[1]GUO Maozu,ZHANG Xinxin,ZHAO Lingling,et al.Phy-LInformers approach toward structural seismic response prediction[J].CAAI Transactions on Intelligent Systems,2024,19(4):1027-1041.[doi:10.11992/tis.202404002]
Copy

Phy-LInformers approach toward structural seismic response prediction

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 19 Number of periods: 2024 4 Page number: 1027-1041 Column: 人工智能院长论坛 Public date: 2024-07-05
Title:
Phy-LInformers approach toward structural seismic response prediction
Author(s):
GUO Maozu1; 2;  ZHANG Xinxin1; 2;  ZHAO Lingling3;  ZHANG Qingyu1; 2
1. School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044, China;
2. Beijing Key Laboratory of Intelligent Processing for Building Big Data, Beijing University of Civil Engineering and Architecture, Beijing 100044, China;
3. Faculty of Computing, Harbin Institute of Technology, Harbin 150001, China
Keywords:
seismic response prediction; physical knowledge; physics-informed deep learning; time series forecasting; few shot learning; Informer; long short-term memory; Phy-LInformers
CLC:
TP18
DOI:
10.11992/tis.202404002
Abstract:
In order to accurately assess the dynamic and ductile properties of building structures under seismic action and to promote the construction of resilient cities and towns, in this study, we introduce a novel deep learning framework denoted as Phy-LInformers, which integrates long short-term memory (LSTM), Transformer-based model Informer, and prior physical knowledge to achieve precise prediction of nonlinear seismic responses in building structures. The central concept of Phy-LInformers lies in fusing the Encoder and Decoder architectures of Informer, while integrating LSTM within the Decoder component to forecast preceding historical states of the building. Meanwhile, the learning space of the Phy-LInformers’ training process is instructed and constrained by encoding existing physical knowledge (e.g., state dependencies between predictor variables and motion control equations, etc.) into the loss function. And at the same time, the prediction performance of the deep learning model is improved with limited training data. Subsequently, the satisfactory performance of the proposed framework is successfully demonstrated through two illustrative examples. The results demonstrate that the proposed Phy-LInformers is a nonlinear seismic response prediction method with better robustness and superior prediction performance, which can still accurately predict the dynamic response of a structure under seismic excitation even with very few training samples (e.g., only 10 samples). This feature makes Phy-LInformers feasible for engineering practice and shows promising application prospects in the field of seismic performance evaluation of building structures.
References:
[1] 史翔宇. 基于机器学习回归算法的地震预测研究及其在中国地震科学实验场的应用[D]. 北京: 中国地震局地震预测研究所, 2021.
SHI Xiangyu. Research on earthquake prediction based on machine learning regression algorithm and its application in China seismic experimental site[D]. Beijing: Institute of Earthquake Forecasting of the China Earthquake Administration, 2021.
[2] 孙柏涛, 张桂欣. 中国大陆建筑物地震灾害风险分布研究[J]. 土木工程学报, 2017, 50(9): 1-7.
SUN Baitao, ZHANG Guixin. Study on seismic disaster risk distribution of buildings in mainland China[J]. China civil engineering journal, 2017, 50(9): 1-7.
[3] 邓家屯. 基于机器学习的区域RC框架结构地震响应与构件损伤预测[D]. 广州: 华南理工大学, 2022.
DENG Jiatun. Seismic response and component damage prediction of regional RC frame structures based on machine learning[D]. Guangzhou: South China University of Technology, 2022.
[4] 商昊江, 祁皑. 高层隔震结构减震机理探讨[J]. 振动与冲击, 2012, 31(4): 8-12,17.
SHANG Haojiang, QI Ai. Isolation mechanism of high-rise isolation structrue[J]. Journal of vibration and shock, 2012, 31(4): 8-12,17.
[5] 武芳文, 赵雷. 大跨度斜拉桥地震响应非线性时程分析[J]. 世界地震工程, 2009, 25(4): 18-24.
