• Indexed in Scopus
  • Source Journal for Chinese Scientific and Technical Papers and Citations
  • Included in A Guide to the Core Journal of China
  • Indexed in Ei Compendex
YU Haitao, ZHU Chenyang, FU Dabao, XU Naixing, LU Zhechao, CAI Huiteng. A hybrid method to identify pulse-like ground motions and pulse periods based on ST-CNN[J]. Chinese Journal of Geotechnical Engineering, 2024, 46(12): 2675-2683. DOI: 10.11779/CJGE20230766
Citation: YU Haitao, ZHU Chenyang, FU Dabao, XU Naixing, LU Zhechao, CAI Huiteng. A hybrid method to identify pulse-like ground motions and pulse periods based on ST-CNN[J]. Chinese Journal of Geotechnical Engineering, 2024, 46(12): 2675-2683. DOI: 10.11779/CJGE20230766

A hybrid method to identify pulse-like ground motions and pulse periods based on ST-CNN

More Information
  • Received Date: August 10, 2023
  • Available Online: July 08, 2024
  • The rapid and precise identification of the pulse-like ground motions is a key challenge that perplexes both the academic and engineering communities. The quantitative identification methods can overcome the empirical limitations of manual identification. However, the traditional quantitative identification methods suffer from inconsistencies in the identified results, limited applicability, and difficulties in simultaneously determining the accurate pulse periods. In response, a problem-targeted fusion learning rule is established, combined with a convolutional neural network (CNN) model, to develop a novel method to synchronously identify pulse-like ground motions and their pulse periods. This learning rule integrates multiple traditional typical identification methods based on different identification principles, thereby eliminating the cumbersome manual labeling process. It employs 30000 ground motion data from arbitrary directions worldwide for training and validation, resulting in three problem-targeted CNN models named the Strict, General, and TP identification models. To address the issue of insufficient temporal input information for ground motions leading to weak model generalization capability, the input structure of the CNN model is optimized, and the ST-CNN model is proposed, incorporating the S-transform layer to convert ground motion time series to time frequency, thereby enhancing frequency domain distribution information and further improving the identification accuracy. The results indicate that the Strict model can strictly differentiate between the pulse-like and non-pulse-like ground motions, with the results consistent with those of other methods. The General model can identify more pulse-like ground motions and has broader applicability. The TP model accurately identifies pulse periods and can be used in conjunction with the aforementioned models to synchronously output the identified results. The proposed problem-targeted fusion learning rule can also be extended to other engineering fields and other machine learning models, and the established identification method can provide scientific guidance for the study on the pulse-like ground motions.
  • [1]
    SOMERVILLE P G, SMITH N F, GRAVES R W, et al. Modification of empirical strong ground motion attenuation relations to include the amplitude and duration effects of rupture directivity[J]. Seismological Research Letters, 1997, 68(1): 199-222. doi: 10.1785/gssrl.68.1.199
    [2]
    SCHIAPPAPIETRA E, LANZANO G, SGOBBA S. Empirical predictive models for fling step and displacement response spectra based on the NESS database[J]. Soil Dynamics and Earthquake Engineering, 2022, 158: 107294. doi: 10.1016/j.soildyn.2022.107294
    [3]
    谢俊举, 温增平, 李小军, 等. 基于小波方法分析汶川地震近断层地震动的速度脉冲特性[J]. 地球物理学报, 2012, 55(6): 1963-1972.

    XIE Junju, WEN Zengping, LI Xiaojun, et al. Analysis of velocity pulses for near-fault strong motions from the Wenchuan earthquake based on wavelet method[J]. Chinese Journal of Geophysics, 2012, 55(6): 1963-1972. (in Chinese)
    [4]
    谢俊举, 李小军, 温增平. 近断层速度大脉冲对反应谱的放大作用[J]. 工程力学, 2017, 34(8): 194-211.

