[1]吴刚,邱俊,祝谭雍,等.基于改进PSO-GMM算法的伸缩缝纵向位移监测数据分析方法[J].长安大学学报(自然科学版),2025,45(6):97-106.
　WU Gang,QIU Jun,ZHU Tan-yong,et al.Analysis method for longitudinal displacement monitoring data of expansion joints based on improved PSO-GMM algorithm[J].Journal of Chang’an University (Natural Science Edition),2025,45(6):97-106.
点击复制

基于改进PSO-GMM算法的伸缩缝纵向位移监测数据分析方法()
分享到：

长安大学学报（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
第45卷
期数:
2025年6期
页码:
97-106
栏目:
桥梁智能运维与防灾减灾
出版日期:
2025-11-30

文章信息/Info

Title:
Analysis method for longitudinal displacement monitoring data of expansion joints based on improved PSO-GMM algorithm
文章编号:
1671-8879(2025)06-0097-10
作者:
吴刚1; 2; 邱俊1; 祝谭雍3; 杜汶澎1; 刘旭政1; 2; 李燊4
(1. 华东交通大学 山区土木工程安全与韧性全国重点实验室,江西 南昌 330013; 2. 华东交通大学 土木建筑学院,江西 南昌 330013; 3. 江西省交通投资集团有限责任公司, 江西 南昌 330108; 4. 延安市公路局,陕西 延安 716000)
Author(s):
WU Gang1; 2;  QIU Jun1;  ZHU Tan-yong3;  DU Wen-peng1;  LIU Xu-zheng1; 2;  LI Shen4
(1. State Key Laboratory of Safety and Resilience of Civil Engineering in Mountain Area, East China Jiaotong University, Nanchang 330013, Jiangxi, China; 2. College of Civil Engineering and Construction, East China Jiaotong University, Nanchang 330013, Jiangxi, China; 3. Jiangxi Communications Investment Group Co., Ltd.,Nanchang 330108, Jiangxi, China; 4. Yanan Municipal Highway Bureau, Yanan 716000, Shaanxi, China)
关键词:
桥梁工程;  伸缩缝;  高斯混合模型;  粒子群优化;  概率密度函数
Keywords:
bridge engineering;  expansion joints;  Gaussian mixture model;  particle swarm optimization;  probability density function
分类号:
U443.31
文献标志码:
A
摘要:
为实现基于长期监测数据对桥梁伸缩缝服役状态的准确评估,提出一种基于改进粒子群优化-高斯混合模型(PSO-GMM)算法的伸缩缝纵向位移监测数据分析方法。该方法通过引入核密度估计窗口结构风险项对高斯混合模型目标函数改进设计,并以改进目标函数作为适应度函数,采用粒子群优化算法分析获得高斯混合模型最优参数,进而建立概率密度函数; 采用有噪点和无噪点的2类仿真数据集对改进PSO-GMM算法有效性进行验证; 以一座斜拉桥伸缩缝纵向位移监测数据为例,运用改进PSO-GMM算法分析伸缩缝纵向位移数据并建立其概率密度函数及服役状态评价方法。研究结果表明:基于改进PSO-GMM算法有效克服了传统高斯混合模型中期望最大化算法易陷入局部最优、对局部特征捕捉不足的问题,提升了监测数据拟合精度和鲁棒性; 相较于核密度估计方法,改进PSO-GMM算法分析仿真数据集时,在整体趋势和局部细节方面均能准确反映数据分布特征; 对于斜拉桥伸缩缝纵向位移监测数据的统计分析,改进PSO-GMM算法拟合概率密度函数精度高于核密度估计方法和期望最大化-高斯混合模型(EM-GMM)方法,基于其建立的伸缩缝服役状态评价方法可为管养决策提供理论依据。
Abstract:
To achieve accurate assessment of the service status of bridge expansion joints based on long-term monitoring data, a analysis method for the longitudinal displacement monitoring data of expansion joints was proposed based on an improved particle swarm optimization-Gaussian mixture model(PSO-GMM)algorithm. The objective function of the Gaussian mixture model(GMM)was improved through the introduction of a kernel density estimation(KDE)window structure risk term. The particle swarm optimization(PSO)algorithm was utilized to obtain the optimal parameters of the GMM under the condition that the improved objective function was adopted as the fitness function. Subsequently, a probability density function was established. The effectiveness of the improved PSO-GMM algorithm was verified using two types of simulated datasets with and without noise. Taking the longitudinal displacement monitoring data of an expansion joint in a cable-stayed bridge as an example, the improved PSO-GMM algorithm was applied to establish the probability density function of the expansion joint's longitudinal displacement, and a method for evaluating its service status was proposed. The research results show that the improved PSO-GMM algorithm effectively overcomes the problems of the expectation-maximization(EM)algorithm in the traditional GMM, such as being prone to local optima and insufficient in capturing local features, and enhances the fitting accuracy and robustness of monitoring data. Compared with the kernel density estimation(KDE)method, the improved PSO-GMM algorithm can accurately reflect the data distribution characteristics in terms of both overall trends and local details when analyzing simulated datasets. For the statistical analysis of longitudinal displacement monitoring data of expansion joints in cable-stayed bridges, the probability density function fitted by this method exhibits higher accuracy than those obtained by the KDE method and expectation maximization-Gaussian mixture model(EM-GMM)method. The evaluation method for the service status of expansion joints established herein provides a theoretical basis for maintenance decision-making.1 tab, 8 figs, 38 refs.

