基于数据挖掘技术的桥梁结构健康状态检测

doi:10.13229/j.cnki.jdxbgxb20190083

摘要/Abstract

摘要：

针对当前桥梁结构健康状态检测模型存在的检测误差大、检测效率差等难题，以改善桥梁结构健康状态检测结果为目标，设计了基于数据挖掘技术的桥梁结构健康状态检测模型。首先,采用无线传感器网络对桥梁结构健康状态数据进行采集，并采用核主成分分析对桥梁结构健康数据处理，去除桥梁结构健康数据的冗余特征，减少桥梁结构健康状态检测特征规模;然后,采用支持向量机对桥梁结构健康数据进行学习，并引入粒子群优化算法确定的桥梁结构健康状态检测模型的参数，建立最优的桥梁结构健康状态检测模型;最后,在Matlab2017平台上对桥梁结构健康模型的有效性和优越性进行测试。结果表明：本文模型获得了较高精度的桥梁结构健康状态检测结果，桥梁结构健康建模时间减少，提高了桥梁结构健康状态检测效率，而且桥梁结构健康状态检测整体性能要明显优于当前其他的桥梁结构健康检测模型，为桥梁结构健康研究提供了一种有效的工具。

关键词: 桥梁结构, 健康状态, 核主成分分析, 冗余特性, 检测精度, 建模效率

Abstract:

In order to improve the health detection results of bridge structures, a health detection model of bridge structures based on data mining technology is designed to solve the problems of large error and poor detection efficiency in the current health detection model. Firstly, the health data of bridge structure is collected by wireless sensor network, and the data is processed by kernel principal component analysis, which eliminates the redundancy of bridge structure health data and reduces the detection scale of bridge structure health. Then, the support vector machine is used to learn the health data of bridge structure. The parameters of bridge structure health detection model determined by particle swarm optimization algorithm are introduced to establish the optimal bridge structure health detection model. Finally, the effectiveness and superiority of the bridge structure health model are tested on the platform of Matlab 2017. The results show that the model achieves high precision bridge structure health. The health detection results show that the time of bridge structure health modeling is reduced, and the efficiency of bridge structure health detection is improved. Moreover, the overall performance of the proposed bridge health detection model is obviously better than that of other bridge health detection models. The proposed model provides an effective tool for bridge structure health research.

Key words: bridge structure, health status, nuclear principal component analysis, redundancy characteristics, detection accuracy, modeling efficiency

中图分类号:

TM933

武立群,张亮亮. 基于数据挖掘技术的桥梁结构健康状态检测[J]. 吉林大学学报(工学版), 2020, 50(2): 565-571.

Li-qun WU,Liang-liang ZHANG. Health detection of bridge structures based on data mining technology[J]. Journal of Jilin University(Engineering and Technology Edition), 2020, 50(2): 565-571.

