Multichannel consecutive data cross-extraction with 1DCNN-attention for diagnosis of power transformer
This work addresses transformer diagnosis for grid infrastructure by improving feature extraction from multichannel data, though it appears incremental as it builds on existing methods with specific enhancements.
The paper tackles the problem of diagnosing power transformers by proposing a multichannel consecutive data cross-extraction (MCDC) structure with a 1DCNN-attention mechanism to exploit temporal information from sequential data, achieving validated effectiveness and superior generalization compared to other algorithms in experiments on real-world data.
Power transformer plays a critical role in grid infrastructure, and its diagnosis is paramount for maintaining stable operation. However, the current methods for transformer diagnosis focus on discrete dissolved gas analysis, neglecting deep feature extraction of multichannel consecutive data. The unutilized sequential data contains the significant temporal information reflecting the transformer condition. In light of this, the structure of multichannel consecutive data cross-extraction (MCDC) is proposed in this article in order to comprehensively exploit the intrinsic characteristic and evaluate the states of transformer. Moreover, for the better accommodation in scenario of transformer diagnosis, one dimensional convolution neural network attention (1DCNN-attention) mechanism is introduced and offers a more efficient solution given the simplified spatial complexity. Finally, the effectiveness of MCDC and the superior generalization ability, compared with other algorithms, are validated in experiments conducted on a dataset collected from real operation cases of power transformer. Additionally, the better stability of 1DCNN-attention has also been certified.