桥梁-雨棚组合结构在市政工程中的应用日益增多。这类桥梁-雨棚组合结构通常采用分离式的抗震设计，在桥梁结构的抗震设计过程中未考虑雨棚的影响。这种设计方法依赖经验，需要反复迭代才能达到预期设计目标，而且不能有效利用雨棚对桥梁抗震的辅助作用。针对上述问题，本文开展了桥梁-雨棚组合结构联合式抗震设计研究，并以桥梁-雨棚组合结构的联合抗震性能为目标，提出了一种基于机器学习的抗震设计优化方法。

本文以一座3×30m带雨棚连续刚构桥为例，基于联合式抗震分析，研究该桥梁-雨棚组合结构的关键设计参数对其抗震性能的影响，并利用机器学习算法对其进行了设计参数优化。主要研究内容如下：

（1）调谐减振原理在桥梁-雨棚组合结构中的适用性及局限性研究。将桥梁-雨棚组合结构简化为双自由度模型，基于地震作用下组合结构的动力学分析，发现桥墩刚度、主梁质量、雨棚侧向刚度和雨棚质量等关键设计参数组合，共同决定了桥梁-雨棚组合结构的位移响应。依据调谐减振原理，当雨棚固有频率接近桥梁固有频率时，桥梁的地震响应减小，但雨棚的地震响应增大。

（2）基于性能的桥梁-雨棚组合结构抗震设计关键参数分析。联合式抗震设计方法可同时考虑桥梁和雨棚的地震响应，合理的设计参数组合可改善桥梁-雨棚组合结构的抗震性能。在桥梁-雨棚组合结构的设计参数接近谐振时，联合式抗震设计方法可以通过简单迭代得到合理设计参数组合，从而有效地提升桥梁-雨棚组合结构的综合抗震性能。但是，当设计参数远离谐振时，难以通过简单迭代获得较优的设计参数组合。

（3）数据驱动的桥梁-雨棚组合结构抗震设计参数优化研究。基于桥梁-雨棚组合结构的动力学分析，获得其在关键设计参数空间内的地震响应数据，建立“设计参数-地震响应”数据集，训练得到桥梁-雨棚组合结构地震响应预测模型。基于此预测模型数据，结合遗传算法对带雨棚连续刚构桥的抗震性能进行了单目标及多目标的参数优化。经验证，本文提出的设计参数智能优化算法，设计流程中不需要人工迭代，在设计参数远离谐振时也能获得最优的设计参数组合。

本文依托桥梁-雨棚组合结构实际案例，提出了一种面向性能目标的抗震设计参数优化策略。该优化策略可推广到其他类似结构的抗震优化，研究成果具有一定的科学意义和工程应用价值。

Bridge-canopy composite structures are widely utilized in municipal engineering. Composite structures undergo separate seismic designs, often neglecting the influence of the canopy on the overall seismic performance of the bridge. The conventional approach relies heavily on experience, necessitates repeated iterations to meet design goals, and fails to effectively leverage the canopy's potential in enhancing seismic resistance. To address these issues, this study investigates the integrated seismic design of bridge-canopy composite structures and proposes a machine learning-based optimization method to enhance their integrated seismic performance.

Taking a 3×30m continuous rigid-frame bridge with a canopy as the case, this work investigated the impact of key design parameters on the seismic performance of the bridge-canopy composite structure., the design parameters were optimized by using machine learning methods with the dataset obtained from the designed dynamic analyses. The main contents are as follows:

(1) Study on the applicability and limitations of the resonance tuning theory in bridge-canopy composite structures. The bridge-canopy composite structure is simplified to a two-degree-of-freedom model. Dynamic analysis under seismic action reveals that key design parameters such as pier stiffness, main girder mass, canopy lateral stiffness, and canopy mass, collectively determine the displacement response of the bridge-canopy composite structure. According to the tuned mass damper principle, when the natural frequency of the canopy approaches that of the bridge, the seismic response of the bridge decreases, while the seismic response of the canopy increases.

(2) Analysis of key parameters for performance-based seismic design of bridge-canopy composite structures. The integrated seismic design method simultaneously considers the seismic responses of both the bridge and the canopy. A well-coordinated combination of design parameters can enhance the seismic performance of the bridge-canopy composite structure. When these parameters approach resonance, the integrated seismic design method can achieve an optimal combination through simple iterations, thereby effectively enhancing the overall seismic performance. However, when the parameters are far from resonance, finding an optimal combination through simple iterations alone becomes challenging.

