Optimized Non-linear Observer for PMSM Speed Control System Integrating Multi-dimensional Taylor Network and Lyapunov Theory

In the realm of permanent magnet synchronous motor speed control systems, this paper puts forward a novel non-linear observer scheme founded on the Multi-dimensional Taylor Network (MTN). Compared with the neural network observer, this MTN-based scheme stands out for its straightforward structure and significantly reduced computational complexity. Specifically, the intricate calculations and high resource consumption typically associated with neural network observers are circumvented. Subsequently, by leveraging the Lyapunov theory, an adaptive learning rule for the MTN weights is meticulously devised, which seamlessly bridges to the theoretical proof of the non-linear observer's stability. Ultimately, the system simulation results effectively corroborate the proposed scheme's efficacy.