Makine Öğrenimi Kullanarak Bir Mekanik Jiroskobun Yalpalama Tahmininde Zaman Serisi Modeli.

Due to the gyroscopic torque production ability, mechanical gyroscopes are frequently used for balancing fully suspended or single/two-wheeled land vehicles such as airplanes and spacecraft. They produce gyroscopic torque thanks to the flywheel rotating at high speed. Precession is required to control this torque. In the study, 415 precession data were collected by performing a rigid dynamic analysis of a mechanical gyroscope. A non-linear autoregressive artificial neural network (NAR) is used to estimate this velocity. In the model obtained, the correlation value was 0.998 and the root mean square of error (RMSE) value was 0.016 rad/s. A high linear relationship was detected between the model output and the data set. The NAR network has eliminated the need for any pre-processing on the data. The network parameters used and the estimation performances obtained with this model are presented in the study. [ABSTRACT FROM AUTHOR]