency in his experiments. He hit 59%. http://www.altenergymag.com/emagazine.php?art_id=1456
And he was justifiably full of derision and scorn for those 3 bladed, 1946 designs found in the bottom of the drawing files at NASA.
What do they get? 20% if they are lucky?
When will the lemming instinct give way to proper development and testing?
When T Boone Pickens announced on Ted this week that he lost $150 millinon dollars on that farm of wind pigs, declaring that Wind Turbines are far to costly and that CNG was the answer what was really going on? This is an important question.
His announcement should be earth shattering because, he joined the lemmings, and showed them to be off base at great personal cost.
Is Boone from Texas and Oklahoma and is he devoid of understanding of proper Engineering testing and development because of that?
Or is he superslick and trying to get us to all buy his CNG and go that route.
If he is sincerly interested in doing this properly, and if he is sincerly interested in advancing the world and science and leading us into the new millenium, a new world driven by intelligence rather that political posturing then maybe he can set up a prize for perfecting the wind engines.
Progressive is probably all petered out by now but there has been too much lemingness in all of this.
Bill was quick to point out that propellers are mechanical devices designed to put power into the atmosphere while his designs were resistors designed to extract power from the atmosphere.
He got his best results with dead flat blades canted at 8deg, highly polished stainless steel. The design section is triangular somewhat similar to Sam Williams blades used in his mini turbines that power the cruise missile.
The design was made by breaking the sheets to the proper angles in section.
Prove him wrong! I'll bet you can't.
His derision, scorn, and laughter was on the mark.
Bill Dickens

Gadgeteer
Here we go again, indeed. Prove your idol William Allison right. I bet you can't. Why haven't his patents been put to use anywhere in the world? At about 35 years old, they're expired, so any company can use them without paying any royalties. If his design had even a fraction of the advantages you keep claiming, surely somebody would be copying the design.
Slowburn
re; Island Architect
When Alexander Graham Bell was trying to invent the airplane he built a wind tunnel to test his lift generating ideas. this wind tunnel was flawed in a manner that made it give erroneous reading of lift. The Wright brothers discovered that using Bells numbers they they did not get a workable design, they built a wind tunnel of a different design that did not have the same flaw as Bell's and it was the Wright brothers that invented the airplane.
Bill Allison's efficiency numbers have never been matched this in itself does not prove nor seriously suggest fraud. Also his perfectly flat blade designs can not be scaled up and maintain the same effiniency.