Block diagram of closed loop system to control plasma vertical position in Damavand tokamak.
Tracking of plasma vertical position with PD controller (k p = 1, k d = 5).
A sample of shots for model training.
Execution of preprocessor program for filtering, offset rejection, time interval selection, and increasing of the sampling time.
(a) Block diagram of the closed loop system and the general structure of simulator model. (b) Simulator model structure used for identification.
Error of test data with respect to the number of neurons for different sample times.
%RMSE with respect to the number of epochs for different sampling time.
Comparison of output of the simulator model with experimental output for shot #5.
Comparison of output of simulator model with experimental output in test for shot #1.
Execution of the simulator model using real control input signal of the system.
Comparison of Z p and I cz with the simulator model outputs and in the closed loop system.
Comparison of Z p and I cz with the simulation model outputs of and in the closed loop system.
Block diagram of complete structure of the closed loop simulator using neural controller.
Block diagram of neural identifier G c (s).
Input PRBS signal, u output of G c (s) and output of neural controller are shown.
Comparison of experimental data of shot #10 with results of closed loop control of model with offline NNC.
Comparison of the performance of the closed loop control of the model with NNC controller tuned online with experimental data of PD controller for shots #10, 22, and 26.
The effect of command pulse frequency of driver on its operating frequency with NNC to improve the quality of the plasma vertical position control.
Performance of the models for data of shot 5.
Results of RMSE for shots of Figure 17 using NNC and PD controllers.
Comparison between the RMSE values of existed controller in shots #22 and 26 using NNC and PD controllers.
Article metrics loading...
Full text loading...