Gain scheduling control of induction motor with artificial neural networks

This paper presents a nonlinear gain scheduling control of a nonlinear, time varying induction motor dynamics with unknown parameters based on pole placement control design. The objective of this control is to force the rotor speed to follow an arbitrarily prescribed trajectory. Neural networks are considered to produce a non parametric model of a nonlinear inverted-fed induction motor. However it's possible to extract a so called gain matrix from a trained neural network model. A partition of this gain matrix allows on-line estimation of the actual relevant parameters. The inverted-fed induction motor will be identified as a NARMAX model and the order of the input-output will be determined by evaluating the modification of an index which is defined as Lipschitz number. The architecture incorporates an artificial neural network and a fuzzy logic controller. The ANN is used to identify the induction motor in order to extract a linear model, and a fuzzy logic controller is used to provide an inner loop inspired by conventional vector control strategy. Simulated results are presented to validate the proposed architecture showing that speed control is stable, rapid to stabilize, and insensitive to parameter uncertainty and load disturbance.