TY - JOUR
T1 - Discrete-time Kalman filter for Takagi–Sugeno fuzzy models
AU - Páramo-Carranza, L. A.
AU - Meda-Campaña, J. A.
AU - de Jesús Rubio, José
AU - Tapia-Herrera, R.
AU - Curtidor-López, A. V.
AU - Grande-Meza, A.
AU - Cázares-Ramírez, I.
N1 - Publisher Copyright:
© 2017, Springer-Verlag Berlin Heidelberg.
PY - 2017/9/1
Y1 - 2017/9/1
N2 - In this work, the Kalman Filter (KF) and Takagi–Sugeno fuzzy modeling technique are combined to extend the classical Kalman linear state estimation to the nonlinear field. The framework for such extension is given, and in this sense the discrete-time fuzzy Kalman filter (DFKF) is obtained. It will be shown that the fuzzy version gives some advantages when is compared with the Extended Kalman Filter (EKF), which is the most typical extension of the KF to the nonlinear field. The proposed approach provides a significantly smaller processing time than the processing time of the EKF while the mean square error is also reduced. Finally, some examples, such as the Lorenz chaotic attractor and under actuated mechatronic system (pendubot), are used to compare the DFKF and EKF.
AB - In this work, the Kalman Filter (KF) and Takagi–Sugeno fuzzy modeling technique are combined to extend the classical Kalman linear state estimation to the nonlinear field. The framework for such extension is given, and in this sense the discrete-time fuzzy Kalman filter (DFKF) is obtained. It will be shown that the fuzzy version gives some advantages when is compared with the Extended Kalman Filter (EKF), which is the most typical extension of the KF to the nonlinear field. The proposed approach provides a significantly smaller processing time than the processing time of the EKF while the mean square error is also reduced. Finally, some examples, such as the Lorenz chaotic attractor and under actuated mechatronic system (pendubot), are used to compare the DFKF and EKF.
KW - Chaotic systems
KW - Fuzzy systems
KW - Kalman filtering
UR - http://www.scopus.com/inward/record.url?scp=85028074813&partnerID=8YFLogxK
U2 - 10.1007/s12530-017-9181-0
DO - 10.1007/s12530-017-9181-0
M3 - Artículo
SN - 1868-6478
VL - 8
SP - 211
EP - 219
JO - Evolving Systems
JF - Evolving Systems
IS - 3
ER -