An ideal wind farm will have all turbines rotating at the same blade angle * in a similar way. The blades of various turbines rotate with variable speed. As a result, the blade angle for each wind turbine is different. Given the case of 4 wind turbines, each 100 meters apart and forming a blade angle of ө1, ө2, ө3 and ө4, we can use OpenCV to control the blade angles of each turbine using suitable computer vision algorithms and consider distance, location and other factors such as webcams that are used to control them. The idea is to get the exact value of the formed blade angles.
* Blade angle (here) is the angle formed between the first blade and the imaginary horizontal axis, measured in the counterclockwise direction.
I hope this gives clarity.
In OpenCV, I have the following methodology:
Get image / frame use canny edge detection - use Hough lines transforms to find the lines that recognize the blades, - find the angles of the blade - go to the next frame.
My problem here is . I do not know how to recognize only blade lines after searching for Hough strings. I know that Hough probability lines return “lines,” that is, the endpoints of all detected lines. But how do I know which lines belong to the blades? Another problem I am facing is how exactly should I draw an imaginary horizontal line through the hub to measure the angle of the blade.
- , . : , 4 . . , , . ? .
- ? openCV . .
: ө1 - :
, , :
