Adaptive Neuro-Fuzzy Inference System (ANFIS) for Friction Modelling and Compensation in Motion Control System

Abstract

In motion control system applications, friction has been experimentally shown to be one of the major sources of performance degradation in terms of slow responses, steady-state accuracy, poor tracking and/or limit cycles near the reference position. Hence, the need for its accurate compensation has become important in high-precision position control. Among the successful approaches is model-based friction compensation which in turn is anchored on accurate model of the friction. Many sophisticated friction models have been proposed by researchers. Unfortunately, there exist no universally agreed model for friction, and at the same time selecting and developing accurate models for friction compensation for a particular application has been historically challenging due to complexity of parametric modelling of the friction nonlinearities. Motivated by the need for simple and yet effective friction compensation in motion control system, an artificial intelligent (AI)-based (non-parametric) friction model using an adaptive neuro-fuzzy inference system (ANFIS) is proposed in this work to estimate the nonlinear friction in a motion control system. The effectiveness of the developed model in representing and compensating for the frictional effects is evaluated experimentally on a rotary experimental motion system. The performance is benchmarked with three parametric-based (Coulomb, Tustin, and Lorentzian) friction models. The results show ANFIS as a viable and efficient alternative to the parametric-based techniques in representing and compensating friction effects.