WU Fangwen, ZHAO Lei. Nonlinear time-history analysis of seismic response of a long-span cab le-stayed bridge[J]. World earthquake engineering, 2009, 25(4): 18-24.
[6] 汪鑫. 基于优化神经网络的多层钢筋混凝土结构地震响应预测[D]. 哈尔滨: 哈尔滨工业大学, 2020.
WANG Xin. Prediction of seismic response of multi-story reinforced concrete structures based on optimized neural network[D]. Harbin: Harbin institute of Technology, 2020.
[7] 郑史雄, 雷川鹤, 贾宏宇, 等. 人工智能技术在桥梁抗震领域的应用综述[J]. 地震工程与工程振动, 2023, 43(4): 1-13.
ZHENG Shixiong, LEI Chuanhe, JIA Hongyu, et al. Application overview of artificial intelligence technology in bridge seismic field[J]. Earthquake engineering and engineering dynamics, 2023, 43(4): 1-13.
[8] DE LAUTOUR O R, OMENZETTER P. Prediction of seismic-induced structural damage using artificial neural networks[J]. Engineering structures, 2009, 31(2): 600-606.
[9] NGUYEN H D, DAO N D, SHIN M. Prediction of seismic drift responses of planar steel moment frames using artificial neural network and extreme gradient boosting[J]. Engineering structures, 2021, 242: 112518.
[10] 赵煜东, 许卫晓, 于德湖, 等. 基于人工神经网络的RC框架结构地震响应预测方法[J]. 地震研究, 2024, 47(1): 123-134.
ZHAO Yudong, XU Weixiao, YU Dehu, et al. Response prediction method of the RC frame structure based on the artificial neural network[J]. Journal of seismological research, 2024, 47(1): 123-134.
[11] HWANG S H, MANGALATHU S, SHIN J, et al. Machine learning-based approaches for seismic demand and collapse of ductile reinforced concrete building frames[J]. Journal of building engineering, 2021, 34: 101905.
[12] 牛志辉, 陈波, 卜春尧. 基于卷积神经网络的速度大脉冲识别方法研究[J]. 震灾防御技术, 2021, 16(3): 485-491.
NIU Zhihui, CHEN Bo, BU Chunyao. Identification of pulse-like strong ground motions based on convolution neural network[J]. Technology for earthquake disaster prevention, 2021, 16(3): 485-491.
[13] WEN Weiping, ZHANG Chenyu, ZHAI Changhai. Rapid seismic response prediction of RC frames based on deep learning and limited building information[J]. Engineering structures, 2022, 267: 114638.
[14] OH B K, GLISIC B, PARK S W, et al. Neural network-based seismic response prediction model for building structures using artificial earthquakes[J]. Journal of sound and vibration, 2020, 468: 115109.
[15] XU Y, LU X, CETINER B, et al. Real-time regional seismic damage assessment framework based on long short-term memory neural network[J]. Computer-aided civil and infrastructure engineering, 2021, 36(4): 504-521.
[16] LIN KY, LIN TK, LIN Y. Real-time seismic structural response prediction system based on support vector machine[J]. Earthquakes and structures, 2020, 18(2): 163-170.
[17] ZHANG Xiaoyu, CHEN Jia, WU Yang, et al. Predicting the maximum seismic response of the soil-pile-superstructure system using random forests[J]. Journal of earthquake engineering, 2022, 26(15): 8120-8141.
[18] CHOU J S, NGO N T, PHAM A D. Shear strength prediction in reinforced concrete deep beams using nature-inspired metaheuristic support vector regression[J]. Journal of computing in civil engineering, 2016, 30(1): 04015002.
[19] MORFIDIS K, KOSTINAKIS K. Rapid prediction of seismic incident angle’s influence on the damage level of RC buildings using artificial neural networks[J]. Applied sciences, 2022, 12(3): 1055.
[20] 李金珂. 基于低成本层间位移监测的建筑结构地震安全评定方法[D]. 大连: 大连理工大学, 2021.
