| Abstract: |
| In the presence of an MMC-HVDC system, current differential protection (CDP) has the risk of failure in operation under an internal fault. In addition, CDP may also incur security issues in the presence of current transformer (CT) saturation and outliers. In this paper, a current trajectory image-based protection algorithm is proposed for AC lines connected to MMC-HVDC stations using a convolution neural network improved by a channel attention mechanism (CA-CNN). Taking the dual differential currents as two-dimensional coordinates of the moving point, the moving-point trajectories formed by differential currents have significant differences under internal and external faults. Therefore, internal faults can be identified using image recognition based on CA-CNN. This is improved by a channel attention mechanism, data augmentation, and adaptive learning rate. In comparison with other machine learning algorithms, the feature extraction ability and accuracy of CA-CNN are greatly improved. Various fault conditions like different network structures, operation modes, fault resistances, outliers, and current transformer saturation, are fully considered to verify the superiority of the proposed protection algorithm. The results confirm that the proposed current trajectory image-based protection algorithm has strong learning and generalizability, and can identify internal faults reliably. |
| Key words: Channel attention mechanism,
Convolutional neural network (CNN),
Differential current,
Current trajectory image,
Modular multilevel converter-based high ,voltage direct current (MMC-HVDC) |
| DOI：10.1186/s41601-023-00280-3 |
|
| Fund:None. |
|
