Tuning of Controllers, PI Controller, PID Controller, Artificial Neural Network, Stabilizing Set. 

PID controllers are present in approximately 96% of industrial control loops, yet it is estimated that a large portion of these controllers are not adequately tuned. Nowadays, tuning controllers using classic techniques is still a challenging task, which has motivated the development of new tools, mainly employing the use of artificial intelligence for adjusting the parameters of PI and PID controllers. This work aims to develop tools that assist in the tuning of PI and PID controllers, based on the stabilizing set theory, developed by researchers from Texas A&M. A database was created with transfer functions for direct current industrial motors, which was used as input for the script, developed in Python, that performs the calculation of the stabilizing set for all the transfer functions in the database. After calculating the stabilizing set, it was possible to generate a new database, with parameters of PI and PID controllers classified as belonging or not to the stability region, for a given transfer function. This procedure was applied to the speed and position controls of the motor, both for the PI controller and the PID controller. This database was used for the training of artificial neural networks, with two configurations used for the network training. The results showed that the artificial neural networks performed well during the tests, with the networks trained for the PI controller showing an accuracy above 0.975 and the networks for the PID controllers showing a final accuracy above 0.95.