TY - JOUR
T1 - State estimation in MIMO nonlinear systems subject to unknown deadzones using recurrent neural networks
AU - Pérez-Cruz, J. Humberto
AU - Rubio, José de Jesús
AU - Pacheco, Jaime
AU - Soriano, Ezequiel
N1 - Funding Information:
First author would like to thank the financial support through a postdoctoral fellowship from Mexican National Council for Science and Technology (CONACYT) under Grant 194775-IPN.
PY - 2014/9
Y1 - 2014/9
N2 - This paper deals with the problem of state observation by means of a continuous-time recurrent neural network for a broad class of MIMO unknown nonlinear systems subject to unknown but bounded disturbances and with an unknown deadzone at each input. With respect to previous works, the main contribution of this study is twofold. On the one hand, the need of a matrix Riccati equation is conveniently avoided; in this way, the design process is considerably simplified. On the other hand, a faster convergence is carried out. Specifically, the exponential convergence of Euclidean norm of the observation error to a bounded zone is guaranteed. Likewise, the weights are shown to be bounded. The main tool to prove these results is Lyapunov-like analysis. A numerical example confirms the feasibility of our proposal.
AB - This paper deals with the problem of state observation by means of a continuous-time recurrent neural network for a broad class of MIMO unknown nonlinear systems subject to unknown but bounded disturbances and with an unknown deadzone at each input. With respect to previous works, the main contribution of this study is twofold. On the one hand, the need of a matrix Riccati equation is conveniently avoided; in this way, the design process is considerably simplified. On the other hand, a faster convergence is carried out. Specifically, the exponential convergence of Euclidean norm of the observation error to a bounded zone is guaranteed. Likewise, the weights are shown to be bounded. The main tool to prove these results is Lyapunov-like analysis. A numerical example confirms the feasibility of our proposal.
KW - Deadzone
KW - Exponential convergence
KW - Neural observer
KW - Recurrent neural network
UR - http://www.scopus.com/inward/record.url?scp=84890984925&partnerID=8YFLogxK
U2 - 10.1007/s00521-013-1533-5
DO - 10.1007/s00521-013-1533-5
M3 - Artículo
SN - 0941-0643
VL - 25
SP - 693
EP - 701
JO - Neural Computing and Applications
JF - Neural Computing and Applications
IS - 3-4
ER -