参考文献/References:

[1] JI W, SHAO T Y, LI J Q. Analytical investigation of fatigue behavior in a modified composite steel box concrete girder bridge with corrugated steel webs under pavement and expansion joint deterioration[J]. Journal of Bridge Engineering, 2024, 29(10):
04024078.
[2]WU Y X, XU W Y, YU T L, et al. Development and performance evaluation of a polyurethane elastomer based seamless expansion joint for bridges[J]. International Journal of Structural Integrity, 2024, 15(6): 1132-1152.
[3]HAN-MIN C H, LEE H W, KIM K S, et al. Investigating the application of smart materials for enhanced maintenance of rubber expansion joints in bridge expansion joint systems[J]. Applied Sciences, 2024, 14(7): 2828.
[4]韩大章,郭 彤,黄灵宇,等.随机车辆荷载下大跨钢桥伸缩缝纵向位移响应及病害控制研究[J].振动与冲击,2019,38(24):172-178.
HAN Da-zhang, GUO Tong, HUANG Ling-yu, et al. A study on longitudinal displacements and damage control of expansion joints of long-span steel bridges under stochastic traffic loads[J].Journal of Vibration and Shock, 2019, 38(24): 172-178.
[5]LI J S, WEN F, CHEN J, et al. Experimental study of bridge expansion joint damage based on natural frequency[J]. Sensors, 2023, 23(14): 6437.
[6]杨 奕,季云峰,王晓宇,等.基于监测数据的大位移伸缩缝性能评估[J].公路,2023,68(1):84-93.
YANG Yi, JI Yun-feng, WANG Xiao-yu, et al. Performance evaluation of large displacement expansion joints based on monitoring data[J]. Highway, 2023, 68(1): 84 - 89.
[7]黄海宾,冯江苏.桥梁伸缩缝服役性能劣化的概率预警方法[J].安全与环境学报,2022,22(4):1789-1796.
HUANG Hai-bin, FENG Jiang-su. Probability warning method for service performance deterioration of bridge expansion joints[J]. Journal of Safety and Environment, 2022, 22(4): 1789-1796.
[8]NI Y Q, WANG Y W, ZHANG C. A Bayesian approach for condition assessment and damage alarm of bridge expansion joints using long-term structural health monitoring data[J]. Engineering Structures, 2020, 212: 110520.
[9]HUANG H B, YI T H, LI H N, et al. New representative temperature for performance alarming of bridge expansion joints through temperature-displacement relationship[J]. Journal of Bridge Engineering, 2018, 23(7): 04018043.
[10]XIAO T G, HONG Y, XU J Y, et al. Performance evaluation of cable-stayed bridge expansion joints based on Lasso dimensionality reduction and temperature-displacement-correlation model[J]. Advances in Structural Engineering, 2024, 27(6): 981-994.
[11]NI Y Q, HUAX G, WONG K Y, et al. Assessment of bridge expansion joints using long-term displacement and temperature measurement[J]. Journal of Performance of Constructed Facilities, 2007, 21(2): 143-151.
[12]王 盛,陶天友,王 浩.大跨度斜拉桥伸缩缝温致位移提取方法对比[J].东南大学学报(自然科学版),2023,53(4):664- 671.
WANG Sheng, TAO Tian-you, WANG Hao. Comparison of extraction methods for temperature-induced displacement of expansion joint of long-span cable-stayed bridge[J]. Journal of Southeast University(Natural Science Edition), 2023, 53(4): 664-671.
[13]李 微.基于贝叶斯线性模型的桥梁伸缩缝损伤评估及可靠性研究[D].石家庄:石家庄铁道大学,2022.
LI Wei. Research on damage assessment and reliability of bridge expansion joints based on Bayesian linear model[D].Shijiazhuang: Shijiazhuang Tiedao University, 2022.
[14]丁幼亮,周 凯,王高新,等.苏通大桥斜拉桥伸缩缝位移的长期监测与分析[J].公路交通科技,2014,31(7):60-64,71.
