In order to improve the accuracy of the open-circuit fault diagnosis of the double-fed asynchronous wind turbine converter, a fault diagnosis method based on the global adaptive whale optimization algorithm to optimize the extreme learning machine is proposed. Firstly, establish a grid-connected model of doubly-fed induction generator(DFIG), and collect the three-phase line voltage signal under the fault state of the grid-side converter. Secondly, fast Fourier transform is performed on the collected voltage signal, and then the frequency amplitude of the different harmonic components of the three-phase line voltage and the DC component are reconstructed into a feature vector. In order to remove some redundant features, use the neighborhood to maintain the projection pair, the feature vector is dimensionally reduced. Finally, an extreme learning machine optimized by the global adaptive whale optimization algorithm(GAWOA-ELM) is used to diagnose the faults of the converter. Different methods are used to diagnose and analyze converter faults under different signal-to-noise ratios, verifying the effectiveness and robustness of the method proposed in this paper.