PS-FB-ZVZCS PWM Converter Modeling and Simulation Based on the PID Neural Network

2011 ◽  
Vol 328-330 ◽  
pp. 1947-1952
Author(s):  
Sheng Zu Xiong ◽  
Huai Lin Shu

In order to overcome the disadvantage of the traditional control methods and general neural network control methods, the above two control methods which used to be applied to the PS-FB-ZVZCS-PWM(Phase-shifted Full-bridge Zero-voltage Zero-current-switching Pulse-Width Modulation, PS-FB-ZVZCS-PWM)converters modeling has been replaced by the PID(Proportional-Integral-Derivative , PID)neural network control. The first PID neural network subnet was used as the outer voltage loop control and the second PID neural network subnet was used as the inner current loop control. The output of the first PID neural network subnet was used as the reference input of the second PID neural network subnet. By the tight integration of two neural network subnets, a dual loop PID neural network control system was got. The result of the simulation which was got by MATLAB software showed the use of PID neural network as a regulator of the double close loop model was not only to achieve the nice control characteristics which are no overshoot, no static error, fast response, short transition time, good tracking performance, but also man-made regulation time was significantly reduced.

2012 ◽  
Vol 591-593 ◽  
pp. 1490-1495 ◽  
Author(s):  
Huai Lin Shu ◽  
Jin Tian Hu

The multivariable PID neural network (MPIDNN) control system is introduced in this paper. MPIDNN is used to perform both the control and the decouple at the same time and to get better performance. It is difficult to control multivariable system by conventional controller because the strong coupling properties of the system. Generally, the decoupling system should be designed first and the multivariable object would be divided into several single variable objects. Then, several simple controller would achieve the control of those objects. The decoupling system and the controller exist in theory but the design process is very difficult actually because the transfer function of the object is difficult to get. Especially, if the number of the object inputs is not equal to that of the object outputs, which is called unsymmetry object, the conventional decoupling is impossible. A actual example is discussed in the paper in order to prove the function of the MPIDNN, in which an un-symmetry multivariable system which has 3 inputs and 2 outputs is controlled by a MPIDNN and the perfect control property is obtained by self-learning process.


2011 ◽  
Vol 317-319 ◽  
pp. 1228-1231
Author(s):  
Xu Chen ◽  
Da Wei Li ◽  
Zhen Jiang Jiang

The brushless direct current motor(DC) simulation model based on neural network control strategy is developed, according to the physical structure of the motor, after the analysis of in-wheel motor mathematical model. The simulation has pulse width modulation (PWM) generation module,which can adjust the PWM duty cycle to regulate the motor speed. Simulation results show that there is good agreement between the output ofsimulation model and the theoretical analysis.The application of neural networkcontrol in brushless DC motor offers the advantages of rapid response, without overshoot ,and higher steady-state accuracy.


Sign in / Sign up

Export Citation Format

Share Document