On line fuzzy learning maximum likelihood-instrumental variable evolving algorithm

In this paper an evolving recursive fuzzy cluster algorithm based on maximum likelihood criterion using the recursive instrumental variable parameter estimation for non-linear system identification, is proposed. The performance of the proposed methodology is illustrated for black box modeling of a thermal plant from real-time acquisition data plataform. The experimental results are evaluated from metrics used in the literature to show the efficiency of the proposed online evolving recursive fuzzy clustering algorithm.