Genetics algorithms based PID tuning using elastic net as model structure in non-parametric system identification

Gonzales I.J.P.; Manzano E.A. · 2020 IEEE ANDESCON, ANDESCON 2020 (2020) · DOI: 10.1109/andescon50619.2020.9272193

Resumen

Over the past few years, the arising of artificial intelligence has suggested its integration in control systems as well as other technologies. In this way, this work mainly presents the development of two important procedures according the artificial intelligence approach: non-parametric identification in order to obtain a Elastic Net model for a speed control of a DC motor system and a proposal of PID parameters adjustment based in genetic algorithms for the same system.Both proposals were validated by comparing them with the traditional methods. Transfer function of the system was obtained to compare the Elastic Net model performance. In addition, Ziegler-Nichols method and PID Tuner of Matlab were used to analyse the performance of the genetic algorithms in the PID tuning for the system.

Instituciones: Universidad Nacional de Trujillo