Comparing SVR and MLP neural network for modelling and fault detection of KAHAK wind farm
In this paper we use SVR and MLP Neural Network for modelling and fault detection of KAHAK wind turbines. Electrical subsystems is our purpose for modelling and fault detection. We have actual data and real parameters about 2.5 MW wind turbines that installed in KAHAK wind farme. In first step we modelled and fault datect with two approach, Support Vector Regresion (SVR) and Multi Layer Perceptron (MLP), in second step we compare model error and accurase of SVR and MLP approach, that we can see SVR approach is better than MLP approach according modelling error. We use MATLAB software for this work.
- حق عضویت دریافتی صرف حمایت از نشریات عضو و نگهداری، تکمیل و توسعه مگیران میشود.
- پرداخت حق اشتراک و دانلود مقالات اجازه بازنشر آن در سایر رسانههای چاپی و دیجیتال را به کاربر نمیدهد.