Friction modelling based on support vector regression machines and genetic algorithms

An accurate friction model is necessary for friction compensation in radar servo systems or industrial robots. In order to obtain an accurate friction model, a method of friction modelling is proposed, based on support vector regression machines (SVRM) and real genetic algorithms (RGA). Three optimization problem formulations are proposed to realize the automatic optimal parameter selection of SVMR to avoid spending much time on parameter selection. Moreover, a friction modelling tool using the proposed method is developed. Some comparisons are carried out on the three formulations of the proposed parameter selection. The comparison results demonstrate that the third formulations can obtain better friction model by using RBF kernel function.