Accurate classification of voltage sag is crucial for sag responsibility allocation and optimization of management decisions. Existing voltage sag classification methods rely heavily on large amounts of labeled data during supervised training. However

it is difficult to obtain sufficient labeled information from field measurements. To address this issue

this paper proposes a novel semi-supervised learning-based voltage sag classification method suitable for situations with limited labeled data. First

voltage sag data is transformed into a two-dimensional graphic form using the space phasor model (SPM)

enabling automatic feature extraction through SENet. Next

a new semi-supervised learning algorithm

the weighted virtual adversarial mean teacher model (WVAMT)

is proposed to construct the classifier. The proposed method not only enables the efficient learning of unlabeled data

but also mitigates the impact of random perturbations introduced in the data augmentation process on classifier stability. Finally

based on the field-measured dataset

the proposed method exhibits excellent classification performance compared with existing methods in complex environments and is suitable for practical engineering applications.