-
Daiana Caroline dos Santos Gomes
Universidade Federal do Maranhão, Av. dos Portugueses, 1966, Bacanga, São Luís, Maranhão
-
Ginalber Luiz de Oliveira Serra
Instituto Federal de Educação, Ciência e Tecnologia do Maranhão, Av. Getúlio Vargas, 04, Monte Castelo, São Luís, Maranhão
Keywords:
Systems identification, Kalman filtering, Recursive parametric estimation, Interval type-2 evolving fuzzy model, Evolving fuzzy systems
Abstract
This paper presents a computational approach for interval type-2 fuzzy evolving Kalman filters desingnig from experimental data. First, an initial parametric estimation of interval type-2 evolving fuzzy Kalman filter model is obtained considering an initial window of the experimental data. From this initial estimation, the parameters defined in the antecedent and consequent propositions of interval type-2 evolving fuzzy Kalman filter are updated recursively from each new sample of the dataset through a type-2 fuzzy version of evolving Takagi-Sugeno (eTS) clustering algorithm and a type-2 fuzzy version of Observer/Kalman Filter Identification (OKID) algorithm, respectively. Computational results and comparative analysis demonstrate the efficiency and applicability of the proposed methodology when applied to Mackey–Glass chaotic time series modeling.
