Dear Ahmed,

thank you very much for your response,

I think that there exist a lot of works about Neuro-PID controller. I want find what is the best method?

thank you for your help

Amar

Why do you want to mix a PID and a neural net ? I suppose you can have several PID for different contexts (imagine working on earth or in zero gravity) and choosing between those experts using a neural net. This would be similar to MOSAIC by Kawato... Additionally you could also fit the parameters of your PID using a neural net and some reinforcement learning...

Please refer to these articles:

https://www.researchgate.net/publication/313576646_From_PID_to_Nonlinear_State_Error_Feedback_Controller

https://www.researchgate.net/publication/312046377_Improved_Sliding_Mode_Nonlinear_Extended_State_Observer_based_Active_Disturbance_Rejection_Control_for_Uncertain_Systems_with_Unknown_Total_Disturbance

https://www.researchgate.net/publication/309655805_On_the_Improved_Nonlinear_Tracking_Differentiator_based_Nonlinear_PID_Controller_Design

Article From PID to Nonlinear State Error Feedback Controller

Article Improved Sliding Mode Nonlinear Extended State Observer base...

Article On the Improved Nonlinear Tracking Differentiator based Nonl...