ADVANCES IN NEUROFUZZY ALGORITHMS FOR REAL-TIME MODELING AND CONTROL

This paper reviews the architecture, representation capability, traini ng and learning ability of a class of adaptive neurofuzzy systems for real-time modelling and control of unknown nonlinear dynamic processes . Issues relating to learning stability, training laws and parametric convergence, network conditioning, gradient noise, the curse of dimens ionality associated with associative memory networks, automatic networ k construction algorithms, and a series of neurofuzzy control design l aws, are discussed, together with future critical research issues asso ciated with neurofuzzy systems.