(3) Data-driven optimization of seismic design parameters for bridge-canopy composite structures. Dynamic analysis is performed to collect seismic response data within the key design parameter space, establishing a 'design parameter-seismic response' dataset. This dataset is utilized to train a seismic response prediction model for the bridge-canopy composite structure. Using this prediction model alongside a genetic algorithm, both single-objective and multi-objective optimization of the seismic performance of the continuous rigid-frame bridge with a canopy are conducted. Verification demonstrates that the proposed intelligent optimization algorithm for design parameters eliminates the need for manual iteration and can achieve the optimal combination of design parameters, even when they are far from resonance.

Based on the real-world case of a bridge-canopy composite structure, this work proposed a performance-oriented optimization strategy for seismic design parameters. This optimization strategy can be extended to the seismic optimization of other similar structures, shedding light on the future engineering applications.

[1] 许立言, 聂鑫, 庄亮东, 等. 基于混合消能减震技术的组合结构独柱高架站台抗震性能研究[J]. 建筑结构学报, 2019, 40(5): 50-62.

[2] 许暮迪, 韦妙鸳, 叶建能, 等. “桥建合一”型地铁高架车站振动舒适度研究[J]. 铁道科学与工程学报, 2022, 19(1): 230-238.

[3] 谢杨. 桥梁与建筑组合结构体系抗震性能分析[D]. 成都: 西南交通大学, 2014.

[4] 邹国泽. 桥建合一式高架车站结构抗震性能分析[D]. 天津: 天津大学, 2019.

[5] 王警. 天津Z2线工程桥建合一高架车站结构抗震性能分析[D]. 天津: 天津大学, 2022.

[6] 王彬. 天津地铁Z2线桥建合一式高架车站结构抗震性能试验研究[D]. 天津: 天津大学, 2023.

[7] 刘亚南. 地铁“建桥合一”车站结构抗震性能分析[J]. 城市轨道交通研究, 2019, 22(6): 107-110.

[8] 高增杰. 基于性能的建桥合一结构抗震性能研究[D]. 西安: 长安大学, 2021.

[9] Zhao Y, Zhang Y, Xu J, et al. Shaking table test on seismic performance of integrated station-bridge high-speed railway station[J]. Structures, 2022, 46: 1981-1993.

[10] Biondi B, Muscolino G, Sofi A. A substructure approach for the dynamic analysis of train–track–bridge system[J]. Computers & Structures, 2005, 83(28-30): 2271-2281.

[11] Guo X, Wang S. Research on the Dynamic Response of the Multi-Line Elevated Station with “Integral Station-Bridge System”[J]. Buildings, 2024, 14(3): 758.

[12] Reaveley L D, Rojahn C. Performance Based Seismic Design[J]. Bulletin of the New Zealand Society for Earthquake Engineering, 2000, 33(3): 2483-2493(11).

[13] Hamburger R, Rojahn C, Moehle J, et al. The ATC-58 Project: Development of Next-Generation Performance-Based Earthquake Engineering Design Criteria for Buildings[C]//World Conference on Earthquake Engineering. 2004.

[14] Lehman D, Moehle J, Mahin S. Experimental Evaluation of the Seismic Performance of Reinforced Concrete Bridge Columns[J]. Journal of Structural Engineering, 2004, 130(6): 869-879.

[15] 李建中, 管仲国. 桥梁抗震设计理论发展:从结构抗震减震到震后可恢复设计[J]. 中国公路学报, 2017, 30(12): 1-9+59.

[16] 殷静. 铁路建桥合一站房结构概念设计问题探讨[J]. 铁道建筑, 2019, 59(6): 43-46.

[17] 徐略勤, 王龙, 李建中, 等. 在役桥梁挡块基于保险丝理念的改造方法[J]. 西南交通大学学报, 2020, 55(1): 118-125+143.

[18] 金福海, 蔡德强. 新广州站桥建合建结构设计探讨[J]. 铁道工程学报, 2010, 27(2): 102-108.

[19] 杨开屏. 高架车站设计中的三种抗震规范参数比较[J]. 城市轨道交通研究, 2016, 19(12): 39-43.

[20] 吴文朋, 叶鑫, 周权, 等. 直缝型后张预应力装配式UHPC挡块抗震性能研究[J]. 中国公路学报, 2023, 36(2): 129-140.

[21] 韩强, 贾振雷, 何维利, 等. 自复位双柱式摇摆桥梁抗震设计方法及工程应用[J]. 中国公路学报, 2017, 30(12): 169-177.

