Characteristic of Fuzzy, ANN, and ANFIS for Brushless DC Motor Controller: An Evaluation by Dynamic Test

Brushless DC (BLDC) motors are the most popular used by industry because they easy to control. BLDC generally controlled artificial controls such as Fuzzy Logic Controller (FLC), Artificial Neural Network (ANN), and Adaptive Neuro-Fuzzy Inference System (ANFIS). However, performance of control system in previous studies was compared separately with their respective parameters, making it difficult evaluate comprehensively. Therefore, order investigate characteristic Fuzzy, ANN, ANFIS, this article provides a comparison these controls. Two scenarios dynamic tests conducted under constant torque-various speed speed-various torque. By testing, characteristics ANFIS can be observed real applications. The testing parameters are: Settling Time, Overshoot Overdamp (in graph average value), then statistic Integral Square Error (ISE), Absolute (IAE), Time (ITAE), Mean (MAE). test result scenario 1 showed that ANN has better other controllers MAE, IAE, ITAE, ISE value 31.3003; 105.6280; 208.0630; 5,7289 e4, respectively. 2, only on just few parameters. In is indeed able maintain but more ripple than ANFIS. Even so, occurs does not have too much setpoint. MAE smaller (18.8937 28.4685 ANFIS).