    XIE Junju, LI Xiaojun, WEN Zengping. The amplification effects of near-fault distinct velocity pulses on response spectra[J]. Engineering Mechanics, 2017, 34(8): 194-211. (in Chinese)
    [5]
    SHAHI S K, BAKER J W. An empirically calibrated framework for including the effects of near-fault directivity in probabilistic seismic hazard analysis[J]. The Bulletin of the Seismological Society of America, 2011, 101(2): 742-755. doi: 10.1785/0120100090
    [6]
    SHAHI S K, BAKER J W. An efficient algorithm to identify strong-velocity pulses in multicomponent ground motions[J]. The Bulletin of the Seismological Society of America, 2014, 104(5): 2456-2466. doi: 10.1785/0120130191
    [7]
    梅贤丞, 崔臻, 盛谦. 近断层/远场地震动作用下隧道结构易损性研究[J]. 岩石力学与工程学报, 2021, 40(2): 344-354.

    MEI Xiancheng, CUI Zhen, SHENG Qian. Research on vulnerability of tunnel structures subjected to near-fault and far-field ground motions[J]. Chinese Journal of Rock Mechanics and Engineering, 2021, 40(2): 344-354. (in Chinese)
    [8]
    MAVROEIDIS G P. A mathematical representation of near-fault ground motions[J]. The Bulletin of the Seismological Society of America, 2003, 93(3): 1099-1131. doi: 10.1785/0120020100
    [9]
    BAKER J W. Quantitative classification of near-fault ground motions using wavelet analysis[J]. The Bulletin of the Seismological Society of America, 2007, 97(5): 1486-1501. doi: 10.1785/0120060255
    [10]
    CHANG Z W, SUN X D, ZHAI C H, et al. An improved energy-based approach for selecting pulse-like ground motions[J]. Earthquake Engineering & Structural Dynamics, 2016, 45(14): 2405-2411.
    [11]
    ZHAI C H, LI C H, KUNNATH S, et al. An efficient algorithm for identifying pulse-like ground motions based on significant velocity half-cycles[J]. Earthquake Engineering & Structural Dynamics, 2018, 47(3): 757-771.
    [12]
    王东升, 陈笑宇, 张锐, 等. 基于希尔伯特-黄变换的近断层地震动脉冲特性研究[J]. 地震学报, 2022, 44(5): 824-844.

    WANG Dongsheng, CHEN Xiaoyu, ZHANG Rui, et al. Characteristics of pulses in near-fault ground motion based on Hilbert-Huang transform[J]. Acta Seismologica Sinica, 2022, 44(5): 824-844. (in Chinese)
    [13]
    FUKUSHIMA K. Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J]. Biological Cybernetics, 1980, 36(4): 193-202. doi: 10.1007/BF00344251
    [14]
    XU Y, WEI S Y, BAO Y Q, et al. Automatic seismic damage identification of reinforced concrete columns from images by a region-based deep convolutional neural network[J]. Structural Control and Health Monitoring, 2019, 26(3): e2313. doi: 10.1002/stc.2313
    [15]
    姬建, 姜振, 殷鑫, 等. 边坡随机场数字图像特征CNN深度学习及可靠度分析[J]. 岩土工程学报, 2022, 44(8): 1463-1473. doi: 10.11779/CJGE202208011

    JI Jian, JIANG Zhen, YIN Xin, et al. Slope reliability analysis based on deep learning of digital images of random fields using CNN[J]. Chinese Journal of Geotechnical Engineering, 2022, 44(8): 1463-1473. (in Chinese) doi: 10.11779/CJGE202208011
    [16]
    MIMOGLOU P, PSYCHARIS I N, TAFLAMPAS I M. Explicit determination of the pulse inherent in pulse-like ground motions[J]. Earthquake Engineering & Structural Dynamics, 2014, 43(15): 2261-2281.
    [17]
    STOCKWELL R G, MANSINHA L, LOWE R P. Localization of the complex spectrum: the S transform[J]. IEEE Transactions on Signal Processing, 1996, 44(4): 998-1001.
    [18]
    ZHAI C, CHANG Z, LI S, et al. Quantitative identification of near-fault pulse-like ground motions based on energy[J]. The Bulletin of the Seismological Society of America, 2013, 103(5): 2591-2603.
    [19]
    SOMERVILLE P G. Magnitude scaling of the near fault rupture directivity pulse[J]. Physics of the Earth and Planetary Interiors, 2003, 137(1/2/3/4): 201-212.
    [20]
    TANG Y C, ZHANG J. Response spectrum-oriented pulse identification and magnitude scaling of forward directivity pulses in near-fault ground motions[J]. Soil Dynamics and Earthquake Engineering, 2011, 31(1): 59-76.
  • Related Articles