[22] 董慧慧, 胡潇, 韩强, 等. 新型自复位变摩擦耗能支撑及其在桥墩抗震中的应用[J]. 中国公路学报, 2024, 37(1): 66-80.

[23] 石岩, 王东升, 韩建平. 设置BRB桥梁排架墩基于位移抗震设计方法[J]. 土木工程学报, 2017, 50(7): 62-68+128.

[24] 秦洪果, 李萍, 石岩, 等. 基于耗能保险丝的桥梁双柱墩减震控制研究[J]. 振动与冲击, 2022, 41(14): 190-198+263.

[25] 叶爱君, 方家欣, 张少为, 等. 小箱梁桥横向减震体系及其耗能特性[J]. 中国公路学报, 2017, 30(12): 21-29.

[26] 乔石. 利用主梁质量和支座性能的连续梁桥调谐减震设计方法[D]. 成都: 西南交通大学, 2018.

[27] 曾永平, 陈克坚, 庞林, 等. 近断层高速铁路典型桥梁抗震优化设计研究[J]. 铁道工程学报, 2020, 37(8): 51-58.

[28] Zhang Y, Yu P, Sun B, et al. Shaking Table Test on Composite Isolation System of High-speed Railway Station with Integrated Station-Bridge Structure[J]. KSCE Journal of Civil Engineering, 2024, 28(2): 787-799.

[29] Xie Y, Zhang J. Design and Optimization of Seismic Isolation and Damping Devices for Highway Bridges Based on Probabilistic Repair Cost Ratio[J]. Journal of Structural Engineering, 2018, 144(8): 04018125.

[30] Liu Q, Guo Z, Wu X, et al. Energy Dissipation Enhanced by Multiple Hinges in Bridge Piers with CFST Y-Shaped Fuses[J]. Symmetry, 2022, 14(11): 2371.

[31] Liu Q, Zhu S, Yu W, et al. Ground Motion Frequency Insensitivity of Bearing-Supported Pedestrian Bridge with Viscous Dampers[J]. KSCE Journal of Civil Engineering, 2021, 25(7): 2662-2673.

[32] Liu Q, Guo Z, Zhu S, et al. Performance-Based Seismic Design of Hybrid Isolation Systems with Gap-Tunable BRBs for Bearing-Supported Bridges[J]. Symmetry, 2022, 14(7): 1373.

[33] Mander J B, Cheng C T. Seismic resistance of bridge piers based on damage avoidance design[J]. Technical Report NCEER, 1997, 97-0014.

[34] 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.

[35] 《中国公路学报》编辑部. 中国桥梁工程学术研究综述·2021[J]. 中国公路学报, 2021, 34(2): 1-97.

[36] 郑玉国, 袁万城. 基于GA-RS的规则钢筋混凝土桥梁圆形单柱桥墩延性抗震优化设计[J]. 振动与冲击, 2010, 29(3): 81-84+205-206.

[37] 戴伦, 张文达, 田石柱. 桥梁线弹性地震反应的卷积神经网络估计[J]. 地震工程与工程振动, 2021, 41(4): 188-195.

[38] 李宇婧, 李宏男, 李超. 基于偏好序的桥梁结构全寿命抗震设计多目标优化模型[J]. 中国公路学报, 2017, 30(12): 187-195.

[39] 李智. 梁拱组合刚构桥地震响应下设计参数优化研究[D]. 重庆: 重庆交通大学, 2022.

[40] 胡科坚. 基于深度学习的梁桥非线性随机地震分析方法研究[D]. 西安: 长安大学, 2023.

[41] 高经纬, 张春涛. 基于长短时记忆网络的结构地震响应预测[J]. 工程抗震与加固改造, 2020, 42(3): 130-136.

[42] 赵钊, 郭恩栋, 王再荣, 等. 基于人工神经网络的城市桥梁震害评估方法[J]. 世界地震工程, 2011, 27(4): 7-12.

[43] 肖行辉, 高惠瑛, 孙海, 等. 基于最小二乘支持向量机的城市桥梁震害预测模型研究[J]. 震灾防御技术, 2016, 11(1): 93-99.

[44] 柳春光, 张利华. 遗传优化神经网络方法在桥梁震害预测中的应用[J]. 地震工程与工程振动, 2008(1): 139-145.

[45] 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.

[46] 何浩祥, 王文涛, 吴山. 基于均匀变形和混合智能算法的框架结构抗震优化设计[J]. 振动与冲击, 2020, 39(4): 113-121.

[47] 刘振亮. 基于数据驱动方法的公路桥梁及网络抗震性能评估[D]. 哈尔滨: 哈尔滨工业大学, 2022.

