基于Kolmogorov-Arnold网络的跟网型与构网型电力电子系统阻抗辨识

An impedance model is being adopted for the stability analysis of power electronic systems. Due to limited accessibility to detailed controller information, the analytical impedance model is difficult to derive. This letter proposes an impedance identification method based on the Kolmogorov–Arnold network (KAN) and physical information for grid-connected converter systems with grid-following and grid-forming control. Leveraging the Kolmogorov–Arnold representation theorem, the proposed two-layer KAN replaces fixed neuronal weights with learnable univariate spline functions, thereby achieving universal approximation with fewer trainable parameters and reduced network depth than a multilayer perceptron with comparable accuracy. The effectiveness of the proposed method is validated by wind farms with doubly fed induction generator converters in the real-time digital simulator and compared with other neural structures.