| Title |
A Hybrid CNN-LSTM Approach for Transformer Remaining Useful Life Prediction Using Dissolved Gas Analysis |
| Authors |
조동일(Dong-Il Cho) ; 문원식(Won-sik Moon) ; 남준혁(Jun-Hyuk Nam) ; 조윤진(Yun-Jin Cho) ; 한성호(Seong-Ho Han) |
| DOI |
https://doi.org/10.5370/KIEE.2026.75.1.223 |
| Keywords |
Remaining useful life; Dissolved gas analysis; convolutional neural networks; long short-term memory; Cox Proportional Hazards Model |
| Abstract |
Power transformers are critical assets in electrical grids, and accurately predicting their remaining useful life (RUL) is essential for predictive maintenance strategies. This paper presents a novel hybrid CNN-LSTM approach for Dissolved Gas Analysis (DGA) data that prioritizes computational efficiency while maintaining high prediction accuracy. The approach combines CNN for extracting spatial patterns from multi-dimensional gas concentrations and LSTM for modeling temporal dependencies, integrated with Cox proportional hazards regression for probabilistic survival predictions.
Using 30 years of DGA data, the proposed model achieved a C-index of 0.822, comparable to LSTM-only model while reducing training time by 89.3%. This 9.3× faster training speed makes the model highly suitable for industrial deployment where rapid model updates are essential. Optimization techniques including CBAM and mixed-precision training further enhanced efficiency. |