DING You-liang, ZHOU Kai, WANG Gao-xin, et al. Long-term monitoring and analysis of expansion joint displacement of Sutong cable-stayed bridge[J]. Journal of Highway and Transportation Research and Development, 2014, 31(7): 60-64, 71.
[15]廖聿宸,张 坤,杜孟林,等.基于长期监测的开口截面组合梁斜拉桥温度场分析[J].东南大学学报(自然科学版),2023,53(6):1080-1090.
LIAO Yu-chen, ZHANG Kun, DU Meng-lin, et al. Analysis on the temperature fields of cable-stayed bridges with open-section composite girder based on long-term monitoring[J]. Journal of Southeast University(Natural Science Edition), 2023, 53(6): 1080-1090.
[16]QU H, NIU Z H, HUANG P M. Research on random fatigue load model of highway bridge by vehicle traffic based on GMM[J]. Tehnicki Vjesnik-Technical Gazette, 2020, 27(3): 961-969.
[17]林思健.基于模态参数和高斯混合模型聚类分析的结构损伤识别[D].广州:暨南大学,2022.
LIN Si-jian. Structural damage identification based on modal parameters and Gaussian mixture model cluster analysis[D]. Guangzhou: Jinan University, 2022.
[18]刘汉藤.基于多维概率分布模型的结构健康监测数据分析研究[D].广州:华南理工大学,2021.
LIU Han-teng. Data analysis of structural health monitoring based on multidimensional probability distribution models[D]. Guangzhou: South China University of Technology, 2021.
[19]QU G, SUN L M, HUANG H W. Bridge performance prediction based on a novel SHM-data assimilation approach considering cyclicity[J]. Structural Control and Health Monitoring, 2023, 2023(1): 2259575.
[20]MAO J X, WANG H, BILLIE F, et al. Gaussian mixture model for automated tracking of modal parameters of long-span bridge[J]. Smart Structures and Systems, 2019, 24(2): 243-256.
[21]MOHAMMAD H D, ALIREZA G, SEYED A Z, et al. Early damage detection under massive data via innovative hybrid methods: Application to a large-scale cable-stayed bridge[J]. Structure and Infrastructure Engineering, 2021, 17(7): 902-920.
[22]李 婧.基于GMM的EM优化算法的应用与研究[D].哈尔滨:哈尔滨工程大学,2018.
LI Jing. Research and application of EM optimization algorithm based on GMM[D]. Harbin: Harbin Engineering University, 2018.
[23]汤 峥,宋余庆,刘 哲.基于粒子群优化和EM算法的图像聚类研究[J].小型微型计算机系统,2015,36(7):1602-1606.
TANG Zheng, SONG Yu-qing, LIU Zhe. Research on clustering based on improved particle swarm optimization and expectation maximization algorithm[J]. Journal of Chinese Computer Systems, 2015, 36(7): 1602-1606.
[24]孙 颖,张 毅,丁卫平,等.基于近似骨架和混合蛙跳算法的K-means方法及其在眼底病历图像中的应用[J].南通大学学报(自然科学版),2020,19(2):36-42.
SUN Ying, ZHANG Yi, DING Wei-ping, et al. K-means method based on the approximate backbone and the shuffled frog leaping algorithm and its application in fundus medical record images[J]. Journal of Nantong University(Natural Science Edition), 2020, 19(2): 36-42.
[25]邓子畏,唐朝晖,朱红求,等.基于改进EM算法的混凝土泵车数据治理[J].中南大学学报(自然科学版),2021,52(2):443-449.
DENG Zi-wei, TANG Zhao-hui, ZHU Hong-qiu, et al. An improved expectation maximization algorithm for missing data management of concrete pump truck[J]. Journal of Central South University(Science and Technology)2021, 52(2): 443-449.
[26]邓 银,唐亚勇.APX-EM算法的带误差加速[J].四川大学学报(自然科学版),2025,62(1):52-56.
DENG Yin, TANG Ya-Yong. An error-included acceleration for the APX-EM algorithm[J]. Journal of Sichuan University(Natural Science Edition), 2025, 62(1): 52-56.
