Re:Why Wind Turbines Have Three Blades
by Houshalter on Friday May 06, 2016 @11:30AM
(#11644617)
Oh yes, this is just some guys weekend project with a simulator. If I wanted to make the optimal wind turbine, I'd add some random noise in the simulator to account for imperfection in the simulation, and do lots of real world tests. Also I'd allow the GA to change more than just a radial shape. But all that adds difficulty and expense.
In fact I've thought about what the optimal way to do real world experiments is. Assuming you want to minimize them as much as possible, if making real prototypes is expensive.
I think you could use machine learning on the results of real world experiments to invent a model. It would predict how well each design would do. Then you could optimize the design to the machine learned model. Which of course won't be very accurate. But then it will give you a new test to do in the real world, which will give you data to make it even more accurate.
Re:Why Wind Turbines Have Three Blades
by logfromblammo on Friday May 06, 2016 @11:39AM
(#11644679)
You would likely need to do one of every N iterations as a real-world test, and significantly increase the reward for winning a real-world test over a simulated-world test, such that the winners and close runners-up of the real-world tests effectively earn immunity from complete elimination until after the next real-world test round.
Additive volume-printer or subtractive CNC machinery would almost be required to make the physical test models.
A more intricate genetic algorithm that runs a 3D wind model and accounts for the cost of manufacture would almost certainly produce some more novel solutions that completely demolish our preconceived notions of what turbines should look like, just like the "jellyfish" cross-section. But it would also probably not effectively scale beyond the model size. Genetic algorithms almost always exploit any previously hidden little flaws you may have in your model simulator, such as the rounding error on floating point numbers at the limit of their precision, or even the way in which you represent airflows. They evolve to maximize performance in the modeling environment, so if your model is not perfect, the solution does not always translate to reality.
As such, you always have to test the evolved solutions in the real world before you can say they are better than the designed solution.