Fuzzy modeling of disturbance torques/forces in rotational/linear interior permanent magnet synchronous motors

We propose several artificial intelligence techniques for fuzzy modeling of electromagnetic and disturbance (friction, ripples) torques/ forces in permanent magnet rotational/linear motors. Based on a model taking into account several nonlinear phenomena such as non-sinusoidal flux linkage, saturation effects, cross-magnetization etc we use observer-based parameter identifiers approach to plan identification experiments. We investigate and compare several training algorithms to tune the model parameters and to simplify the model structure. We especially recommend application of bacterial evolutionary algorithm for these purposes. Applications of obtained model in adaptive control are suggested.