[27]翟继友,张 鹏.高斯混合模型参数估值算法的优化[J].计算机技术与发展,2011,21(11):145-148.
ZHAI Ji-you, ZHANG Peng. Optimization of parameter estimation based on gaussian mixture model[J]. Computer Technology and Development, 2011, 21(11): 145-148.
[28]陶叶辉.基于改进EM算法的高斯混合模型的研究与应用[D].上海:上海工程技术大学,2022.
TAO Ye-hui. Research and application of GMM based on improved EM algorithm[D]. Shanghai: Shanghai University of Engineering Science, 2022.
[29]SUN J, ZHAO Y, WANG S, et al. Image compression based on gaussian mixture model constrained using markov random field[J]. Signal Processing, 2021, 183: 107990.
[30]BRANISLAV P, JERNEJ K, MARKO N. Improved initialization of the EM algorithm for mixture model parameter estimation[J]. Mathematics, 2020, 8(3): 373.
[31]韩宇超,同向前,邓亚平.基于概率密度估计与时序Transformer网络的风功率日前区间预测[J].中国电机工程学报,2024,44(23):9285-9296.
HAN Yu-chao, TONG Xiang-qian, DENG Ya-ping. Probabilistic distribution estimation and temporal transformer-based interval prediction in day-ahead wind power prediction[J]. Proceedings of the CSEE, 2024, 44(23): 9285-9296.
[32]樊学平,刘月飞.基于改进高斯混合粒子滤波新算法的桥梁极值应力动态预测[J].吉林大学学报(工学版),2024,54(4):1038-1044.
FAN Xue-ping, LIU Yue-fei. Bridge extreme stress dynamic prediction based on improved Gaussian mixed particle filter new algorithm[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(4): 1038-1044.
[33]吴 铮,张 悦,董 泽.基于改进高斯混合模型的热工过程异常值检测[J].系统仿真学报,2023,35(5):1020-1033.
WU Zheng, ZHANG Yue, DONG Ze. Outlier detection during thermal processes based on improved Gaussian mixture model[J]. Journal of System Simulation, 2023, 35(5): 1020-1033.
[34]WANG D S, TAN D P, LIU L. Particle swarm optimization algorithm: An overview[J]. Soft Computing, 2018, 22(2): 387-408.
[35]蔡邦国,楼允鹏,尹 恒,等.基于监测数据的斜拉桥伸缩缝服役性能评估[J].公路,2020,65(5):98-105.
CAI Bang-guo, LOU Yun-peng, YIN Heng, et al. Evaluation of service performance of cable-stayed bridge expansion joints based on monitoring data[J]. Highway, 2020, 65(5): 98-105.
[36]刘 杰,武晓阳.基于健康监测长期数据的伸缩缝性能评估[C]//世界交通运输大会执委会.桥梁与隧道工程篇.北京:人民交通出版社股份有限公司,2022:393-400.
LIU Jie, WU Xiao-yang. Performance evaluation of expansion joints based on long-term health monitoring data[C]// ECWT. Executive Committee of World Transportation Conference. Bridge and Tunnel Engineering. Beijing: China Communications Press Co. Ltd., 2022: 393-400.
[37]张宇峰,承 宇,傅 斌,等.基于健康监测实测数据的江阴长江大桥伸缩缝状态分析与评定[C]//交通部公路科学研究院,东南大学.全国既有桥梁加固、改造与评价学术会议论文集.北京:人民交通出版社,2008:260-265.
ZHANG Yu-feng, CHENG Yu, FU Bin, et al. Analysis and evaluation of the expansion joint status of Jiangyin Yangtze River Bridge based on measured health monitoring data[C]// Research Institute of Highway Ministry of Transport, Southeast University. Proceedings of the National Academic Conference on Reinforcement, Reconstruction and Evaluation of Existing Bridges. Beijing: China Communications Press, 2008: 260-265.
[38]刘 扬,李杜宇,邓 扬.大跨度悬索桥伸缩缝位移监测数据分析与评估[J].长沙理工大学学报(自然科学版),2015,12(2):21-28.
LIU Yang, LI Du-yu, DENG Yang. Analysis and assessment of the monitoring data of expansion joints for long span suspension bridge[J]. Journal of Changsha University of Science and Technology(Natural Science), 2015, 12(2): 21-28.

