Static system reliability analysis of cable-stayed bridge based on improved BP neural network
-
摘要: 为提高斜拉桥静力体系可靠度计算效率，基于改进的反向传播(BP)神经网络构建了体系可靠度计算模型，引入了遗传算法(GA)优化BP神经网络，实现斜拉桥关键构件功能函数的高效重构和验算点的快速捕捉，建立了构件可靠指标的GA-BP-GA-Monte Carlo(GBGMC)算法；应用修正的β约界法识别失效历程中的候选失效单元，采用GBGMC计算随结构拓扑模型改变而更新变化的构件可靠指标，搜寻结构主要失效模式，建立了结构失效树；在确定各失效模式等效线性功能函数和相关系数的基础上，利用微分等价递归算法实现了结构体系可靠度计算；通过3个数值算例的可靠度分析，验证了GBGMC的正确性和有效性；以主跨448 m的斜拉桥为例，采用提出的体系可靠度计算模型分析了失效历程各阶段斜拉桥关键构件可靠指标的演化规律，创建了斜拉桥结构体系失效树，实现了结构体系可靠指标的高效计算和控制体系安全性的重要构件识别。研究结果表明: GBGMC的计算误差在0.3%以内, 优于其他传统方法; 正常使用极限状态下, 斜拉桥主跨跨中挠度可靠指标最小, 为2.7, 承载能力极限状态下, 主跨跨中斜拉索、索塔处主梁和索塔拉索锚固区下部可靠指标相对较小，分别为3.1、3.6和3.9, 为失效历程第一阶段候选单元，失效风险大; 搜寻19个获得承载能力极限状态的主要失效模式, 计算该斜拉桥体系可靠指标为3.8, 可为斜拉桥设计优化和维养决策体系安全性管控提供量化分析依据。Abstract: In order to enhance the efficiency of static system reliability calculation for cable-stayed bridges, a system reliability analysis model was developed based on an improved back propagation (BP) neural network. By introducing the genetic algorithm (GA) into the BP neural network, the limit state functions of key cable-stayed bridge components could be efficiently reconstructed, the design points could be captured rapidly, and the algorithm of GA-BP-GA-Monte Carlo (GBGMC) for component reliability index calculation was established. The rectified β-unzipping method was used to select candidate failure components, and the structure was modified by assuming in turn failure in the potential failure elements. The primary failure modes of the cable-stayed bridge were identified, upon which the fault tree was subsequently constructed. Based on the equivalent linear functions of the failure modes and correlation coefficients, the differential equivalent recursion algorithm was employed to calculate the reliability of the structural system. The effectiveness and accuracy of GBGMC were verified through a reliability study of three numerical examples. The proposed system reliability analysis method was used to evaluate the structural failure history of a cable-stayed bridge with a main span of 448 m. The component reliability indexes in each failure stage were calculated, and the structural system failure tree of the cable-stayed bridge was created. The structural system reliability index was efficiently calculated, and important components controlling the system safety were identified. Research results show that the computational error of GBGMC is within 0.3%, which is better than other traditional methods.The deflection reliability index at the main span center of the cable-stayed bridge is the lowest for the normal utilization limit state, which is 2.7. In terms of the ultimate limit state, the reliability indexes of the cables in the center of the main span, the main girder at the tower, and the lower section of the tower's cable anchorage area all pose a high risk of failure. Their respective reliability indexes are 3.1, 3.6, and 3.9, respectively. Nineteen main failure modes for the cable-stayed bridge at ultimate limit state are obtained, and the system reliability index is 3.8. Research results provide a theoretical basis of system safety control for the design optimization and maintenance decision of cable-stayed bridges.
-
Key words:
- bridge engineering /
- cable-stayed bridge /
- system reliability /
- BP neural network /
- genetic algorithm /
- failure mode
-
图 4 期望输出和BP神经网络预测输出曲线
Figure 4. Curves of desired output and BP neural network predicted output
图 18 失效第一阶段主梁位移可靠指标
Figure 18. Reliability indexes of girder displacement in first failure stage
表 1 算例1计算结果对比
Table 1. Comparison of calculation results in example 1
方法 验算点 可靠指标 失效概率 FORM (1 118.546 5, 165.464 7) 2.331 9.88×10-3 RSM (1 125.711 5, 165.816 4) 2.331 9.87×10-3 MCS 2.336 9.74×10-3 BP神经网络 2.361 9.12×10-3 GBGMC (1 125.257 0, 165.986 3) 2.334 9.82×10-3 
下载: 导出CSV
表 2 算例2计算结果对比
Table 2. Comparison of calculation results in example 2
方法 验算点 可靠指标 失效概率 FORM (-2.539 7, 0.945 3) 2.710 3.40×10－3 RSM (-2.458 6, 1.159 5) 2.718 3.30×10－3 MCS 2.688 3.60×10－3 BP神经网络 2.702 3.40×10－3 GBGMC (-2.627 0, 0.827 6) 2.688 3.60×10－3
下载: 导出CSV
表 3 算例3计算结果对比
Table 3. Comparison of calculation results in example 3
可靠度计算方法 可靠指标 失效概率 MCS 2.835 2.30×10－3 BP神经网络(隐节点20个，抽样10万次) 2.819 2.40×10－3 GBGMC(隐节点10个，抽样1万次) 2.831 2.30×10－3
下载: 导出CSV
表 4 迭代索力与设计索力对比
Table 4. Comparison of iterated and designed cable force
编号 设计索力/kN 计算索力/kN 误差率/ % 编号 计算索力/kN 误差率/ % C1 25.03 24.79 0.99 C15 24.47 0.85 C2 21.12 70.78 1.67 C16 20.74 1.30 C3 23.64 23.26 1.64 C17 22.59 1.16 C4 28.05 27.62 1.54 C18 25.78 0.95 C5 29.74 29.40 1.14 C19 26.69 0.53 C6 31.37 31.15 0.69 C20 29.35 0.12 C7 33.96 33.87 0.26 C21 30.84 0.28 C8 35.29 35.34 0.13 C22 34.47 0.58 C9 38.79 38.98 0.49 C23 38.04 0.75 C10 39.79 40.08 0.74 C24 41.42 0.95 C11 40.36 40.77 0.91 C25 39.65 1.01 C12 40.89 41.30 1.00 C26 42.69 0.95 C13 41.47 41.90 1.02 C27 45.49 0.87 C14 42.05 42.47 0.99 C28 46.59 0.79
下载: 导出CSV
表 5 随机变量统计
Table 5. Statistical random variables
随机变量名称 变量分类 变量分布类型 均值 标准差 弹性模量/GPa 主梁 正态 200 20.0 索塔 正态 36 3.6 斜拉索 正态 205 20.5 截面面积/m2 主梁 对数正态 1.76 0.18 索塔下部 对数正态 27.50 1.37 索塔中部 对数正态 17.80 0.89 索塔上部 对数正态 63.90 3.20 109型斜拉索 对数正态 7.85×10－3 7.85×10－5 139型斜拉索 对数正态 9.50×10－3 9.50×10－5 151型斜拉索 对数正态 1.04×10－2 1.04×10－4 163型斜拉索 对数正态 1.13×10－2 1.13×10－4 187型斜拉索 对数正态 1.23×10－2 1.23×10－4 199型斜拉索 对数正态 1.54×10－2 1.54×10－4 惯性矩/m4 主梁 对数正态 3.83 0.19 索塔下部 对数正态 166.00 8.28 索塔中部 对数正态 60.90 3.04 索塔上部 对数正态 225.00 11.30 材料容重/(kg·m－3) 主梁 正态 7.70×103 770.00 索塔 正态 2.60×103 160.00 拉索 正态 7.85×103 785.00 荷载集度/(kN·m－1) 活载 正态 63.00 6.30
下载: 导出CSV
-
[1] BRUNEAU M. Evaluation of system-reliability methods for cable-stayed bridge design[J]. Journal of Structural Engineering, 1992, 118(4): 1106-1120. doi: 10.1061/(ASCE)0733-9445(1992)118:4(1106) [2] 陈铁冰, 王书庆, 石志源. 计入结构几何非线性影响时斜拉桥可靠度分析[J]. 同济大学学报(自然科学版), 2000, 28(4): 407-412.CHEN Tie-bing, WANG Shu-qing, SHI Zhi-yuan. Reliability analysis of cable-stayed bridges considering geometrical non-linearity[J]. Journal of Tongji University (Natural Science), 2000, 28(4): 407-412. (in Chinese) [3] 程进, 肖汝诚. 斜拉桥结构静力可靠度分析[J]. 同济大学学报(自然科学版), 2004, 32(12): 1593-1598.CHENG Jin, XIAO Ru-cheng. Static reliability analysis of cable-stayed bridges[J]. Journal of Tongji University (Natural Science), 2004, 32(12): 1593-1598. (in Chinese) [4] 王达, 唐浩. 基于响应面法的斜拉桥静力体系可靠度[J]. 交通科学与工程, 2014, 30(2): 34-39.WANG Da, TANG Hao. The static system reliability of cable-stayed bridges using the response surface method[J]. Journal of Transport Science and Engineering, 2014, 30(2): 34-39. (in Chinese) [5] 颜东煌, 郭鑫. 斜拉索损伤对在役斜拉桥体系可靠度的影响[J]. 中南大学学报(自然科学版), 2020, 51(1): 213-220.YAN Dong-huang, GUO Xin. Influence of damage of stay cables on system reliability of in-service cable-stayed bridges[J]. Journal of Central South University (Science and Technology), 2020, 51(1): 213-220. (in Chinese) [6] 刘健, 晏铖, 方其样, 等. 基于响应面法与JC法结合的大跨度桥梁可靠度分析[J]. 桥梁建设, 2022, 52(4): 32-38.LIU Jian, YAN Cheng, FANG Qi-yang, et al. Reliability analysis of long-span bridges based on combination of response surface method and JC method[J]. Bridge Construction, 2022, 52(4): 32-38. (in Chinese) [7] 刘扬, 鲁乃唯, 蒋友宝. 结构体系可靠度分析的改进支持向量回归[J]. 浙江大学学报(工学版), 2015, 49(9): 1692-1699.LIU Yang, LU Nai-wei, JIANG You-bao. Adaptive support vector regression method for structural system reliability analysis[J]. Journal of Zhejiang University(Engineering Science), 2015, 49(9): 1692-1699. (in Chinese) [8] LU Nai-wei, LIU Yang, BEER M. Reliability and Safety of Cable-Supported Bridges[M]. London: CRC Press, 2021. [9] 刘扬, 鲁乃唯, 殷新锋. 基于更新支持向量的大跨度斜拉桥体系可靠度分析[J]. 计算力学学报, 2015, 32(2): 154-159.LIU Yang, LU Nai-wei, YIN Xin-feng. System reliability assessment of long-span cable-stayed bridges using an updating support vector algorithm[J]. Chinese Journal of Computational Mechanics, 2015, 32(2): 154-159. (in Chinese) [10] 张建仁, 刘扬. 遗传算法和人工神经网络在斜拉桥可靠度分析中的应用[J]. 土木工程学报, 2001, 34(1): 7-13.ZHANG Jian-ren, LIU Yang. Reliability analysis of cable-stayed bridge using GAS and ANN[J]. China Civil Engineering Journal, 2001, 34(1): 7-13. (in Chinese) [11] LI Jian-hui, LI Ai-qun, MARIA Q. FENG, et al. Sensitivity and reliability analysis of a self-anchored suspension bridge[J]. Journal of Bridge Engineering, 2013, 18(8): 703-711. doi: 10.1061/(ASCE)BE.1943-5592.0000424 [12] CHENG Jin. An artificial neural network based genetic algorithm for estimating the reliability of long span suspension bridges[J]. Finite Elements in Analysis and Design, 2010, 46(8): 658-667. doi: 10.1016/j.finel.2010.03.005 [13] 粟洪. 大跨度悬索桥结构可靠度分析方法研究[D]. 上海: 同济大学, 2009.SU Hong. Study on structural reliability analysis method of long span suspension bridge[D]. Shanghai: Tongji University, 2009. (in Chinese) [14] SHAO S, MUROTSU Y. Approach to failure mode analysis of large structures[J]. Probabilistic Engineering Mechanics, 1999, 14(1/2): 169-177. [15] 罗晓瑜, 王春生, 姚书奎, 等. 基于双向渐进结构优化法的钢桥系统失效模式识别[J]. 中国公路学报, 2017, 30(3): 31-39.LUO Xiao-yu, WANG Chun-sheng, YAO Shu-kui, et al. Identification of system failure modes of steel bridges based on bi-directional evolutionary structual optimization[J]. China Journal of Highway and Transport, 2017, 30(3): 31-39. (in Chinese) [16] 王春生, 陈惟珍, 陈艾荣. 铆接钢桥的系统疲劳可靠度评估[J]. 中国公路学报, 2008, 21(5): 45-49.WANG Chun-sheng, CHEN Wei-zhen, CHEN Ai-rong. System fatigue reliability assessment of riveted steel bridges[J]. China Journal of Highway and Transport, 2008, 21(5): 45-49. (in Chinese) [17] 王春生, 聂建国, 陈艾荣, 等. 既有铁路钢桥的系统疲劳可靠度评估[J]. 清华大学学报(自然科学版), 2005, 45(9): 1157-1161.WANG Chun-sheng, NIE Jian-guo, CHEN Ai-rong, et al. Systems fatigue reliability assessment of existing steel railway bridges[J]. Journal of Tsinghua University (Science and Technology), 2005, 45(9): 1157-1161. (in Chinese) [18] 张小庆. 结构体系可靠度分析方法研究[D]. 大连: 大连理工大学, 2003.ZHANG Xiao-qing. Study on the analysis methods of structural system reliability[D]. Dalian: Dalian University of Technology, 2003. (in Chinese) [19] 张小庆, 康海贵, 王复明. 改进的微分等价递归算法[J]. 土木工程学报, 2004, 37(1): 31-38.ZHANG Xiao-qing, KANG Hai-gui, WANG Fu-ming. An improved differential equivalent recursion algorithm[J]. China Civil Engineering Journal, 2004, 37(1): 31-38. (in Chinese) [20] KIM S H, NA S W. Response surface method using vector projected sampling points[J]. Structural Safety, 1997, 19(1): 3-19. [21] HAGAN M T, DEMUTH H B, BEALE M H. Neural Network Design[M]. Boston: PWS Publishing Company, 1997. [22] LOPES P A M, GOMES H M, AWRUCH A M. Reliability analysis of laminated composite structures using finite elements and neural networks[J]. Composite Structures, 2010, 92(7): 1603-1613. [23] 巩春领. 大跨度斜拉桥施工风险分析与对策研究[D]. 上海: 同济大学, 2006.GONG Chun-ling. Construction risk analysis and countermeasures research of long span cable-stayed bridges[D]. Shanghai: Tongji University, 2006. (in Chinese) [24] 沈花玉, 王兆霞, 高成耀, 等. BP神经网络隐含层单元数的确定[J]. 天津理工大学学报, 2008, 24(5): 13-15.SHEN Hua-yu, WANG Zhao-xia, GAO Cheng-yao, et al. Determining the number of BP neural network hidden layer units[J]. Journal of Tianjin University of Technology, 2008, 24(5): 13-15. (in Chinese) [25] CHENG J. Optimum design of steel truss arch bridges using a hybrid genetic algorithm[J]. Journal of Constructional Steel Research, 2010, 66(8/9): 1011-1017. [26] THOFT-CHRISTENSEN P, MUROTSU Y. Application of Structural Systems Reliability Theory[M]. Berlin: Springer, 2012. [27] 董聪. 结构系统可靠性理论: 进展与回顾[J]. 工程力学, 2001, 18(4): 79-89, 59.DONG Cong. Reliability theory of structural systems: advance and review[J]. Engineering Mechanics, 2001, 18(4): 79-89, 59. (in Chinese) [28] 余建星. 工程结构可靠性原理及其优化设计[M]. 中国建筑工业出版社, 2013.YU Jian-xing. Engineering Structure Reliability Theory and Optimization Design[M]. Beijing: China Architecture and Building Press, 2013. (in Chinese) [29] ERNST H J. Der E-modul von seilen unter bercksichtigung des durchhanges[J]. Der Bauingenieur, 1965, 40(2): 52-55. [30] LIU Y, LU N, YIN X, et al. An adaptive support vector regression method for structural system reliability assessment and its application to a cable-stayed bridge[J]. Journal of Risk and Reliability, 2016, 230(2): 204-219. -
点击查看大图
图(25) / 表(5)
计量
- 文章访问数: 21
- HTML全文浏览量: 6
- PDF下载量: 2
- 被引次数: 0
