Research Output
Investigation of MPC performance for wind turbine system during wind speed uncertainty
Double sigmoid activation function for fault detection in wind turbine generator using artificial neural network
1 - 2 of 2
Publication
Real-time implementation for wind turbines (WTs) needs a controller that could explicitly formulate the system constraints and uncertainty in the design process to avoid undesired behavior or breakdown. Model-Predictive-Control (MPC) approach will be used in this research due to its ability to cover actuator and state constraints as well as multivariable control in a more convenient way. To investigate the impact of ad-hoc constraints and wind speed uncertainties, the MPC controller will first be developed. This paper will observe the effect on wind turbines (WT) during uncertainty happen. Multiple uncertainties are simulated to investigate the behavior of the wind turbine system. The simulation results using MATLAB Simulink output are expected to indicate that the MPC controller can ensure the system stability to meet the desired output while satisfying all of the constraints. During the presence of uncertainty, it shows that the MPC controller takes time to stabilize the system.
No Thumbnail Available
Publication
The activation function has gained popularity in the research community since it is the most crucial component of the artificial neural network (ANN) algorithm. However, the existing activation function is unable to accurately capture the value of several parameters that are affected by the fault, especially in wind turbines (WT). Therefore, a new activation function is suggested in this paper, which is called the double sigmoid activation function to capture the value of certain parameters that are affected by the fault. The fault detection in WT with a doubly fed induction generator (DFIG) is the basis for the ANN algorithm model that is presented in this study. The ANN model was developed in different activation functions, namely linear and double sigmoid activation functions to evaluate the effectiveness of the proposed activation function. The findings indicate that the model with a double sigmoid activation function has greater accuracy than the model with a linear activation function. Moreover, the double sigmoid activation function provides an accuracy of more than 82% in the ANN algorithm. In conclusion, the simulated response demonstrates that the proposed double sigmoid activation function in the ANN model can effectively be applied in fault detection for DFIG based WT model.