Title :
Robust nonlinear control using neural networks
Author :
Wams, Bart ; De Vries, Rob A J
Author_Institution :
Fac. of Inf. Technol. & Syst., Delft Univ. of Technol., Netherlands
Abstract :
In this article, the influence of uncertainty on weights and biases of neural networks on the input/output behavior is investigated. Moreover, a uncertainty description of uncertain neural networks is derived and an appropriate norm bound of the model uncertainty, which is needed for robust control design, is derived. Finally, feedback linearization is used in order to fully incorporate neural networks in standard robust l1 model based control
Keywords :
control system synthesis; feedback; linearisation techniques; neurocontrollers; nonlinear control systems; robust control; uncertain systems; I/O behavior; feedback linearization; input/output behavior; neural networks; norm bound; robust control design; robust l1 model based control; robust nonlinear control; uncertain neural networks; uncertainty; Control system synthesis; Linear feedback control systems; Neural networks; Neurofeedback; Nonlinear control systems; Predictive control; Predictive models; Robust control; Robust stability; Uncertainty;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.687184
