A new neural network structure dedicated to the control of nonlinear systems

Tsurng-Jehng Shen (1, 2) , Felix Mora-Camino (3) , Karim Achaibou (3)

1 LAAS - Laboratoire d'analyse et d'architecture des systèmes
2 CSIST
3 LAAS-DISCO - Équipe DIagnostic, Supervision et COnduite

In this communication is proposed a new neural network structure to design a robust controller for non-exactly known nonlinear systems. Based on input-output data, the neural network structure provides a global affine model of the controlled system which is compatible with well known nonlinear control techniques. An Affine Neural Tracking controller is developed and applied to an invertled pendulum submitted to random perturbations. The performance of the controller and the main advantage of the proposted approach are discussed.

Mots clés: neurocontrollers; nonlinear control systems; pendulums; robust control

Domaines: Sciences de l'ingénieur [physics]; Automatique / Robotique

Tsurng-Jehng Shen, Felix Mora-Camino, Karim Achaibou. A new neural network structure dedicated to the control of nonlinear systems. MWSCAS 1995, 38th Midwest Symposium on Circuits and Systems, Aug 1995, Rio de Janeiro, Brazil. pp 433-436, ⟨10.1109/MWSCAS.1995.504469⟩. ⟨hal-01022426⟩