EUVIMEDEUVIMED entdecken
Crossref

Quantitative analysis of transformer fault gas acetylene photothermal spectroscopy data based on CNN-WAM-LSTM

Xingang Chen, Bowen Luo, Lei Zhu, Yi Ao, Fanbo Wei, Jinmei Liang

Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2026-12 · 363 · 128333

DOI: 10.1016/j.saa.2026.128333 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2026-12. Verfasst von Xingang Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, China; Chongqing Energy Internet Engineering T…. Die Arbeit nennt 37 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The detection of acetylene content in the fault gas of oil immersed transformers is the key to determining the type of internal faults and safe operation of the equipment. The photothermal spectroscopy method has a high sensitivity advantage in detecting fault gases, but there are problems such as information redundancy in the analysis process of photothermal spectroscopy data. This article proposes an improved convolutional neural network quantitative model that integrates wavelength attention mechanism and long short-term memory model, and designs and builds a photothermal spectroscopy platform based on Sagnac interference structure to collect C2H2 multi concentration samples. The dataset is augmented with data augmentation to enhance the robustness and generalization of the model. Optimize the model structure and network weights through experiments, complete model training, and verify prediction performance. Verify the contribution of wavelength attention and long short-term memory models through ablation experiments, and compare them with SVR, PLS, and XGBoost. The results indicate that the model has good prediction accuracy, outperforming traditional regression models in R2, RMSE, MAE, and MAPE indicators, and is suitable for quantitative analysis of gas spectra in transformer faults.

Schlagwörter

Stichwörter der Autor:innen

AcetyleneDeep learning networksOil-immersed transformerPhotothermal spectroscopyQuantitative analysis

Autor:innen und Institutionen

  • School of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, China; Chongqing Energy Internet Engineering Technology Research Center, Chongqing 400054, China.
  • School of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, China. Electronic address: luobowen@stu.cqut.edu.cn.
  • State Key Laboratory of Power Transmission Equipment Technology, School of Electrical Engineering, Chongqing University, Chongqing 400044, China.
  • School of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, China.

Zitieren

APA

Chen, X., Luo, B., Zhu, L., Ao, Y., Wei, F., & Liang, J. (2026). Quantitative analysis of transformer fault gas acetylene photothermal spectroscopy data based on CNN-WAM-LSTM. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 363, 128333. https://doi.org/10.1016/j.saa.2026.128333

Vancouver

Chen X, Luo B, Zhu L, Ao Y, Wei F, Liang J. Quantitative analysis of transformer fault gas acetylene photothermal spectroscopy data based on CNN-WAM-LSTM. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2026;363:128333. doi:10.1016/j.saa.2026.128333

BibTeX
@article{Chen2026,
  author = {Chen, Xingang and Luo, Bowen and Zhu, Lei and Ao, Yi and Wei, Fanbo and Liang, Jinmei},
  title = {Quantitative analysis of transformer fault gas acetylene photothermal spectroscopy data based on CNN-WAM-LSTM},
  journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
  year = {2026},
  volume = {363},
  pages = {128333},
  doi = {10.1016/j.saa.2026.128333}
}
Kostenlos starten →