How To Design Automatic Voltage Regulator Model using ANN in MATLAB/SIMULINK ? | Dr. J. A. Laghari

[@do_not_reply4784]

Sir , how can we include load disturbance in the AVR system ?? it has to be inserted at some time and detached after some time to study systems robustness. please clarify

[@DrJALAGHARI]

Thanks for the comment. By introducing the new signal builder using from the simulink Library you may give load variation.

[@do_not_reply4784]

Dear Sir, how cam we draw the bode diagram of the AVR.

[@DrJALAGHARI]

Thanks for the comment. There are many ways to draw the bode plot using matlab program, or pid tuner block.

[@AyazzMir]

Assalamualkim Sir. After getting data from Simulink to Workspace and running this code it gave me this error: Error using network/train (line 340) Output data size does not match net.outputs{3}.size. Error in annt (line 20) net=train(net,I,T); % Start training the network

[@DrJALAGHARI]

Thanks for the comment. May I know how many inputs you are using?

[@MUHAMMADNURHAFIZSIDIQ]

Assalamu'alaikum sir, why did u use 3 input layer, since there were only one input data?

[@DrJALAGHARI]

Wa'alaikum salam, yes you are right. it is typo mistake. you may use one.

[@aungonrafin6422]

assalam walaikum sir, simulation that you have done in this video, I want to practically implement it as an experiment. how can i do this ? how can i extract the ann simulink model in real life world to practically implement it in a physical circuit? please help me . thank you in advance

[@DrJALAGHARI]

Thanks for the comment. if you want to apply it practically then you may need dsp kit or fpga kit to apply it in practice.

[@aungonrafin6422]

@@DrJALAGHARI sir, could you please explain the procedure ? Or give me any tutorial link. It would be very helpful

[@shubhtest4551]

Sir Tuned PID controller gives better result so why should we use ANN controller

[@DrJALAGHARI]

Thanks for the comment. the tuned PID controller always give compromised response. it is not optimized. furthermore, PID controller may give good response for some cases but not for all cases. on the other hand, ANN has the ability to provide optimum response if properly trained.

[@PuneethS-i1w]

Sir why we need to set 1 and 0

[@DrJALAGHARI]

Thanks for the comment. 1 means per unit value of 1. Which means if the actual value is 11KV, and base value is also 11kV, then its per unit value will be 1.

[@walelgnakele7302]

Dear , sir, by using your Matlab code in the description I get a custom neural network block but when I replace instead of PID by this block on your diagram. brings this error(1.Error in port widths or dimensions. 'Output Port 1' of 'AVRFNN(name of project)/Add' is a one dimensional vector with 1 elements. Component: Simulink | Category: Model error 2.Error in port widths or dimensions. 'Input Port 1' of 'AVRFNN/Custom Neural Network' is a one dimensional vector with 3 elements.) how can I solve this problem

[@DrJALAGHARI]

Thanks for the comment. Kindly watch the video step by step. May be you are using three input or multiple inout that's why it is giving error.

[@walelgnakele7302]

thanks for your swift response but I followed your tutorial steps from 1-4 and AVR ANN others but there is the same error on AVRANN and LFCANN

[@DrJALAGHARI]

@@walelgnakele7302 which MATLAB version you are using?

[@DrJALAGHARI]

@@walelgnakele7302 which MATLAB version you are using?

[@walelgnakele7302]

@@DrJALAGHARI 2021a

[@do_not_reply4784]

pranaam sir , in my case , the result from PID is much better that ANN. There is an overshoot in ANN at the start. The output values , i kept under 1 , while the input values were even less than 1. can you suggest any research paper on this particular topic so that i can refer it to write a research paper. to add , very good videos though , from 2 days , i am watching your channel full day. Thanks sir

[@DrJALAGHARI]

Thanks for the comment. Basically in this particular case we have maximum value or margin to 1 therefore it takes a lot of effort to improve the response. But in case there is a big difference between the. Output results, then ANN will be surely best. To publish paper kindly watch my videos on LFC and AGC and try to implement the latest techniques.

[@dineshrajv4116]

Hai sir please explained avr step size in this video

[@DrJALAGHARI]

Thanks for the message. Step size in this model is used to assign the input reference voltage.

[@aswinanil1295]

Sir could you please share the simulink file?

[@DrJALAGHARI]

Thanks for the comment. I think the link is given in the description section of the video. You may download it from there.

[@shakeelahmed7701]

Great sir

[@DrJALAGHARI]

Thanks for the compliments.