Structure identification in Takagi-Sugeno fuzzy modeling

In the Takagi-Sugeno fuzzy modeling for complex system modeling, global system model is obtained by combining a number of local models, each of which has simpler structure. Since the local models are identified for corresponding fuzzy subsets, the performance of the global model is highly affected by the choice of the subsets. This paper addresses a structure identification algorithm with subset decomposition and merging in the Takagi-Sugeno fuzzy modeling based on three criteria, Kullback discrimination information, Akaike information criterion, and mean squared errors.