[1]刘国光,武志玮,牛富俊,等.基于BP神经网络的场道脱空检测方法及实验[J].深圳大学学报理工版,2016,33(No.3(221-330)):309-316.[doi:10.3724/SP.J.1249.2016.03309]
 Liu Guoguang,Wu Zhiwei,Niu Fujun,et al.Airport pavement void testing based on back propagation neural network[J].Journal of Shenzhen University Science and Engineering,2016,33(No.3(221-330)):309-316.[doi:10.3724/SP.J.1249.2016.03309]
点击复制

基于BP神经网络的场道脱空检测方法及实验()
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第33卷
期数:
2016年No.3(221-330)
页码:
309-316
栏目:
土木建筑工程
出版日期:
2016-05-20

文章信息/Info

Title:
Airport pavement void testing based on back propagation neural network
文章编号:
201603013
作者:
刘国光12武志玮2牛富俊1赵龙飞2
1) 冻土工程国家重点实验室,甘肃兰州 730000
2) 中国民航大学机场学院,天津 300300
Author(s):
Liu Guoguang12 Wu Zhiwei2 Niu Fujun1 and Zhao Longfei2
1) State Key Laboratory of Frozen Soil Engineering, Lanzhou 730000, Gansu Province, P.R.China
2) Airport College, Civil Aviation University of China, Tianjin 300300, P.R.China
关键词:
道路工程场道脱空小波变换BP神经网络模型试验现场测试
Keywords:
pavement engineering pavement void wavelet transform back propagation neural network model experiment site test
分类号:
U 416.201
DOI:
10.3724/SP.J.1249.2016.03309
文献标志码:
A
摘要:
为研究场道脱空检测方法,进行室内模型试验,获得冲击荷载作用下道面板加速度响应时程曲线,利用Matlab小波变换工具箱提取加速度曲线特征值,分析脱空对振动信号的影响规律. 通过优化荷载级数、筛选输入向量,建立了场道脱空的BP(back propagation)神经网络预测方法. 为检验理论研究结果的正确性,利用重锤式弯沉仪在机场进行跑道脱空测试,通过场道取芯脱空观察评价BP神经网络预测结论的可靠性. 结果表明,荷载级数、输入向量、训练次数、训练强度和算法对BP神经网络预测准确性影响较大;脱空影响下场道加速度信号可作为BP神经网络脱空预测的输入向量,取芯后场道脱空状况同BP神经网络预测结果一致.
Abstract:
In order to investigate the test method of airport pavement voids, a laboratory model test was conducted to achieve the time-history curve of acceleration response of airport pavement under impact loading. The characteristic value of the acceleration curve was obtained by the wavelet transform tool box of Matlab, by which the influence law of pavement voids on vibration signal was analyzed. By optimizing loading steps and screening input vectors, a pavement void prediction method based on back propagation neural network was established. To calibrate the prediction method, a runway field test was carried out by using heavy weight deflector, by which the reliability of back propagation neural network prediction was evaluated by plate coring. The results show that the loading steps, the input vector, training times, the training intensity and algorithm have significant influences on the prediction accuracy of the back propagation neural network. The pavement acceleration influenced by void could be used as the input vector of back propagation neural network, the prediction result of the back propagation neural network was proved by void observation of site coring.

参考文献/References:

