Parameters Identification of Sub-Synchronous Oscillation in D-PMSG Based on Improved VMD and TLS-MP

To address the problems of modal aliasing, limited identification accuracy, and inadequate noise adaptability in the parameters identification of sub-synchronous oscillation (SSO) in direct-drive permanent magnet synchronous generator (D-PMSG), a method based on improved variational mode decomposition (VMD) and total least squares matrix pencil (TLS-MP) is proposed. The grid-connected current of the D-PMSG, acquired by the phasor measurement unit (PMU), is decomposed through VMD, which is optimized via the Bayesian optimization (BO) algorithm to determine the optimal number of intrinsic mode functions (IMFs) K and the penalty factor α. By this means, mode mixing phenomena in VMD are eliminated, and noise adaptability is reinforced. The derived IMFs are subjected to mutual information (MI) analysis with the grid-connected current, from which the dominant IMFs are extracted. Each dominant IMF is subsequently resampled, and its parameters are identified through TLS-MP. In this process, the strength Pareto evolutionary algorithm II (SPEA2) is employed to improve the MP method, and the optimal signal subspace order g is obtained, which facilitates improved identification accuracy and noise adaptability. Finally, TLS is incorporated to accomplish the identification of characteristic parameters of the D-PMSG SSO components, including amplitude, frequency, phase, and damping factor. Simulation analyses based on composite signals and a four-machine two-area system model containing a direct-drive wind farm are conducted, and the effectiveness of the proposed identification method is validated.