Neural network-based correction and interpolation of encoder signals for precision motion control

Precision control is the core of many applications in the industry, particularly robotics and drive control. To achieve it, precise measurement of the signals generated by incremental encoder sensors is essential. High precision and resolution motion control relies critically on the precision and resolution achievable from the encoders. In this paper, a dynamic neural network-based approach for the correction and interpolation of quadrature encoder signals is developed. In this work, the radial basis functions (RBF) neural network is employed to carry out concurrently the correction and interpolation of encoder signals in realtime. The effectiveness of the proposed approach is verified in the simulation results provided.