Neural-Network Vector Controller for Permanent-Magnet Synchronous Motor Drives: Simulated and Hardware-Validated Results

Surrogate Modeling of Electrical Machine Torque Using Artificial Neural Networks

“…For example, numerous publications have presented the efficiency of model predictive control (MPC) in real-time control of PMSMs [63]- [65]. However, only a few published articles are available that suggest the utilization of an FE-based surrogate model in these applications, even though there are articles presenting the utilization of non-FE-based ANNs for PMSM control [66]- [68]. The main challenge in this utilization is the computational time constraints of the real-time applications.…”

Adaptive Decoupling Control Using Radial Basis Function Neural Network for Permanent Magnet Synchronous Motor Considering Uncertain and Time-Varying Parameters

“…Meanwhile, because the control parameters obtained through trial and error are usually constants, it is difficult to achieve optimal decoupling performance in the whole ranges of the speed and torque. In [15], a neural network (NN) vector controller is proposed to realize dynamic decoupling. In [16], a decoupling control scheme which incorporates the neural network inverse (NNI) method and 2-degree-of-freedom (DOF) internal model controllers is presented to achieve fast response and high precision.…”

Optimal torque control of permanent magnet synchronous motors using adaptive dynamic programming

“…optimal cost‐to‐go) and the second neural network is called the ‘actor’, which generates the optimal control based on the optimal value function and system states. ADP also has been used in the control of PMSMs in [29, 30]. In [29], a single ANN based on ADP is designed which substitutes the outer loop PI speed controller in classical FOC.…”