图/表 5

图1

图2

表1

表2

图3

参考文献 20

1	柳春光, 张士博. 考虑地震、波浪和海流作用的跨海桥梁结构研究进展[J]. 大连理工大学学报, 2017, 57(1): 105-110.
	Liu Chun-guang, Zhang Shi-bo. Research progress of sea-crossing bridge structure considering action of earthquake, wave and current[J]. Journal of Dalian University of Technology, 2017, 57(1): 105-110.
2	Wang J, Song Y, Yu Z. Impact factor method for design of bridge foundations under ship collisions[J]. Advances in Structural Engineering, 2017, 20(4): 534-548.
3	余志武, 何华武, 蒋丽忠, 等. 多动力作用下高速铁路轨道-桥梁结构体系动力学及关键技术研究[J]. 土木工程学报, 2017, 50(11): 1-9.
	Yu Zhi-wu, He Hua-wu, Jiang Li-zhong, et al. Dynamics and key technology research on high-speed railway track-bridge system under multiple dynamic sources[J]. China Civil Engineering Journal, 2017, 50(11): 1-9.
4	崔春义, 孟坤, 陈守龙, 等. 场地软土夹层对桥梁结构相互作用体系动力响应影响参数化分析[J]. 防灾减灾工程学报, 2017, 37(6): 951-957.
	Cui Chun-yi, Meng Kun, Chen Shou-long, et al. Parametric analyses of effects of soft-soil layer on seismic response of interaction system of bridge structure[J]. Journal of Disaster Prevention and Mitigation Engineering, 2017, 37(6): 951-957.
5	万华平, 任伟新, 颜王吉. 桥梁结构动力特性不确定性的全局灵敏度分析的解析方法[J]. 振动工程学报, 2016, 29(3): 429-435.
	Wan Hua-ping, Ren Wei-xin, Yan Wang-ji. Analytical global sensitivity analysis for uncertainty in structural dynamic properties of bridges[J]. Journal of Vibration Engineering, 2016, 29(3): 429-435.
6	陈东军, 李天华, 彭凯, 等. 基于损伤性能函数的桥梁结构损伤识别[J]. 重庆交通大学学报: 自然科学版, 2018, 37(10): 1-7, 20.
	Chen Dong-jun, Li Tian-hua, Peng Kai, et al. Bridge structure damage identification based on the damage performance function[J]. Journal of Chongqing Jiaotong University (Natural Sciences), 2018, 37(10): 1-7, 20.
7	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.
	Li Yu-jing, Li Hong-nan, Li Chao. Preference-based multi-objective optimization model for life-cycle seismic design of bridge [J]. China Journal of Highway and Transport, 2017, 30(12): 187-195.
8	Lai Z, Lei Y, Zhu S, et al. Moving-window extended kalman filter for structural damage detection with unknown process and measurement noises[J]. Measurement, 2016, 88: 428-440.
9	刘洋, 熊伟芬, 邱明喜. 基于正态云模型的桥梁结构安全风险评价[J]. 筑路机械与施工机械化, 2017, 34(9): 116-120.
	Liu Yang, Xiong Wei-fen, Qiu Ming-xi. Risk assessment of bridge structures based on normal cloud model[J]. Road Machinery ＆ Construction Mechanization, 2017, 34(9): 116-120.
10	兰日清, 李小军, 丰彪, 等. 近场强震作用下城市桥梁结构灾害评价方法研究[J]. 自然灾害学报, 2017, 26(4): 135-142.
	Lan Ri-qing, Li Xiao-jun, Feng Biao, et al. Study on the seismic damage evaluation method of urban bridges under the near-field strong ground motion[J]. Journal of Natural Disasters, 2017, 26(4): 135-142.
11	Mansouri M, Avci O, Nounou H, et al. Iterated square root unscented Kalman filter for nonlinear states and parameters estimation: three DOF damped system[J]. Journal of Civil Structural Health Monitoring, 2015, 5(4): 493-508.
12	李修云, 黄硕, 杨文伟, 等. 面向桥梁结构状态预测的ARMA-GM组合时序模型研究[J]. 重庆交通大学学报：自然科学版, 2016, 35(4): 6-9, 24.
	Li Xiu-yun, Huang Shuo, Yang Wen-wei, et al. Study on ARMA-GM combined time-series model for structural state prediction of bridges[J]. Journal of Chongqing Jiaotong University (Natural Sciences), 2016, 35(4): 6-9, 24.
13	Fan W, Yuan W. Dynamic demand of bridge structure subjected to vessel impact using simplified interaction model[J]. Journal of Bridge Engineering, 2017, 16(1): 117-126.
14	张春丽, 吕中荣. 考虑温度影响的桥梁结构损伤识别[J]. 中山大学学报：自然科学版, 2016, 55(3): 102-105.
	Zhang Chun-li, Lu Zhong-rong. Structural damage identification including the temperature difference based on response sensitivity analysis[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2016, 55(3): 102-105.
15	肖书敏, 闫云聚, 姜波澜. 基于小波神经网络方法的桥梁结构损伤识别研究[J]. 应用数学和力学, 2016, 37(2): 149-159.
	Xiao Shu-min, Yan Yun-ju, Jiang Bo-lan. Damage identification for bridge structures based on the wavelet neural network method [J]. Applied Mathematics and Mechanics, 2016, 37(2): 149-159.
16	隗海林, 包翠竹, 李洪雪, 等. 基于最小二乘支持向量机的怠速时间预测[J]. 吉林大学学报：工学版, 2018, 48(5): 1360-1365.
	Kui Hai-lin, Bao Cui-zhu, Li Hong-xue, et al. Idling time prediction method based on least square support vector machine[J]. Journal of Jilin University (Engineering and Technology Edition), 2018, 48(5): 1360-1365.
17	李元诚, 邱日轩, 曾婧. 基于核主成分分析的智能电网盲在线虚假数据注入攻击[J]. 电网技术, 2018, 42(7): 2270-2278.
	Li Yuan-cheng, Qiu Ri-xuan, Zeng Jing. Blind online false data injection attack using kernel principal component analysis in smart grid[J]. Power System Technology, 2018, 42(7): 2270-2278.
18	陈永高. 基于自适应EEMD和盲辨识算法的桥梁结构模态参数识别[J]. 重庆交通大学学报：自然科学版, 2016, 35(3): 11-16.
	Chen Yong-gao. Modal parameter identification of bridge structure based on adaptive EEMD and blind identification algorithm[J]. Journal of Chongqing Jiaotong University (Natural Sciences), 2016, 35(3): 11-16.
19	徐健, 周志祥, 赵丽娜, 等. 基于AEEMD和改进DATA-SSI算法的桥梁结构模态参数自动化识别[J]. 土木工程学报, 2017, 50(7): 87-98.
	Xu Jian, Zhou Zhi-xiang, Zhao Li-na, et al. Automatic identification of modal parameter for bridges based on AEEMD and improved DATA-SSI[J]. China Civil Engineering Journal, 2017, 50(7): 87-98.
20	马宏伟, 林逸洲, 聂振华. 利用少量传感器信息与人工智能的桥梁结构安全监测新方法[J]. 建筑科学与工程学报, 2018, 35(5): 9-23.
	Ma Hong-wei, Lin Yi-zhou, Nie Zhen-hua. New methods of structural health monitoring based on small amount of sensor information and artificial intelligence[J]. Journal of Architecture and Civil Engineering, 2018, 35(5): 9-23.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

类型标签	桥梁结构损伤程度	损伤指数	训练样本数量/个	测试样本数量/个
1	微损伤	<0.05	500	150
2	轻度损伤	0.05~0.4	150	50
3	中等损伤	0.4~0.75	80	20
4	严重损伤	0.75~1	20	5

桥梁结构损伤程度	第1元特征值	第2元特征值	第3元特征值	第4元特征值	第5元特征值
微损伤	8.73	5.51	3.84	2.35	1.55
轻度损伤	9.90	4.95	3.76	2.06	1.43
中等损伤	13.33	4.05	2.00	1.59	1.08
严重损伤	8.79	5.13	2.93	2.58	1.32

[1]	刘寒冰, 吴春利, 程永春. 不同适应度函数的遗传算法在桥梁结构传感器布设中的应用[J]. 吉林大学学报(工学版), 2012, 42(01): 51-56.
[2]	殷涌光，葛晶, ，于庆宇，王凯. 利用胶体金复合抗体提高SPR生物传感器的微生物检测精度[J]. 吉林大学学报(工学版), 2005, 35(04): 446-450.