Modeling of Complex Large-Scale System Using Fuzzy Neural Networks

A new modeling method for complex large-scale system (CLSS) is proposed. Uncertainties in the mathematical structure of a CLSS are modeled using fuzzy neural networks (FNN) and then its unknown parameters are tuned using a simultaneous perturbation stochastic approximation (SPSA) algorithm. As a result of the method, the simulation model of the landing process of a helicopter with rotator self-rotating is built. It is shown that the proposed method is available and applicable.