ADALINE-based friction identification of a linear voice coil DC motor

This paper presents a nonlinear friction identification algorithm based on artificial neural networks (ANNs) for a linear positioning system. An adaptive linear neuron (ADALINE) with two different network structures is used to estimate the parameters of the system including the Coulomb friction and viscous friction coefficients. The training of the network is carried out in off-line and on-line modes. An experimental setup with a linear voice coil DC motor and a high resolution position encoder is developed to test and validate the different identification algorithms. A comparison between the ADALINE-based method and the conventional steady-state velocity-control method is made to evaluate the advantages and disadvantages of each technique.