Neural network sliding mode controller for a class of nonlinear uncertain systems

In this paper a neural network sliding mode controller (NNSM) is designed for a class of nonlinear uncertain systems. Sliding mode control approach (SMC) can be used for nonlinear systems with small uncertainties. However, for nonlinear systems with large uncertainties the SMC produce chattering phenomenon due to the higher switching gain. In order to reduce this gain, neural network with one hidden layer is used to estimate uncertain or unknown parts of the system plant. This neural network is trained on-line using the backpropagation algorithm. A second robust control term is added to compensate the neural network errors. The performance of the proposed approach is investigated in simulations by the comparison with traditional sliding mode control.