相似文献/References:

[1]李宇,朱晞,杨庆山,等.高墩大跨桥梁结构的脆弱性分析[J].长安大学学报(自然科学版),2012,32(01):0.
[2]高亮,刘健新,张丹,等.桁架桥主梁三分力系数试验[J].长安大学学报(自然科学版),2012,32(01):0.
[3]刘旭政,王丰平,黄平明,等.斜拉桥各构件校验系数的常值范围[J].长安大学学报(自然科学版),2012,32(01):0.
[4]尚维波,张春宁.高墩刚构桥系梁抗震分析[J].长安大学学报(自然科学版),2012,32(01):0.
[5]邬晓光,李冀弘,宋伟伟.基于改进响应面法的在役PC桥梁承载力可靠性[J].长安大学学报(自然科学版),2012,32(03):53.
　WU Xiao-guang,LI Ji-hong,SONG Wei-wei.Reliability of existing PC bridge based on improved response surface method[J].Journal of Chang’an University (Natural Science Edition),2012,32(6):53.
[6]石雄伟,袁卓亚,马毓泉,等.钢板-混凝土组合加固预应力混凝土箱梁[J].长安大学学报(自然科学版),2012,32(03):58.
　SHI Xiong-wei,YUAN Zhuo-ya,MA Yu-quan,et al.Prestressed concrete box girder strengthened with comsposition of steel plate and concrete[J].Journal of Chang’an University (Natural Science Edition),2012,32(6):58.
[7]李传习,陶 伟,董创文.斜交墩截面刚度与弯曲正应力[J].长安大学学报(自然科学版),2012,32(03):63.
　LI Chuan-xi,TAO Wei,DONG Chuang-wen.Sectional stiffness and bending normal stress of oblique pier[J].Journal of Chang’an University (Natural Science Edition),2012,32(6):63.
[8]邓继华,邵旭东.带铰平面梁元几何非线性有限元分析[J].长安大学学报(自然科学版),2012,32(03):68.
　DENG Ji-hua,SHAO Xu-dong.Geometric nonlinear finite element analysis of plane beam element with hinge[J].Journal of Chang’an University (Natural Science Edition),2012,32(6):68.
[9]蒲广宁,赵 煜,宋一凡.减梁增肋法加固空心板桥的力学性能[J].长安大学学报(自然科学版),2012,32(06):38.
　PU Guang-ning,ZHAO Yu,SONG Yi-fan.Mechanical properties of strengthening hollow slab bridge based on beam-reduction and rib-addition method[J].Journal of Chang’an University (Natural Science Edition),2012,32(6):38.
[10]党 栋,贺拴海,周勇军,等.基于车辆统计数据的汽车荷载标准值取值与评估[J].长安大学学报(自然科学版),2012,32(06):44.
　DANG Dong,HE Shuan-hai,ZHOU Yong-jun,et al.Choosing and assessment for the standard of vehicle load based on vehicle statistical data[J].Journal of Chang’an University (Natural Science Edition),2012,32(6):44.

备注/Memo

备注/Memo:
收稿日期:2025-05-22
基金项目:国家自然科学基金项目(52368073,52068026); 赣鄱俊才支持计划项目(20243BCE51050); 江西省自然科学基金项目(20232BAB204070,20232BAB204071)
作者简介:吴 刚(1988-),男,江西高安人,副教授,工学博士,E-mail:wugang523@126.com。
更新日期/Last Update: 2025-12-20