Could we soon be seeing semi-sentient Wind Turbines, that are able to learn and use that learning?
One of the problems of most conventional wind turbines is that they have only a limited set of automatic reactions to changes in wind speed. That’s powering down when the wind speed is too low or too high and adjusting the blade angles and/or the electromagnetic torque of the generator. These relatively simple adjustments are designed to harvest the maximum allowable power once winds have attained a certain speed; the rated speed. These changes help keep the power efficiency high in low winds and protect the turbine from damage in high winds. However even these relatively simple adjustments rely on complex and expensive models of the turbine’s behavior.
That may be set to change as a group of Chinese researchers decided to experiment with a different approach. They developed a biologically inspired control system, described in the American Institute of Physics’ Journal of Renewable and Sustainable Energy, that used the memory of past control experiences and their outcomes to generate new actions. In simulations, the controller showed initially poor results but quickly learned how to improve, matching the performance of a more traditional control system overall. So what’s the advantage then? The memory-based system is attractive because of its simplicity and the researchers concluded that “the human-memory-based method holds great promise for enhancing the efficiency of wind power conversion.”
There’s not a great deal of additional information about where this is likely to take wind turbine production, but anything that lowers the cost of production and maintenance must be a good thing.
More information: “A Bio-inspired Approach to Enhancing Wind Power Conversion” is published in the Journal of Renewable and Sustainable Energy, provided by the American Institute of Physics.
