An experimental implementation of SPSA algorithms for induction motor adaptive control

This paper describes the implementation of a self-optimizing embedded control scheme for an induction motor drive. The online design problem is formulated as a search problem and solved with a stochastic optimization algorithm. The objective function aggregates several performance indices on tracking error and control signals, and is measured directly on the hardware bench. The online optimization is performed with simultaneous perturbation stochastic approximation (SPSA) algorithms, which offer a very effective tradeoff between simplicity of implementation, speed of convergence and quality of the final solutions. The cascaded control system obtained by SPSA in about three minutes of search outperforms alternative schemes obtained with model-based linear design techniques generally used in industrial practice