[48] 马东辉, 罗立, 王威, 等. 基于DRSA和CART的桥梁震损状态决策关联规则提取[J]. 北京工业大学学报, 2023, 49(11): 1167-1179.

[49] Chen X, Spencer B F, Li J, et al. Optimization of distribution patterns of link beams in a double‐column tall pier bent subjected to earthquake excitations[J]. Earthquake Engineering & Structural Dynamics, 2023, 52(3): 641-659.

[50] Guo W, He Y, Zhu Y, et al. Performance parameter design of seismic isolation bearings for high-speed railway simply-supported bridges using neural network[J]. Soil Dynamics and Earthquake Engineering, 2024, 179: 108535.

[51] Zhong J, Zheng X, Zhu Y, et al. Resilience-based seismic design optimization of novel link beam in a double-column bridge bent using Gaussian process regression[J]. Bulletin of Earthquake Engineering, 2023, 21(13): 6121-6142.

[52] Zhang H Y, Yang Y. Optimization of Mechanical Performance of Seismic Isolation Bearings for Continuous Beam Bridges[J]. Journal of Vibration Engineering & Technologies, 2023.

[53] Xu J, Feng D, Mangalathu S, et al. Data‐driven rapid damage evaluation for life‐cycle seismic assessment of regional reinforced concrete bridges[J]. Earthquake Engineering & Structural Dynamics, 2022, 51(11): 2730-2751.

[54] Zhou W, Xiong L, Jiang L, et al. Optimal combinations of parameters for seismic response prediction of high-speed railway bridges using machine learnings[J]. Structures, 2023, 57: 105089.

[55] Zhang P, Zhao H, Shao Z, et al. A rapid analysis framework for seismic response prediction and running safety assessment of train-bridge coupled systems[J]. Soil Dynamics and Earthquake Engineering, 2024, 177: 108386.

[56] Bakhshinezhad S, Mohebbi M. Multi-objective optimal design of semi-active fluid viscous dampers for nonlinear structures using NSGA-II[J]. Structures, 2020, 24: 678-689.

[57] Mangalathu S, Karthikeyan K, Feng D C, et al. Machine-learning interpretability techniques for seismic performance assessment of infrastructure systems[J]. Engineering Structures, 2022, 250: 112883.

[58] Wang M, Zhang H, Dai H, et al. A deep learning-aided seismic fragility analysis method for bridges[J]. Structures, 2022, 40: 1056-1064.

[59] Li W, Huang Y, Xie Z. Machine Learning-Based Probabilistic Seismic Demand Model of Continuous Girder Bridges[J]. Advances in Civil Engineering, 2022, 2022: 1-10.

[60] 胡海岩. 机械振动基础[M]. 北京: 机械振动基础, 2005.

[61] 陈政清, 华旭刚. 人行桥的振动与动力设计[M]. 北京: 人民交通出版社, 2009.

[62] Augusti G. Dynamics of structures: Theory and applications to earthquake engineering[J]. Meccanica, 1996, 31(6): 719-720.

[63] Constantinou M C, Soong T T, Dargush G F. Passive Energy Dissipation Systems for Structural Design and Retrofit[M]. New York: Multidisciplinary Center for Earthquake Engineering Research A National Center of Excellence in Advanced Technology Applications, 1998.

[64] Warburton G B, Ayorinde E O. Optimum absorber parameters for simple systems[J]. Earthquake Engineering & Structural Dynamics, 1980, 8(3): 197-217.

[65] 周锡元, 李中锡. 规则型隔震桥梁结构的简化分析方法[J]. 土木工程学报, 2001(3): 53-58+66.

[66] 孙颖, 王忠欲, 卓卫东. 多跨简支规则直线梁桥横桥向地震反应合理简化计算模型研究[J]. 防灾减灾工程学报, 2013, 33(S1): 38-43.

[67] 中华人民共和国交通运输部. 公路桥梁抗震设计规范. JTG/T 2231-01—2020. 北京: 中华人民共和国交通运输部, 2020.

[68] Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016.

[69] Deb K, Pratap A, Agarwal S, et al. A fast and elitist multiobjective genetic algorithm: NSGA-II[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182-197.

[70] FEMA. Applied Technology Council and Federal Emergency Management Agency[R]. Washington, D.C.: Applied Technology Council Federal Emergency Management Agency, 2009.

[71] Al Atik L, Abrahamson N. An Improved Method for Nonstationary Spectral Matching[J]. Earthquake Spectra, 2010, 26(3): 601-617.