Fuzzy system identification via chaotic ant swarm

In this paper, we introduce a chaotic optimization method, called CAS (chaotic ant swarm), to solve the problem of designing a fuzzy system to identify dynamical systems. The position vector of each ant in the CAS algorithm corresponds to the parameter vector of the selected fuzzy system. At each learning time step, the CAS algorithm is iterated to give the optimal parameters of fuzzy systems based on the fitness theory. Then the corresponding CAS-designed fuzzy system is built and applied to the identification of the unknown nonlinear dynamical systems. Numerical simulation results are provided to show the effectiveness and feasibility of the developed CAS-designed fuzzy system.