A Dissolved Gas Prediction Method for Transformer On-Load Tap Changer Oil Integrating Anomaly Detection and Deep Temporal Modeling

The On-Load Tap Changer (OLTC), as a critical component of transformers, undergoes frequent switching operations that can lead to faults such as contact wear and arc discharge, which are often difficult to detect at an early stage using traditional monitoring methods. In particular, dissolved gas analysis (DGA) in OLTC oil is challenged by the unique oil gas decomposition mechanisms and the presence of background noise, making conventional DGA criteria less effective. Moreover, OLTC oil monitoring data are typically obtained through intermittent sampling, resulting in sparse time series with low resolution that complicate fault prediction. To address these challenges, this paper proposes an integrated framework combining LGOD-based anomaly detection, Locally Weighted Regression (LWR) for data repair, and the ETSformer temporal prediction model. This approach effectively identifies and corrects anomalies, restores the dynamic variation trends of gas concentrations, and enhances prediction accuracy through deep temporal modeling, thereby providing more reliable data support for OLTC state assessment and fault diagnosis. Experimental results demonstrate that the proposed method significantly improves prediction accuracy, enhances sensitivity to gas concentration evolution, and exhibits robust adaptability under both normal and fault scenarios. Furthermore, ablation experiments confirm that the observed performance gains are attributable to the complementary contributions of LGOD, LWR, and ETSformer, rather than any single component alone, highlighting the effectiveness of the integrated approach.