1.上海交通大学船舶海洋与建筑工程学院, 上海 200240
2.上海市公共建筑和基础设施数字化运维重点实验室,上海 200240
3.上海市城市建设设计研究总院(集团)有限公司,上海 200001
安超(1997—),男,硕士研究生。主要从事建筑抗震信息化研究。E-mail:ankh123@sjtu.edu.cn
史健勇(1975—),男,副教授,博士。主要从事建筑信息化、智慧城市等研究。E-mail:shijy@sjtu.edu.cn
收稿:2022-11-25,
修回:2023-03-07,
纸质出版:2023-06-28
移动端阅览
安超,史健勇,潘泽宇等.基于集成学习的结构地震动响应预测方法研究[J].防灾减灾工程学报,2023,43(03):435-443.
AN Chao,SHI Jianyong,PAN Zeyu,et al.Research on Prediction Method of Structural Seismic Response Based on Ensemble Learning[J].Journal of Disaster Prevention and Mitigation Engineering,2023,43(03):435-443.
安超,史健勇,潘泽宇等.基于集成学习的结构地震动响应预测方法研究[J].防灾减灾工程学报,2023,43(03):435-443. DOI: 10.13409/j.cnki.jdpme.20221125002.
AN Chao,SHI Jianyong,PAN Zeyu,et al.Research on Prediction Method of Structural Seismic Response Based on Ensemble Learning[J].Journal of Disaster Prevention and Mitigation Engineering,2023,43(03):435-443. DOI: 10.13409/j.cnki.jdpme.20221125002.
为获取建筑结构在地震过程中的位移响应,解决结构主动控制中的时滞问题,使用集成学习方法预测结构位移响应。提出了一套适用于结构地震动响应预测的集成学习模型,使用不同的神经网络和损失函数组合作为基学习器,在此基础上使用全连接网络构建二级学习器,得到最终预测模型。模型使用双向地震动加速度和结构位移响应作为输入,预测短期的结构位移响应;结构位移响应可实现多步预测,进行动态化输出。将该框架应用于某钢框架结构,进行数值实验,结果表明,集成后的模型预测结果要优于单一模型的预测结果,所有模型都表现出预测误差随着预测时间的增加而增加的规律。模型的预测随着地震过程在同步进行,当模型预测值第一次达到某一阈值时,则将预测结果反馈到主动控制系统中,提前进行结构振动控制,而不必等待位移传感器采集到真实的响应数据,从而减小甚至避免主动控制中时滞问题的影响。
In order to obtain the displacement response of building structures in the earthquake process, and solve the delay problem in the active control of structures, ensemble learning was used to predict the seismic structural response. In this paper, an ensemble learning model is proposed for the prediction of ground motion response of structures. Different neural networks and loss functions are combined as the base learners, then a Fully Connected Neural Network is used to construct a second-level learner to obtain the final prediction model. Bidirectional ground motion acceleration and structural displacement response are used as inputs to predict the short-term structural seismic response. This model could realize multi-step prediction of structural seismic response and dynamic outputs. Several numerical experiments are carried out on a steel frame structure, and the experimental results show that the prediction results of the integrated model is better than those of the single model, and all models display a trend of prediction errors increasing with the increase of the prediction time. When the model’s predicted value reaches a certain threshold for the first time, the prediction result will be sent to the active control system, so the structure vibration control will be carried out in advance without waiting for the real response data collected by displacement sensors, thereby reducing or even negating the influence of time delay in active control.
Yao J T P . Concept of structural control [J]. Asce Journal of the Structural Division , 1972 , 98 ( 7 ): 1567 - 1574 .
王伟 . 土木工程结构振动控制技术的发展 [J]. 居业 , 2022 ( 3 ): 10 - 12 .
Wang W . Development of vibration control technology for civil engineering structures [J]. Residential Engineering , 2022 ( 3 ): 10 - 12 . (in Chinese)
邱敏 , 张学文 , 陆中玏 , 等 . 土木工程结构振动控制的研究现状与展望 [J]. 安全与环境工程 , 2013 , 20 ( 3 ): 14 - 18 .
