Real-time seismic response prediction for electrical equipment using CNN-MLP model
Renpeng Liu, Zhihang Xue, Qiang Xie
Abstract. Monitoring the seismic response of substation equipment is critical for developing effective real-time emergency response strategies. However, traditional monitoring approaches face significant challenges due to the electromagnetic sensitivity of electrical equipment. This study proposes a CNN-MLP neural network architecture that aggregates both long-duration seismic data and local temporal window information to enable real-time prediction of equipment acceleration responses based on seismic accelerations. Additionally, a beyond-range training strategy is introduced to enhance model performance under high-intensity seismic conditions. The proposed model is evaluated using a damped ±800kV wall bushing, which has been validated through shaking table tests, and compared to an LSTM model. Results show that the CNN-MLP model significantly outperforms the LSTM model, with the beyond-range training strategy effectively improving prediction accuracy and stability. This method requires only ground motion signals as input, avoiding the need to install sensors on electromagnetically sensitive equipment surfaces, thereby providing reliable support for emergency decision-making in substations during earthquakes.
Keywords
Substation Equipment, Seismic Response Prediction, Temporal Prediction, CNN-MLP, Wall Bushing
Published online 3/25/2025, 9 pages
Copyright © 2025 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Renpeng Liu, Zhihang Xue, Qiang Xie, Real-time seismic response prediction for electrical equipment using CNN-MLP model, Materials Research Proceedings, Vol. 50, pp 338-346, 2025
DOI: https://doi.org/10.21741/9781644903513-40
The article was published as article 40 of the book Structural Health Monitoring
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] Xie Qiang, Zhu Ruiyuan. Earth, Wind, and Ice[J]. IEEE Power and Energy Magazine, 2011, 9(2): 28-36. https://doi.org/10.1109/MPE.2010.939947
[2] He Chang, He Ziwei, Zhu Wang. Seismic interconnecting effects of multi-span flexible conductor-post electrical equipment coupling system[J]. Journal of Constructional Steel Research, 2024, 212: 108209. https://doi.org/10.1016/j.jcsr.2023.108209
[3] Shi Gaoyang, Xie Qiang, Liu Yun, et al. A design method on seismic isolation and reduction of post equipment in substation [J]. Journal of Vibration and Shock, 2023, 42(24): 109-116+142.
[4] Zhu Wang, Wu Minger, Xie Qiang, et al. Post-earthquake rapid assessment method for electrical function of equipment in substations[J]. IEEE Transactions on Power Delivery, 2023: 1-9. https://doi.org/10.1109/TPWRD.2023.3270178
[5] Zhu Wang, Xie Qiang. Post-earthquake rapid assessment for loop system in substation using ground motion signals[J]. Mechanical Systems and Signal Processing, 2024, 208: 111058. https://doi.org/10.1016/j.ymssp.2023.111058
[6] Torky Ahmed A, Ohno Susumu. Deep learning techniques for predicting nonlinear multi-component seismic responses of structural buildings[J]. Computers and Structures, 2021, 252: 106570. https://doi.org/10.1016/j.compstruc.2021.106570
[7] Huang Pengfei, Chen Zhiyi. Deep learning for nonlinear seismic responses prediction of subway station[J]. Engineering Structures, 2021, 244: 112735. https://doi.org/10.1016/j.engstruct.2021.112735
[8] Liao Yuchen, Zhang Ruiyang, Lin Rong, et al. A stacked residual lstm network for nonlinear seismic response prediction of bridges [J]. Engineering Mechanics, 2022: 1-12.
[9] Xu Zekun, Chen Jun, Shen Jiaxu, et al. Recursive long short-term memory network for predicting nonlinear structural seismic response[J]. Engineering Structures, 2022, null: null. https://doi.org/10.1016/j.engstruct.2021.113406
[10] Guo Yanyan, Chen Yafang, He Chang, et al. Seismic response prediction of electrical equipment interconnected system of traction station based on LSTM neural network [J]. Journal of Railway Science and Engineering, 2023: 1-11.
[11] Wang Xiaoyou, Xie Qiang, Luo Bing, et al. Seismic Responses and Vibration Control of ±800 kV Wall Bushing [J]. High Voltage Apparatus, 2018, 54(1): 16-22.
[12] Xie Qiang, Wang Xiaoyou, Hu Rong, et al. Shaking Table Tests on ±800 kV UHV DC Wall Bushing with Damper Devices [J]. High Voltage Engineering, 2018, 44(10): 3368-3374.
[13] GB 50011-2010, Code for seismic design of buildings, Beijing, 2010 (in Chinese).
[14] Ancheta Timothy D, Darragh Robert B, Stewart Jonathan P, et al. NGA-West2 database[J]. Earthquake Spectra, 2014, 30(3): 989-1005. https://doi.org/10.1193/070913EQS197M
[15] GB 50260-2013, Code for Seismic Design of Electrical Installations, Beijing, 2013 (in Chinese).
[16] Xu Zekun, Chen Jun. Neural network algorithm for nonlinear structural seismic response [J]. Engineering Mechanics, 2021, 38(9): 133-145.