    [1]ZHANG Kunbiao, WANG Yimin, CHEN Yekai, QIU Shen, YI Hao, ZENG Zhaoyu. Mechanism of reinforcement of squeezed branch piles for deep soft foundation based on load bearing capacities[J]. Chinese Journal of Geotechnical Engineering, 2024, 46(S2): 97-102. DOI: 10.11779/CJGE2024S20009
    [2]WU Ai-qing, WU Qing-hua. Evolution mechanism of dike risks, quick detection of hidden dangers, and technical equipments of emergency rescues[J]. Chinese Journal of Geotechnical Engineering, 2022, 44(7): 1310-1328. DOI: 10.11779/CJGE202207010
    [3]CAI Yao-jun, ZHOU Zhao, YANG Xing-guo, WEI Ying-qi, ZHENG Dong-jian, PENG Wen-xiang, ZHONG Qi-ming, WANG Heng. Rapid detection for risk assessment, emergency disposal technology and equipment development of barrier lakes[J]. Chinese Journal of Geotechnical Engineering, 2022, 44(7): 1266-1280. DOI: 10.11779/CJGE202207007
    [4]ZHANG Zong-liang, WU Xue-ming, WANG Kun, HE Ning, ZHOU Yan-zhang. Researches and application of key technologies for risk analysis and emergency rescue of landslide-dammed lakes[J]. Chinese Journal of Geotechnical Engineering, 2020, 42(S2): 13-19. DOI: 10.11779/CJGE2020S2003
    [5]ZHU Yan-peng, ZHU Sheng-xiang, YE Shuai-hua, ZHENG Xiao-jing. Analysis and secondary reinforcement design of a deep foundation pit accident[J]. Chinese Journal of Geotechnical Engineering, 2014, 36(zk1): 186-191. DOI: 10.11779/CJGE2014S1032
    [6]FU Wen-guang. Discussions on emergency rescue management mechanism for foundation pit engineering according to several unexpected dangers[J]. Chinese Journal of Geotechnical Engineering, 2014, 36(zk1): 165-174. DOI: 10.11779/CJGE2014S1029
    [7]FENG Chen, FENG Shen-hui. Prevention and treatment of shallow pit accidents in deep and soft soil areas[J]. Chinese Journal of Geotechnical Engineering, 2012, 34(suppl): 711-714.
    [8]LIU Yi, LI Jing-pei, CHEN Wei. Effect of reinforcement of deep mixing piles on deformation of ultra-deep excavations in passive zone[J]. Chinese Journal of Geotechnical Engineering, 2012, 34(suppl): 465-469.
    [9]SHAO Guang-biao, SUN Jian-ping, JIANG Zong-bao. Reinforcing design and construction technology of large-diameter artificial bored pile segregation accident[J]. Chinese Journal of Geotechnical Engineering, 2011, 33(sup2): 260-264.
    [10]Zhou Guo-jun, Hu Tong-an, Sha Bing-chun, Liu Yun-zhao. A New Technique of Reinforcing Soft Cohesive Ground by Deep Mixing Method[J]. Chinese Journal of Geotechnical Engineering, 1981, 3(4): 54-65.

Catalog

    Article views (295) PDF downloads (75) Cited by()
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return