[1] 徐秉铮,张百灵. 神经网络及其在信号处理中的应用[J]. 信号处理, 1992,8(2):65-73.
Xu Bingzheng, Zhang Bailing. Neural network and their application in signal processing[J]. Signal Processing, 1992, 8(2): 65-73.(in Chinese)
[2] Muleta M K, Nicklow J W. Joint application of artificial neural networks and evolutionary algorithms to watershed management[J]. Water Resources Management, 2004, 18(5): 459-482.
[3] Nash J E, Sutcliffe J V. River flow forecasting through conceptual models: a discussion of principles[J]. Journal of Hydrology, 1970, 125: 277-291.
[4] Maier H R, Dandy G C. Neural networks for the prediction and forecasting of water resources variables: a review of modeling issues and applications[J]. Environmental Modeling and Software, 2000, 15(1): 101-124.
[5] 丁鸽,花向红,田茂,等. 改进的小波神经网络在沉降预测中的应用[J]. 测绘地理分析, 2013, 38(6): 27-29.
Ding Ge, Hua Xianghong, Tian Mao, et al. Subsidence prediction based on the application of modified wavelet neural network[J]. Journal of Geomatics, 2013, 38(6): 27-29.(in Chinese)
[6] 王雪红,刘晓青,陶海龙,等. 优化BP神经网络的位移预测模型[J]. 水利水运工程学报, 2014(2): 38-42.
Wang Xuehong, Liu Xiaoqing, Tao Hailong, et al. A displacement prediction model based on improved particle swarm-BP neural network algorithm[J]. Hydro-Science and Engineering, 2014(2):38-42.(in Chinese)
[7] 郑伟花,王宗华. 蚁群神经网络算法在超声检测混凝土缺陷中的应用[J]. 无损检测, 2013, 35(5): 4-7.
Zheng Weihua, Wang Zonghua. Ant colony algorithm and application in inspection of concrete structure defects[J]. Non Destructive Testing, 2013, 35(5) : 4-7.(in Chinese)
[8] 于伟, 蔡璟珞, 安凤平. 边坡位移LMD-BP神经网络模型研究[J].计算机应用与软件,2013, 30(9): 107-109.
Yu Wei, Cai Jingluo, An Fengping. On slope displacement prediction model based on LMP-BP neural network[J]. Computer Applications and Software, 2013, 30(9): 107-109.(in Chinese)
[9] 戴张俊,余飞,陈善雄,等. 淮北平原地基分层与承载力的BP网络预测方法[J].土木建筑与环境工程, 2013, 35(3):18-24.
Dai Zhangjun, Yu Fei, Chen Shanxiong, et al. Stratifications and bearing capacity prediction method based on BP neural network for foundation in Huaibei plain[J]. Journal of Civil Architectural and Environmental Engineering, 2013, 35(3): 18-24.(in Chinese)
[10] 陈春来. 基于BP神经网络模型的建筑工程安全损失预测研究[J]. 建筑施工, 2013, 35(1): 88-90.
Chen Chunlai. Study on prediction of construction engineering accident loss based on BP neural network model[J]. Building Construction, 2013, 35(1): 88-90.(in Chinese)
[11] 张蛟龙,柳献,朱洪波,等. 基于神经网络的UHPC力学性能预测模型[J].混凝土理论研究, 2013(3): 18-22.
Zhang Jiaolong, Liu Xian, Zhu Hongbo, et al. Model for predicting the mechanical behavior of UHPC based on BP neural network[J]. Concrete Theoretical Research, 2013(3): 18-22.(in Chinese)
[12] 吴陈,盛晖. 一个基于BP神经网络和数据库的综合预测系统[J]. 华东船舶工业学院学报, 1993, 7(3): 53-60.
Wu Chen, Sheng Hui. An integrated predictive system based on BP ANN and databases[J]. Journal of East China Shipbuilding Institute, 1993, 7(3): 53-60.(in Chinese)
[13] 刁延松,张启亮,孟冬梅. 基于振动传递率的钢质导管架海洋平台结构损伤识别方法研究[J]. 建筑钢结构进展, 2013, 15(1): 50-56.
Diao Yansong, Zhang Qiliang, Meng Dongmei. Study on the damage identification method of steel jacket offshore platform based on vibration transmissibility function[J]. Progress in Steel Building Structures, 2013, 15(1): 50-56.(in Chinese)

相似文献/References:

