Back propagation neural network prediction method research of pavement void based on wavelet transform method

PDF(2319 KB)

Journal of Vibration and Shock ›› 2016, Vol. 35 ›› Issue (18) : 203-209.

Liu Guoguang1,Wu Zhiwei1, Liu Zhiyong2, Zhao Longfei1

Author information +

History +

Abstract

Pavement void is one of the important parameters of influencing airport operation safety. In order to study the non-destructive test, back propagation prediction method research of pavement void on the basis of wavelet transform was proposed. By indoor model test, impacting load was imposed on scaled pavement model and vertical acceleration signals of pavement were obtained, which were used to achieve power spectrum analysis, energy spectrum analysis and time-scale analysis by wavelet transform method. Back propagation(BP) neural network was trained by 1500 sets of feature vectors of indicating different pavement void conditions in order to improve the prediction function. Site experiment of airport pavement was conducted and pavement concrete samples were drilled to validate the reliability of BP neural network prediction. The results showed that, pavement vibration signals reflected the dissipative effects of energy signal in void area after wavelet transform analysis. It had significant differences and regular patterns in completed void and half void areas. The results of site experiment were satisfied the prediction of BP neural network trained by indoor test results. And signal of slight void was distinguished, by which the reliability and feasibility were proved in pavement void evaluation by this method.

Key words

pavement engineering / pavement void / wavelet transform / back propagation neural network

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Liu Guoguang1,Wu Zhiwei1, Liu Zhiyong2, Zhao Longfei1. Back propagation neural network prediction method research of pavement void based on wavelet transform method[J]. Journal of Vibration and Shock, 2016, 35(18): 203-209

References

[1] Huang M H and Thambiratnam D P. Dynamic response of plates on elastic foundation to moving loads[J]. Journal of engineering mechanics, 2002, 128(9):1016-1022.
[2] 李洪泉, 董亮, 吕西林. 基于小波变换的结构损伤识别与试验分析[J]. 土木工程学报, 2003, 36(5): 52-57.
Li Hong-qua, Dong Li-ang, Lv Xi-lin. Identification of structural damage and test study based on wavelet transform[J]. China civil engineering journal, 2003, 36(5): 52-57.
[3] 陈仕龙, 张杰, 毕贵红等. 基于小波分析的特高压直流输电线路双端电压暂态保护[J]. 电网技术, 2013, 37(10): 2719-2725.
Chen Shi-long, Zhang Jie, Bi Gui-hong, et al. Wavelet analysis based two-terminal transient voltage protection for UHVDC transmission lines[J]. Power system technology,2013, 37(10):2719-2725.
[4] 章浙涛, 朱建军, 匡翠林等. 小波包多阈值去噪法及其在形变分析中的应用[J]. 测绘学报, 2014, 43(1): 13-20.
Zhang Zhe-tao, Zhu Jian-jun, Kuang Cui-lin, et al. Multi-threshold wavelet packet de-noising method and its application in deformation analysis[J]. Acta geodaeticaet cartographica sinica, 2014, 43(1):13-20.
[5] 叶玮琳, 郑传涛, 王一丁. 基于TDLAS的红外湿度检测中的小波去噪试验研究[J]. 光电子﹒激光, 2013, 24(1): 104-111.
Ye Wei-lin, Zheng Chuan-tao, Wang Yi-ding. Experimental research on wavelet denoising in infrared humidity detection based on TDLAS technique[J]. Journal of optoelectronics﹒laser, 2013, 24(1): 104-111.
[6] 孙磊, 慕玉坤, 郝宪武.基于小波变换和ARIMA模型的桥梁健康监测数据分析[J]. 中外公路, 2015, 35(1): 126-130.
Sun Lei, Mu Yu-kun, Hao Xian-wu. Analysis of bridge health monitoring data based on wavelet transform and arima model[J]. Journal of china & foreign highway, 2015, 35(1): 126-130.
[7] 李保琦, 周泽江, 马妍博. 基于小波神经与随机分析的径流预测[J]. 西北农林科技大学学报（自然科学版）, 2014, 34（11）: 169-174.
Li Bao-qi, Zhou Ze-jiang, Ma Yan-bo. Runoff forecasting based on wavelet analysis, artificial neural network and hydrologic frequency analysis[J]. Journal of northwest A&F university(natural science edition), 2014, 34(11): 169-174.
[8] 卢正, 姚海林, 胡智. 基于车辆-道路结构耦合振动的不平整路面动力响应分析[J]. 岩土工程学报, 2013, 35(1): 232-238.
Lu Zheng, Yao Hai-lin, Hu Zhi. Dynamic response analysis of rough pavement under vehicle-road system coupled vibration[J]. Chinese journal of geotechnical engineering, 2013, 35(1): 232-238.
[9] Maier H R and 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.
[10] Muleta M K and Nicklow J W. Joint application of artificial neural networks and evolutionary algorithms to watershed management[J]. Water resources management, 2004, 18(5): 459-482.
[11] Nash J E and Sutcliffe J V. River flow forecasting through conceptual models: Part I-A discussion of principles[J]. Journal of hydrology,1970, 125: 277-291.
[12] 崔东文. 多隐层BP神经网络模型在径流预测中的应用[J]. 水文, 2013, 33(1): 68-73.
Cui Dong-wen. Application of hidden multilayer BP neural network model in runoff prediction[J]. Journal of china hydrology, 2013, 33(1): 68-73.
[13] 杨发群, 邱卫宁, 魏成等. 顾及不确定因素的GA-BP神经网络在路基沉降预测中的应用[J]. 测绘工程, 2013, 22(6): 51-54.
Yang Fa-qun, Qiu Wei-ning, Wei Cheng, et al. Application of GA-BP neural network with uncertainties to the subgrade settlement prediction[J]. Engineering of surveying and mapping, 2013, 22(6): 51-54.
[14] 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 Jing-luo, An Feng-ping. Study on slope displacement prediction model based on LMD-BP neural network[J]. Computer applications and software, 2013, 30(9): 107-109.
[15] 彭永恒, 任瑞波, 罗跃纲等. 刚性路面脱空声识别集成神经网络方法[J]. 中南公路工程, 2005, 30(3):15-18.
Peng Yong-heng, Ren Rui-bo, Luo Yue-gang. Void acoustic identifying of rigid pavement based on integrated neural network[J]. Journal of central south highway engineering, 2005, 30(3):15-18.
[16] 刘海平, 刁延松. 基于小波包分析与BP神经网络的结构损伤检测研究[J]. 工程建设, 2013, 45(4): 13-16.
Liu Hai-ping, DiaoYan-song. Study on the structural damage identification based on wavelet packet and BP neural network[J]. Engineering construction, 2013, 45(4):13-16.