Figure 1 - uploaded by Abdulrahim Humod
Content may be subject to copyright.
Source publication
ABSTRACT
This paper investigates the improvement of the speed and torque dynamic responses of three phase Permanent Magnet Synchronous Motor (PMSM) using Direct Torque Control (DTC) technique. Different torques are applied to PMSM at different speeds during operation to ensure the robustness of the controller for wide torque variations. Optimal PI...
Similar publications
In order to improve the dynamic performance and robustness of permanent magnet synchronous motor (PMSM) servo system, the moment of inertia identification based on model reference adaptive algorithm is studied. According to the problem that the stability and convergence response speed of the model reference adaptive identification (MRAI) algorithm...
This paper proposes a robust nonlinear predictive current control (RNPCC) method for permanent magnet synchronous motor (PMSM) drives, which can optimize the current control loop performance of the PMSM system with model parameter perturbation. First, the disturbance caused by parameter perturbation was considered in the modeling of PMSM. Based on...
The model predictive current control (MPCC) method has been widely used in permanent magnet synchronous motor (PMSM) drive systems for excellent dynamic performance. The fault diagnosis of the PMSM drive system becomes as important as dynamic performance improvement. The open-circuit fault of the semiconductor power switches is commonly seen in the...
Aiming at the output current distortion problem in the low frequency operation of permanent magnet synchronous motor (PMSM) drive system of modular multilevel converter (MMC), the essential relationship between the output current distortion and the injected components is analyzed in this paper. A current harmonic suppression method combining feedfo...
Multilevel inverters offers eminent solutions to high voltage high power applications due to the association of several devices in a series configuration. In this paper, a comparative investigation of both 15 and 17 level cascaded h-bridge multi level inverter with cross h-bridge fed permanent magnet synchronous motor are presented by appropriate s...
Citations
... The NARMA-L2 model is one of the most widely used models for time series forecasting [Haider et al., 2019, Jibril et al., 2020, Humod et al., 2016. In this paper, the authors use the NARMA-L2 model to find the coefficients of PID controller. ...
In the paper, the problem of controlled synchronization of Two-rotor Vibration Units is considered. A new bidirectional control law combined with Neural Network based PID controller is proposed for multisynchronization of rotors. Besides, an algorithm for design of Neural Network based PID Controller of Two rotor Vibration Units is developed. The robustness of the proposed controller under the effect of unknown exogenous disturbances is illustrated.
... The authors in [15] controlled a bioreactor using an NARMA-L2 neural control strategy and proved that the trajectory tracking performance obtained was better than with the use of the inverse neural model control strategy. The authors in [16] suggested direct torque control for three phase Permanent Magnet Synchronous Motor for improving the speed and torque dynamic responses. Two types of controllers are used, NARMA-L2 controller and optimal PI controller (PI-PSO), where NARMA-L2 is trained based on optimal PI controller (PI-PSO) data. ...
... Schematic diagram of the proposed MIMO neural networks based on NARMA-L2 modelwhere the indices 1, 2 and 3 of u and y represent respectively the first, second, and third input or output, and k is a time step. Hence, a neural network approximation of a three-DOF NARMA-L2 model is given by(16), ...
This paper introduces a nonlinear adaptive controller of unknown nonlinear dynamical systems based on the approximate models using a multi-layer perceptron neural network. The proposal of this study is to employ the structure of the Multi-Layer Perceptron (MLP) model into the NARMA-L2 structure in order to construct a hybrid neural structure that can be used as an identifier model and a nonlinear controller for the MIMO nonlinear systems. The big advantage of the proposed control system is that it doesn’t require previous knowledge of the model. Our ultimate goal is to determine the control input using only the values of the input and output. The developed NARMA-L2 neural network model is tuned for its weights employing the backpropagation optimizer algorithm. Nonlinear autoregressive-moving average-L2 (NARMA-L2) neural network controller, based on the inputs and outputs from the nonlinear model, is designed to perform control action on the nonlinear for the attitude control of unmanned aerial vehicles (UAVs) model. Once the system has been modeled efficiently and accurately, the proposed controller is designed by rearranging the generalized submodels. The controller performance is evaluated by simulation conducted on a quadcopter MIMO system, which is characterized by a nonlinear and dynamic behavior. The obtained results show that the NARMA-L2-based neural network achieved good performances in modeling and control.
This work presents the design of a nonlinear autoregressive-moving average controller (NARLA-L2) applied to a TWIN ROTOR MIMO SYSTEM (TRMS). This system simulates the dynamic of a helicopter, which is a kind of UAVs; they are the interest of nowadays researches, in particular the control of this system. Because of the difficulty presented in modeling of such non linear systems, a non model control technique is used -to avoid this hard and not exact task- based on neural network structure.
So this method is applicable for the control of this type of complex nonlinear system, and its strength is that it is not based on physical modeling that is often far from the real system, thus the ease of synthesizing the corrector with good performances in trajectory tracking and disturbances rejection.
This paper proposes improving the structure of the neural controller based on identification model for nonlinear systems. The goal of this work is to employ the structure of the Modified Elman Neural Network (MENN) model into the NARMA-L2 structure instead of Multi-Layer Perceptron (MLP) model in order to construct a new hybrid neural structure that can be used as an identifier model and a nonlinear controller for the SISO linear or nonlinear systems. Two learning algorithms are used to adjust the parameters weight of the hybrid neural structure with its serial-parallel configuration; the first one is supervised learning algorithm based Back Propagation Algorithm (BPA) and the second one is an intelligent algorithm namely Particle Swarm Optimization (PSO) algorithm. The numerical simulation results show that the hybrid NARMA-L2 controller with PSO algorithm is more accurate than BPA in terms of achieving fast learning and adjusting the parameters model with minimum number of iterations, minimum number of neurons in the hybrid network and the smooth output one step ahead prediction controller response for the nonlinear CSTR system without oscillation.
