Neural Networks and Sliding Modes in Controlled Uncertain Synchronous Motor Systems Academic Article in Scopus uri icon

abstract

  • A new robust motion tracking control design framework for uncertain synchronous motors based on differential flatness, artificial neural networks, sliding modes and swarm intelligence, is proposed. Robustness with respect to significant dynamic generalized uncertainty is proved. Knowledge of system parameters and variable load torque are unnecessary. Dependence on mathematical modeling based on physics is reduced. The presented control design approach is extended for a wide class of highly uncertain and multi-input multi-output, nonlinear flat dynamic systems. Incorporation of observer algorithms for accurate real-time disturbance estimation is not required. The introduced robust flat output-feedback control design framework considers radial basis function and B-spline artificial neural networks to dynamically tune in real-time sliding mode parameters. In this fashion, active attenuation of chattering is achieved from a dynamic artificial intelligence control design perspective. Reliable control performance under exogenous disturbances and endogenous uncertainty is demonstrated. A key insight is that B-splines networks offer fast and localized adaptation with lower computational cost compared to traditional radial basis function networks, making them more suitable for embedded real-time applications. Particle swarm optimization is employed to optimize initial neural weights. The control scheme offers a scalable and efficient solution suitable for embedded real-time applications, as demonstrated through various operating scenarios involving nonlinear disturbances, load torque variations, and parametric uncertainty. The findings reveal the robust performance of the proposed synchronous motor system control strategy for the efficient tracking of smooth speed reference trajectories in presence of a wide spectrum of dynamic uncertainties. Moreover, numerical results confirm the superiority of the proposed robust adaptive neural-network trajectory tracking control framework for highly uncertain operating environments over previous model-based design studies. Efficiency, robustness and uncertain system stability are guaranteed from the introduced dynamic artificial intelligence control design perspective. © 2013 IEEE.

publication date

  • January 1, 2025