EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Hybrid CNN-LSTM Method for Seismic Classification and Time-Series Response Prediction of Disconnect Switch

Yijun Yan, Jianhui Feng, Guobin Li, Jiang He, Teng Ma, Lina Feng, Minjun Wu, Bingbing Zhang, Zhiguang Zhou

Buildings · 26.05.2026 · 16 (11) · 2131

DOI: 10.3390/buildings16112131 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Buildings, online erschienen am 26.05.2026. Verfasst von Yijun Yan und 8 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Shanghai Key Laboratory of Engineering Materials Application and Evaluation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To ensure a reliable electrical isolation point in power systems, the seismic performance assessment of disconnect switches is of critical importance for maintaining operational continuity under earthquake excitations. In this study, a hybrid method combining a convolutional neural network (CNN) and a long short-term memory (LSTM) network is proposed for the seismic intelligent classification and response prediction of disconnect switches. Unlike conventional approaches that rely on finite element simulations or shake table tests with high computational costs, the proposed method learns directly from raw ground motion records. The CNN component is designed to capture local frequency characteristics of input ground motions, enabling automatic classification into low-, medium-, or high-frequency categories. Subsequently, category-specific LSTM models are established to map the ground motion time series to multi-dimensional performance indicators of the disconnect switch. These indicators include top absolute accelerations, bottom shear forces, and relative deformations of porcelain posts. A training set comprising 102 ground motion records is constructed based on numerical simulations of a validated simplified model, while another testing set comparing 21 ground motion records are employed to validate the performance of predicted models. Training and validation results demonstrate that the CNN achieves a great classification accuracy. The LSTM predictions show good agreement with the computed time-history responses, with errors of root-mean-square responses generally within 10%. The proposed method provides a rapid, data-driven alternative to traditional seismic analysis, significantly reducing computational time while preserving prediction fidelity. It also enables the parallel prediction of multiple coupled performance indicators, which is not readily achievable by existing single-output surrogate models.

Förderung

  • National Key Research and Development Program of China
  • Shanghai Key Laboratory of Engineering Materials Application and Evaluation

Zitieren

APA

Yan, Y., Feng, J., Li, G., He, J., Ma, T., Feng, L., Wu, M., Zhang, B., & Zhou, Z. (2026). A Hybrid CNN-LSTM Method for Seismic Classification and Time-Series Response Prediction of Disconnect Switch. Buildings, 16(11), 2131. https://doi.org/10.3390/buildings16112131

Vancouver

Yan Y, Feng J, Li G, He J, Ma T, Feng L, et al. A Hybrid CNN-LSTM Method for Seismic Classification and Time-Series Response Prediction of Disconnect Switch. Buildings. 2026;16(11):2131. doi:10.3390/buildings16112131

BibTeX
@article{Yan2026,
  author = {Yan, Yijun and Feng, Jianhui and Li, Guobin and He, Jiang and Ma, Teng and Feng, Lina and Wu, Minjun and Zhang, Bingbing and Zhou, Zhiguang},
  title = {A Hybrid CNN-LSTM Method for Seismic Classification and Time-Series Response Prediction of Disconnect Switch},
  journal = {Buildings},
  year = {2026},
  volume = {16},
  number = {11},
  pages = {2131},
  doi = {10.3390/buildings16112131}
}
Kostenlos starten →