Nonlinear adaptive control method based on ANFIS and multiple models

An adaptive control method based on adaptive-network-based fuzzy inference system (ANFIS) and multiple models is proposed for a class of uncertain discrete-time nonlinear systems with unstable zero-dynamics. The approach is composed of a linear robust adaptive controller, a nonlinear adaptive controller based on ANFIS and switching mechanism. The linear controller ensures the boundedness of the input and output signals, and the nonlinear controller improves the performance of the system. By using the switching scheme, the performance is improved and the stability is achieved simultaneously. Moreover, the ANFIS is used to estimate and compensate the unmodeled dynamics adaptively, which overcomes the uncertainty of neural network and saves the training time of the network and at the same time avoids the possibility that the network becomes trapped in local minima and so on. It improves the convergence rate and the precision of the unmodeled dynamics estimation, thereby improving the control effect. Stability and convergence analysis of the proposed method are established. The simulation results show the effectiveness of the approach.