Neuro-Fuzzy Modelling Using a Logistic Discriminant Tree

An algorithm for nonlinear static and dynamic identification using Takagi-Sugeno fuzzy models is presented. For practical applications the incorporation of prior knowledge and the interpretability of the local models is of great interest. Using a tree structured algorithm in combination with the distinction between the input arguments for the consequents and for the premises the nonlinear optimisation is performed in an efficient way. The axis oblique decomposition of the partition space is based on an expectation-maximisation (EM) algorithm. Simulation results demonstrate the capabilities of the proposed concept.