LI Jinke. Seismic safety assessment method of building structures based on low-cost inter-story displacement monitoring methods[D]. Dalian: Dalian University of Technology, 2021.
[21] 施静. BO-CatBoost在西部地区地震预测中的应用[D]. 桂林: 广西师范大学, 2023.
SHI Jing. Application of BO-CatBoost to earthquake prediction in western China[D]. Guilin: Guangxi Normal University, 2023.
[22] 禹海涛, 朱晨阳. 基于BP神经网络的圆形隧道地震响应预测方法及参数分析[J]. 隧道与地下工程灾害防治, 2023, 5(3): 19-26.
YU Haitao, ZHU Chenyang. A BP neural network-based prediction method for seismic response of circular tunnel linings and parameter analysis[J]. Hazard control in tunneling and underground engineering, 2023, 5(3): 19-26.
[23] ZHANG Ruiyang, CHEN Zhao, CHEN Su, et al. Deep long short-term memory networks for nonlinear structural seismic response prediction[J]. Computers & structures, 2019, 220: 55-68.
[24] OH B K, PARK Y, PARK H S. Seismic response prediction method for building structures using convolutional neural network[J]. Structural control and health monitoring, 2020, 27(5): e2519.
[25] TORKY A A, OHNO S. Deep learning techniques for predicting nonlinear multi-component seismic responses of structural buildings[J]. Computers & structures, 2021, 252: 106570.
[26] ZAMANI A A, ETEDALI S. Seismic response prediction of open-and closed-loop structural control systems using a multi-state-dependent parameter estimation approach[J]. International journal of computational methods, 2022, 19(5): 2250006.
[27] MENG Chuizheng, SEO S, CAO D, et al. When physics meets machine learning: a survey of physics-informed machine learning[EB/OL]. (2022-03-31) [2023-03-07]. https://arxiv.org/abs/2203.16797.
[28] HAO Zhongkai, LIU Songming, ZHANG Yichi, et al. Physics-informed machine learning: a survey on problems, methods and applications[EB/OL]. (2022-11-15)[2023-03-07]. https://arxiv.org/abs/2211.08064.
[29] KARNIADAKIS G E, KEVREKIDIS I G, LU L, et al. Physics-informed machine learning[J]. Nature reviews physics, 2021, 3: 422-440
[30] WILLARD J, JIA X, XU S, et al. Integrating physics-based modeling with machine learning: a survey[EB/OL]. (2020-3-10)[2022-03-14]. https://arxiv.org/abs/2003.04919v1.
[31] YU Yang, YAO Houpu, LIU Yongming. Structural dynamics simulation using a novel physics-guided machine learning method[J]. Engineering applications of artificial intelligence, 2020, 96: 103947.
[32] ESHKEVARI S S, TAKA M, PAKZAD S N, et al. DynNet: physics-based neural architecture design for nonlinear structural response modeling and prediction[J]. Engineering structures, 2021, 229: 111582.
[33] GUO Jia. Combination of physics-based and data-driven modeling for structural seismic response prediction[C]// The 66th Japan National Congress for Theoretical and Applied Mechanics. Tokyo: National Committee for IUTAM, 2022: 131.
[34] WANG T, LI H, NOORI M, et al. Seismic response prediction of structures based on Runge-Kutta recurrent neural network with prior knowledge[J]. Engineering structures, 2023, 279: 115576.
[35] ZHANG Ruiyang, LIU Yang, SUN Hao. Physics-guided convolutional neural network (PhyCNN) for data-driven seismic response modeling[J]. Engineering structures, 2020, 215: 110704.
[36] ZHANG Ruiyang, LIU Yang, SUN Hao. Physics-informed multi-LSTM networks for metamodeling of nonlinear structures[J]. Computer methods in applied mechanics and engineering, 2020, 369: 113226.
[37] VASWANJ A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.
[38] ZHOU Haoyi, ZHANG Shanghang, PENG Jieqi, et al. Informer: beyond efficient transformer for long sequence time-series forecasting[C]//Proceedings of AAAI. Vancouver: AAAI. 2021.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems