Prediction model and optimization algorithm application of support void degree for highway beam bridges

PDF(3335 KB)

Journal of Vibration and Shock ›› 2024, Vol. 43 ›› Issue (15) : 218-227.

MA Shiji1,2, QIAO Lan1,2, DENG Naifu1,2, LI Qingwen1,2, CHEN Lu3

Author information +

History +

Abstract

Bridge bearing disengagement is a common structural defect in bridge structures that has a significant impact on the safety and service life of bridges. Therefore, accurately obtaining the disengagement information of the bearing becomes an important research topic. This study proposes a two-stage method for bearing disengagement detection. In the first stage, the bearing position is determined based on the Flexibility Matrix Diagonal Matrix Change Rate indicator (FDMCR). In the second stage, a BP neural network is used to predict the bearing disengagement degree. The study focuses on single span simply supported and triple span continuous beam bridges and uses finite element simulation to obtain the theoretical mode shapes and natural frequencies of the bridges. Modal testing is conducted on an indoor single-span beam bridge using a laser Doppler vibrometer system to obtain experimental data and validate the proposed method's feasibility. Therefore, for single-span beam bridges, the single-objective PSO/SFLA/ABC optimization algorithm and the multi-objective and non-dominant sorting genetic algorithm (NSGA-II) are applied to optimize the BP model and analysis. The research results show that the two-stage method can effectively achieve disengaged bearing position determination and degree prediction. The optimization algorithm can improve the prediction performance of the models, especially the ABC algorithm, which exhibits lower prediction errors in the clearance prediction model for single-span beam bridges. Additionally, constructing a multi-objective function based on the bearing position attributes can alleviate the issue of uneven prediction performance among the bearings in a single-objective scenario. This study is of great practical significance for predicting highway beam bridge bearing disengagement and provides new ideas and methods for similar problems.

Key words

bridge bearing / bearing disengagement degree prediction / flexibility matrix / BP neural network / optimization algorithm

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

MA Shiji1,2, QIAO Lan1,2, DENG Naifu1,2, LI Qingwen1,2, CHEN Lu3. Prediction model and optimization algorithm application of support void degree for highway beam bridges[J]. Journal of Vibration and Shock, 2024, 43(15): 218-227

References

[1] 金玉泉. 桥梁的病害及灾害[D]. 上海：同济大学，2006. Jin Yuquan. Bridge diseases and failures[D]. Shanghai: Tongji University, 2006. [2] Ma Hongwei, Nie Zhenhua. Recent advances and review of bridge safety monitoring[J]. Mechanics in Engineering, 2015, 37(2): 161-170+181. [3] 王凌波, 王秋玲, 朱钊, 赵煜. 桥梁健康监测技术研究现状及展望[J]. 中国公路学报，2021，34(12)：25-45. Wang Lingbo, Wang Qiuling, Zhu Zhao, Zhao Yu. Current status and prospects of research on bridge health monitoring technology[J]. China Journal of Highway and Transportation, 2021, 34(12): 25-45. [4] 马万飞. 桥梁支座病害成因及防治[J]. 西部交通科技，2017(12)：56-58. Ma Wanfei. Causes and Prevention of Bridge Bearing Disease[J]. Western China Communications Science & Technology, 2017(12): 56-58. [5] 邱文, 邹开泰. 高速公路桥梁支座病害分析及修复[J]. 公路，2021，66(02)：129-132. Qiu Wen, Zou Kaitai. Analysis and Repair of Expressway Bridge Support Defects[J]. Highway, 2021, 66(02): 129-132. [6] 周伟, 唐茗, 童浩. 支座观测仪的开发与应用[J]. 科技创新导报，2012(10)：27-28. Zhou Wei, Tang Ming, Tong Hao. Development and Application of Support Observation Instrument[J]. Science and Technology Innovation Herald, 2012(10): 27-28. [7] Seo J, Duque L, Wacker J. Drone-enabled bridge inspection methodology and application[J]. Automation in construction, 2018, 94: 112-126. [8] Lee J H, Yoon S, Kim B, et al. A new image-quality evaluating and enhancing methodology for bridge inspection using an unmanned aerial vehicle[J]. Smart Structures and Systems, 2021, 27(2): 209-226. [9] 崔弥达. 基于图像处理的桥梁支座病害自动识别关键技术研究[D]. 南京：东南大学，2018. Cui Mida. Research on key techniques of automatic defect identification for bridge bearings based on image processing[D]. Nanjing: Southeast University, 2018. [10] 周正茂, 韩光强, 田清勇. 基于位移的桥梁支座脱空测试方法[J]. 公路交通科技，2012，29(04)：85-90. Zhou Zhengmao, Han Guangqiang, Tian Qingyong. Separation test method for bridge bearing based on displacement[J]. Journal of Highway and Transportation Research and Development, 2012, 29(04): 85-90. [11] 梁栋, 张聪正, 刘菁, 陈磊, 陈红霞. 基于高斯曲率模态相关系数的梁桥支座损伤识别研究[J]. 地震工程与工程振动，2020，40(02)：23-32. Liang Dong, Zhang Congzheng, Liu Jing, Chen Lei, Chen Hongxia. Research on damage identification of beam-bridge bearing based on gaussian curvature modal correlation coefficient[J]. EARTHQUAKE ENGINEERING AND ENGINEERING DYNAMICS, 2020, 40(02): 23-32. [12] 战家旺, 夏禾, 张楠, 卢洋. 一种基于冲击振动响应分析的桥梁橡胶支座病害诊断方法[J]. 振动与冲击，2013，32(08)：153-157+182. Zhan Jiawang, Xia He, Zhang Nan, Lu Yang. A diagnosis method for bridge rubber support disease based on impact responses[J]. Journal of Vibration and Shock, 2013, 32(08): 153-157+182. [13] 闫宇智, 战家旺, 张楠, 邵斌. 基于车激响应的桥梁支座脱空病害识别方法研究[J]. 桥梁建设，2020，50(02)：19-24. Yan Yuzhi, Zhan JiaWang, Zhang Nan, Shao Bin. Study of methods to identify bridge bearing displacement based on vehicle-excited responses[J]. Bridge Construction, 2020, 50(02): 19-24. [14] 包龙生, 曹悦, 赵宁, 孟宪彪, 张筱薇. BP神经网络和曲率模态理论在桥梁损伤识别中的应用[J]. 沈阳建筑大学学报(自然科学版)，2021，37(02)：296-302. Bao Longsheng, Cao Yue, Zhao Ning, Meng Xianbiao, Zhang Xiaowei. Application of BP neural network and curvature mode theory in bridge damage identification[J]. Journal of Shenyang Jianzhu University (Natural Science), 2021, 37(02): 296-302. [15] Tan Z X, Thambiratnam D P, Chan T H T, et al. Damage detection in steel-concrete composite bridge using vibration characteristics and artificial neural network[J]. Structure and Infrastructure Engineering，2020，16(9)：1247-1261. [16] Nick H, Aziminejad A, Hosseini M H, et al. Damage identification in steel girder bridges using modal strain energy-based damage index method and artificial neural network[J]. Engineering Failure Analysis, 2021, 119: 105010. [17] 王国平. 动手学PyTorch深度学习建模与应用[M]. 北京：清华大学出版社，2022. Wang Guoping. Hands-on learning PyTorch deep learning modeling and application[M]. Beijing: Tsinghua University Press, 2022. [18] 邱锡鹏. 神经网络与深度学习[M]. 北京：机械工业出版社，2020. Qiu Xipeng. Neural networks and deep learning[M]. Beijing: China Machine Press, 2020. [19] Ewins D J. Modal testing: theory, practice and application[M]. New York: John Wiley & Sons, 2009. [20] 王树青, 田晓洁. 结构振动测试与模态识别[M]. 青岛：中国海洋大学出版社，2021.04. Wang Shuqing, Tian Xiaojie. Structural vibration testing and modal identification[M]. Qingdao: China Ocean University Press, 2021.04. [21] 茹宁, 张力. 非接触式测振技术最新进展及应用——2016非接触式激光测振国际会议评述[J]. 计测技术，2016，36(06)：1-3+61. Ru Ning, Zhang Li. The latest development and application of non-contact measurement technology--Review of the 2016 international conference of non-contact laser vibration measurement[J]. Metrology & Measurement Technology, 2016, 36(06): 1-3+61. [22] 宋安平. 连续扫描激光多普勒测振技术及模态分析方法研究[D]. 南京：南京航空航天大学，2017. Song Anping. Study of continuously scanning laser Doppler vibrometer test and modal analysis technique[D]. Nanjing: Nanjing University, 2017. [23] 冯苠, 刘晓娣, 李文杰. JT/T4-2019公路桥梁板式橡胶支座[S]. 北京：中华人民共和国交通运输部，2019.09.01. Feng Min, Liu Xiaodi, Li Wenjie. JT/T4-2019 Laminated bearing for highway bridge[S]. Beijing: Ministry of Transport of the People's Republic of China, 2019.09.01. [24] 易晓罡. 基于柔度矩阵的桥梁损伤识别法的应用[J]. 中国水运(理论版)，2007(03)：44-45. Yi Xiaogang. Application of the method of damage detection on the bridge based on flexibility matrix[J]. China Water Transport, 2007(03): 44-45. [25] 尚鑫. 基于动力测试的桥梁损伤识别研究[D]. 西安：长安大学，2014. Shang Xin. Study on bridge damage identification based on dynamic detection[D]. Xian: Chang’an University, 2014. [26] 张利伟. 在役钢筋混凝土桥梁损伤辨识及寿命预测研究[D]. 河南：河南大学，2011. Zhang Liwei. Damage identification for existing reinforced concrete bridge and research on prediction of life[D]. Henan: Henan University, 2011. [27] 荆磊, 闫长旺, 刘曙光, 张菊, 段连钧. BP神经网络预测氯盐渍土环境中混凝土结构使用寿命[J]. 混凝土，2016(10)：8-10+15. Jing Lei, Yan Changwang, Liu Shuguang, Zhang Ju, Duan LianJun. BP neural netw ork to predict service life of concrete structures in the chlorine saline soil environment[J]. Concrete, 2016(10): 8-10+15. [28] 刘喜波. 概率论与数理统计[M]. 北京：北京邮电大学出版社, 2020.04. Liu Xibo. Probability and mathematical statistics[M]. Beijing: Beijing university of posts and telecommunications press, 2020.04. [29] Kaveh A,Maniat M. Damage detection based on MCSS and PSO using modal data[J]. Smart Structures and Systems, 2015, 15(5). [30] 李益兵, 马建波, 江丽. 基于SFLA改进卷积神经网络的滚动轴承故障诊断[J]. 振动与冲击，2020，39(24)：187-193. LI Yibing, Ma Jianbo, Jiang Li. Fault diagnosis of rolling bearing based on an improved convolutional neural network using SFLA[J]. Journal of Vibration and Shock, 2020, 39(24): 187-193. [31] Vahidi M, Vahdani S, Rahimian M, et al. Evolutionary-base finite element model updating and damage detectionusing modal testing results[J]. Structural Engineering and Mechanics, 2019, 70(3). [32] 鲁四平, 张会峰, 黄方林. 基于单元模态应变能与区间分析的不确定性损伤识别[J]. 铁道科学与工程学报，2021，18(10)：2715-2721. Lu Siping, Zhang Huifeng, Huang Fanglin. Damage detection considering uncertaining based on interval analysis and element modal strain energy[J]. Journal of Railway Science and Engineering, 2021, 18(10): 2715-2721. [33] 娄高中, 谭毅. 基于PSO-BP神经网络的导水裂隙带高度预测[J]. 煤田地质与勘探，2021，49(04)：198-204. Lou Gaozhong, Tan Yi. Prediction of the height of water flowing fractured zone based on PSO-BP neural network[J]. Coal Geology & Exploration, 2021, 49 (04): 198-204. [34] Wang Y. Determination of bridge prestress loss under fatigue load based on PSO-BP neural network[J]. Computational Intelligence and Neuroscience, 2021, 2021. [35] 范勇, 裴勇, 杨广栋, 冷振东, 卢文波. 基于改进PSO-BP神经网络的爆破振动速度峰值预测[J]. 振动与冲击，2022，41(16)：194-203+302. Fan Yong, Pei Yong, Yang Guangdong, Leng Zhendong; Lu Wenbo. Prediction of blasting vibration velocity peak based on an improved PSO-BP neural network[J]. Journal of Vibration and Shock, 2022, 41 (16): 194-203+302. [36] 杨洁, 褚书培. 改进SFLA-BP神经网络在遮盖干扰信号识别应用[J]. 传感器与微系统，2020，39(08)：155-157+160. Yang Jie, Chu Shupei. Application of modified SFLA-BP neural network in covering jamming signals identification[J]. Transducer and Microsystem Technologies, 2020, 39 (08): 155-157+160. [37] Ding Z H, Huang M, Lu Z R. Structural damage detection using artificial bee colony algorithm with hybrid search strategy[J]. Swarm and Evolutionary Computation, 2016, 28: 1-13. [38] 黄富程, 刘德新, 曹杰, 安天圣. 基于ABC优化BP神经网络的船舶交通流量预测[J]. 中国航海，2021，44(02)：78-83. Huang Fucheng, Liu Dexin, Cao Jie, An Tiansheng. Integration of BP Neuro Network with Artificial Bee Colony algorithm for Traffic Flow Prediction[J]. Navigation of China, 2021, 44 (02): 78-83. [39] 臧子婧, 吴海波, 张平松, 董守华. 基于ABC-BP模型的煤层含气量预测[J]. 煤田地质与勘探，2021，49(02)：152-158. Zang Zijing, Wu Haibo, Zhang Pingsong, Dong Shouhua. Prediction of coal seam gas content based on ABC-BP model[J]. Coal Geology & Exploration, 2021, 49 (02): 152-158 [40] 徐文韬, 黄亚继, 曹歌瀚, 陈波, 金保昇. 基于BP-改进NSGA-Ⅱ锅炉燃烧多目标优化[J]. 东南大学学报(自然科学版)，2022，52(05)：943-952. Xu Wentao, Huang Yaji, Cao Gehan, Chen Bo, Jin Baosheng. Multi-objective combustion optimization for boiler based on BP-improved NSGA-II[J]. Journal of Southeast University (Natural Science Edition), 2022, 52 (05): 943-952.