Neural network-based adaptive funnel sliding mode control for servo mechanisms with friction compensation

In this paper, a novel adaptive funnel sliding mode control scheme is proposed for servo mechanisms with friction compensation. A continuously differentiable friction model is employed to capture the unknown friction dynamics. The friction nonlinearities and unknown dynamics are estimated by using neural network (NN). Moreover, a modified funnel variable, which relaxes limitation in original funnel control (e.g., systems with relative degree 1 or 2), is developed using the tracking error to replace the scaling factor, which is used to design the sliding mode surface. Then, a novel adaptive funnel sliding mode control scheme is proposed for servo mechanisms to improve the transient performance. The effectiveness of the developed control method is validated via experimental results.