Model Predictive Control Coupled with Artificial Intelligence for Eddy Current Dynamometers

The recent studies on Artificial Intelligence (AI) accompanied by enhanced computing capabilities supports increasing attention into traditional control methods coupled with AI learning in an attempt to bringing adaptiveness and fast responding features. Model Predictive Control (MPC) technique is a widely used, safe reliable method based constraints. On the other hand, Eddy Current dynamometers are highly nonlinear braking systems whose performance parameters related many processes variables. This study adaptive model predictive that utilizes selected methods. presented approach presents updated mathematical of Dynamometer experimentally obtained system operational data. Finally, comparison performances assessment mean absolute percentage error (MAPE) issues discussed. results indicate Single Hidden Layer Neural Network (SHLNN), General Regression (GRNN), Radial Basis (RBNN), Neuro Fuzzy (ANFIS) MPC have quite satisfying performances. that, amongst them, GRNN appears provide best performance.