Motor state prediction and friction compensation for brushless DC motor drives using data-driven techniques

Friction compensation is critical for robust, dependable, and accurate position and velocity control of motor drives. Large position inaccuracies and vibrations caused by non-characterised friction may be amplified by stick–slip motion and limit cycles. This research study uses two data-driven methodologies to find the governing equations of motor dynamics, which also describe friction. Specifically, data obtained from a brushless DC (BLDC) motor is subjected to Sparse Identification of Nonlinear Dynamics with Control (SINDYc), and low-energy data extraction from time-delayed motor velocity coordinates is done to determine the underlying dynamics. Next, the identified nonlinear model is compared to a linear model without friction and a nonlinear model that contains the LuGre friction model. The optimal friction parameters for the LuGre model are determined using a nonlinear grey box model estimation approach with the collected data. The three validation datasets taken from the BLDC motor are then used to validate the proposed nonlinear motor model with friction characteristics. Over \(90\%\) $90\%$ accuracy in predicting the motor states in all input excitation signals under consideration is demonstrated by the proposed model. Additionally, when applied to a model-based feedback friction compensation technique, the proposed model demonstrates a relative improvement in performance in comparison to a system that uses the LuGre model.