Comparative study of feedback linearization control for IM taking into account magnetic saturation effects

This study examines how the nonlinear characteristics of the magnetic core, where the magnetic material in an induction machine (IM) exhibits a nonlinear relationship between magnetizing current and resulting flux, affect the performance of control systems. In typical IM operation, these nonlinearities lead to noticeable changes in inductance values, complicating accurate flux estimation. To address this, we develop a nonlinear observer (NLO) that explicitly incorporates the effects of the magnetic core's nonlinearity for rotor flux estimation. The observer gain is designed using a Lyapunov stability framework to ensure exponential convergence of the estimation error under varying flux conditions. This approach is compared with a conventional full-order Luenberger observer (LO) that assumes a simple, linear magnetization characteristic. Within the FOC framework, two feedback linearization strategies are evaluated. The FL sat takes into account the non-linear variations in machine inductances caused by saturation, enabling a more accurate representation of IM dynamics. However, this approach is more complex to calculate because of the nonlinear terms. The FL unsat simplifies control design by neglecting the effects of magnetic saturation, thus reducing computational requirements. Despite its simplified structure, FL unsat delivers comparable performance over the nominal speed and flux operating range. The results highlight a trade-off between dynamic modeling fidelity and control accuracy, offering valuable insights for the design of controllers and observers for IM. While FL sat is well suited to scenarios requiring high accuracy and dynamic tracking, FL unsat emerges as a pragmatic alternative for applications favoring simplicity and real-time implementation. Quantitative measurements further support these results: under constant resistances, the proposed NLO achieves an absolute integral error (IAE) of 0.0133 in rotor magnetization current tracking compared to 1.026 with LO, underlining the robustness and accuracy advantages of explicit magnetic saturation modeling.