Modern wind turbines are capable of producing thousands of watts of energy, all without polluting the air or destroying our mountains. But in order for wind power to compete with the entrenched fossil fuel and nuclear energy industries, it has to be cost-effective, which means it has to be efficient.
Wind, on the other hand, likes to be unpredictable. Depending on the weather, wind turbines can face whispering breezes or gale-force gusts. Such variable conditions make extracting the maximum power from the turbines a tricky control problem, but a collaboration of Chinese researchers in a new study may have found a novel solution to this situation.
The study, recently described in the American Institute of Physics’ Journal of Renewable and Sustainable Energy, investigates the benefits of a biologically inspired control system that would be able to memorize its responses to changing wind speeds. In essence, the research team developed a human-inspired learning model.
In simulations, the controller showed initially poor results, but quickly learned how to improve, matching the performance of a more traditional control system overall. If equipped with this kind of of artificial intelligence, wind turbines will be able to automatically make changes to the turbine system, such as modifying the angle of the blades or the electromagnetic torque of the generator. This will not only increase energy output during periods of low wind, but also protect the turbine from damage in high winds.
The memory-based system is attractive because of its simplicity, the researchers write, concluding that “the human-memory-based method holds great promise for enhancing the efficiency of wind power conversion.” As for wide scale implementation, that is likely still a bit off in the future, but the system does look promising.