Qiu M , Zhang X W , Lu Z L , et al . Research status and prospect of structural vibration control in civil engineering [J]. Safety and Environmental Engineering , 2013 , 20 ( 3 ): 14 - 18 . (in Chinese)
郑晓君 . 结构主动控制系统时滞补偿及混合试验研究 [D]. 广州 : 广州大学 , 2022 .
Zheng X J . Research on delay compensation and hybrid experiment of structural active control system [D]. Guangzhou : Guangzhou University , 2022 . (in Chinese)
Zou L H , Dai S L , Butterworth J , et al . Grey forecasting model for active vibration control systems [J]. Journal of Sound and Vibration , 2009 , 322 ( 4/5 ): 690 - 706 .
Zhang R Y , Liu Y , Sun H . Physics-informed multi-LSTM networks for metamodeling of nonlinear structures [J]. Computer Methods in Applied Mechanics and Engineering , 2020 , 369 : 113226 .
许泽坤 , 陈隽 . 非线性结构地震响应的神经网络算法 [J]. 工程力学 , 2021 , 38 ( 9 ): 133 - 145 .
Xu Z K , Chen C . Neural network algorithm for seismic response of nonlinear structures [J]. Engineering Mechanics , 2021 , 38 ( 9 ): 133 - 145 . (in Chinese)
杨迪雄 , 杨开胜 , 郭贵强 . 强震作用下高层结构地震响应时程的多步预测 [J]. 土木工程学报 , 2016 , 49 ( 增1 ): 25 - 31 .
Yang D X , Yang K S , Guo G Q . Multi-step prediction of seismic response time history of high-rise structures under strong earthquakes [J]. Chinese Journal of Civil Engineering , 2016 , 49 ( Sup1 ): 25 - 31 . (in Chinese)
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 X . Seismic response prediction of multi-storey reinforced concrete structures based on optimized neural network [D]. Harbin : Harbin Institute of Technology , 2020 . (in Chinese)
Hochreiter S , Schmidhuber J . Long short-term memory [J]. Neural Computation , 1997 , 9 ( 8 ): 1735 - 1780 .
Chung J , Gulcehre C , Cho K , et al . Empirical evaluation of gated recurrent neural networks on sequence modeling [J]. Eprint Arxiv , 2014 . DOI: 10.48550/arXiv.1412.3555 http://dx.doi.org/10.48550/arXiv.1412.3555 .
Waibel A , Hanazawa T , Hinton G E , et al . Phoneme recognition using time-delay neural networks [J]. Readings in Speech Recognition , 1990 , 1 ( 3 ): 393 - 404 .
Lecun Y , Bottou L . Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE , 1998 , 86 ( 11 ): 2278 - 2324 .
Lawrence S , Giles C L , Tsoi A C , et al . Face recognition: a convolutional neural network approach [J]. IEEE Transactions on Neural Networks , 1997 , 8 ( 1 ): 98 - 113 .
李炳臻 , 刘克 , 顾佼佼 , 等 . 卷积神经网络研究综述 [J]. 计算机时代 , 2021 ( 4 ): 8 - 12,17 .
Li B Z , Liu K , Gu J J , et al . Review of convolutional neural networks [J]. Computer Age , 2021 ( 4 ): 8 - 12,17 . (in Chinese)
Cuturi M , Blondel M . Soft-DTW: a differentiable loss function for time-series [C]∥ 34th International Conference on Machine Learning , ICML . Sydney : International Machine Learning Society(IMLS) , 2017 : 1483 - 1505 .
Le Guen V , Thome N . Shape and time distortion loss for training deep time series forecasting models [C]∥ Advances in Neural Information Processing Systems . [S.l.] : Neural Information Processing Systems Foundation , 2019 : 32 .
Wang K , Liu X , Zhao J , et al . Application research of ensemble learning frameworks [C]∥ Proceedings of 2020 Chinese Automation Congress , CAC 2020 , art. no. 9326882 . Shanghai : Institute of Electrical and Electronics Engineers(IEEE) ,2020: 5767 - 5772 .
0
浏览量
0
下载量
1
CSCD
关联资源
相关文章
相关作者
相关机构
苏公网安备32010202012147号