[1]栗振锋,张敏.FWD动载下的横观各向同性路基动力响应分析[J].深圳大学学报理工版,2013,30(No.2(111-220)):195.[doi:10.3724/SP.J.1249.2013.02195]
 Li Zhenfeng and Zhang Min.The analysis of dynamic response of transversely isotropic subgrade based on FWD[J].Journal of Shenzhen University Science and Engineering,2013,30(No.3(221-330)):195.[doi:10.3724/SP.J.1249.2013.02195]
[2]胡江洋,毛君,张浩,等.火山渣作为路基填料的试验研究[J].深圳大学学报理工版,2015,32(No.6(551-660)):625.[doi:10.3724/SP.J.1249.2015.06625]
 Hu Jiangyang,Mao Jun,et al.Research on test characteristic of cinder as subgrade filling[J].Journal of Shenzhen University Science and Engineering,2015,32(No.3(221-330)):625.[doi:10.3724/SP.J.1249.2015.06625]
[3]胡江洋,陈团结,折学森.路用改性煤沥青毒性消减试验效果分析[J].深圳大学学报理工版,2016,33(No.4(331-440)):418.[doi:10.3724/SP.J.1249.2016.04418]
 Hu Jiangyang,Chen Tuanjie,et al.Analysis of toxicity reduction test about modified coal tar used for road[J].Journal of Shenzhen University Science and Engineering,2016,33(No.3(221-330)):418.[doi:10.3724/SP.J.1249.2016.04418]
[4]吴朝阳,杨少伟,林岚,等.互通式立交高事故率出口的判定方法[J].深圳大学学报理工版,2016,33(No.5(441-550)):536.[doi:10.3724/SP.J.1249.2016.05536]
 Wu Zhaoyang,Yang Shaowei,Lin Lan,et al.Method for identifying the high accident rate exits of interchange[J].Journal of Shenzhen University Science and Engineering,2016,33(No.3(221-330)):536.[doi:10.3724/SP.J.1249.2016.05536]
[5]杨俊,李晓峰,相飞飞,等.废弃混凝土用作再生路面的试验研究[J].深圳大学学报理工版,2017,34(No.3(221-330)):252.[doi:10.3724/SP.J.1249.2017.03252]
 Yang Jun,Li Xiaofeng,Xiang Feifei,et al.Experimental study on waste concrete as regenerate pavement[J].Journal of Shenzhen University Science and Engineering,2017,34(No.3(221-330)):252.[doi:10.3724/SP.J.1249.2017.03252]
[6]柯文豪,陈华鑫,雷宇,等.基于GRNN神经网络的沥青路面裂缝预测方法[J].深圳大学学报理工版,2017,34(No.4(331-440)):378.[doi:10.3724/SP.J.1249.2017.04378]
 Ke Wenhao,Chen Huaxin,Lei Yu,et al.Prediction method for asphalt pavement crack based on GRNN neural network[J].Journal of Shenzhen University Science and Engineering,2017,34(No.3(221-330)):378.[doi:10.3724/SP.J.1249.2017.04378]
[7]李晶晶,张擎,陈忠达.水泥路面环氧树脂磨耗层的抗滑衰变模型[J].深圳大学学报理工版,2017,34(No.6(551-660)):562.
 Li Jingjing,Zhang Qing,and Chen Zhongda.Skid resistance performance model of epoxy wear layer for cement pavement[J].Journal of Shenzhen University Science and Engineering,2017,34(No.3(221-330)):562.
[8]武志玮,刘国光,刘智勇.基于小波变换的场道脱空识别[J].深圳大学学报理工版,2017,34(No.3(221-330)):265.[doi:10.3724/SP.J.1249.2017.03265]
 Wu Zhiwei,Liu Guoguang,and Liu Zhiyong,et al.Runway pavement void identification based on wavelet transform[J].Journal of Shenzhen University Science and Engineering,2017,34(No.3(221-330)):265.[doi:10.3724/SP.J.1249.2017.03265]

备注/Memo

备注/Memo:
Received:2016-01-07;Accepted:2016-03-08
Foundation:National Natural Science Foundation of China(51178456); Open Foundation of State Key Laboratory of Frozen Soil Engineering (SKLFSE201409); Fundamental Research Funds for the Central Universities(3122016D019)
Corresponding author:Professor Niu Fujun. E-mail:niufujun@lzb.ac.cn
Citation:Liu Guoguang, Wu Zhiwei, Niu Fujun, et al. Airport pavement void testing based on back propagation neural network[J]. Journal of Shenzhen University Science and Engineering, 2016, 33(3): 309-316.(in Chinese)
助项目(SKLFSE201409);中央高校基本业务费资助项目(3122016D019)
作者简介:刘国光(1980—),男,中国民航大学讲师. 研究方向:机场工程及结构振动分析. E-mail:ggliu@cauc.edu.cn
引文:刘国光,武志玮,牛富俊,等. 基于BP神经网络的场道脱空检测方法及实验[J]. 深圳大学学报理工版,2016,33(3):309-316.
更新日期/Last Update: 2016-05-08