Abstract：Background vibration can disturb environmental vibration induced by highway, railway and urban rail transit. Neural Network method based on L-M (Levenberg-Marquardt) algorithm, a time-domain analysis approach, was proposed to remove background vibration from environmental vibration testing data. The basic principle and implementation steps were discussed. Neural Network was trained by using L-M algorithm which sped up the network training rate and improved the accuracy of network training. A background vibration acceleration time history was superimposed on a traffic vibration to synthesize a testing vibration record, which was used to remove background vibration by L-M Neural Network approach and other approaches. The calculated results indicated that L-M Neural Network method can obtain time history, power spectral density, vibration acceleration level on one-third octave band center frequency and weighted level of the true traffic vibration more accurately, which showed that L-M Neural Network method was superior to other current methods.
耿传飞1，卢文良1，俞醒2. 基于L-M算法的神经网络在环境振动分析中消除本底振动的应用[J]. 振动与冲击, 2016, 35(13): 14-19.
GENG Chuanfei1, LU Wenliang1, YU Xing2. Application of Neural Network based on L-M Algorithm in removing background vibration from environmental vibration analysis. JOURNAL OF VIBRATION AND SHOCK, 2016, 35(13): 14-19.
[1] 李小珍，刘全民，张迅，等.高架轨道交通附近自由地表振动试验研究[J].振动与冲击，2014,33(16):56-61.
LI Xiao-zhen, LIU Quan-min, ZHANG Xun, et al. Ground vibration induced by inter-city express train[J]. Journal of Vibration and Shock, 2014,33(16):56-61.
[2] 张 昕.高架轨道交通引起环境振动的实测和理论分析研究
[D].上海：同济大学，2002.
ZHANG Xin. Practical and Theoretical Research on the Environmental Vibration caused by Elevated Railroad Traffic[D].Shanghai: Tongji University,2002.
[3] 邱俊杰.高架轨道交通引起环境振动的实测与评价方法研究
[D].武汉：武汉理工大学，2005.
QIU Jun-jie. Practical and Evaluation Research on the Environmental Vibration caused by Elevated Railway Traffic[D]. Wuhan: Wuhan University of Technology, 2005.
[4] 崔高航，陶夏新，陈宪麦.城轨交通地面线路产生环境振动频域分析[J].沈阳建筑大学学报（自然科学版），2008,24(2)：239-243.
CUI Gao-hang, TAO Xia-xin, CHEN Xian-mai. Analysis of Environmental Vibration induced by Urban Rail Transit on Ground in Frequency Domain.[J]. Shenyang Jianzhu University (Natural Science), 2008,24(2): 239-243.
[5] 张向东，闫维明，任 珉，等.交通环境振动测试中的本底振
动分析[J].振动与冲击，2009,28(4)：177-179,197.
ZHANG Xiang-dong, YAN Wei-ming, REN Min, et al. Background Vibration Analysis for Traffic Environmental Vibration Testing[J]. Journal of Vibration and Shock, 2009,28(4)：177-179,197.
[6] 王福彤，陶夏新，郑鑫，等.交通环境振动观测中本底振动去除的功率谱修正法[J].振动与冲击，2011,30(4):124-126,172.
WANG Fu-tong, TAO Xia-xin, ZHENG Xin, et al. PSD Correction Method for Removing Background Vibration from Traffic Environmental Vibration Observation[J]. Journal of Vibration and Shock, 2011,30(4):124-126,172.
[7] 郑鑫，陶夏新，王福彤，等.去除交通环境振动观测记录中本底振动的自互功率谱法[J].地球物理学报，2013,56(1):348-353.
ZHENG Xin, TAO Xia-xin, WANG Fu-tong, et al. An Auto-cross PSD Method to Remove Background Vibration from Observational Records of Traffic Environment Vibration[J]. Chinese Journal of Geophysics, 2013,56(1):348-353.
[8] 毛健，赵红东，姚婧婧.人工神经网络的发展及应用[J].电子设计工程，2011,19(24)：62-65.
Mao Jian, Zhao Hong-dong, Yao Jing-jing. Application and prospect of Artificial Neural Network[J]. Electronic Design Engineering, 2011,19(24)：62-65.
[9] 朱大奇,史慧.人工神经网络原理及应用[M].北京:科学出版社，2006.
ZHU Da-qi, SHI Hui. Theory and application of artificial neural network[M]. Beijing: Science Press, 2006.
[10] 吴昌友.神经网络的研究及应用[D].哈尔滨：东北农业大学，2007.
Wu Chang-you. The research and application on neural network[D]. Harbin: Northeast Agricultural University, 2007.
[11] 刘天舒.BP神经网络的改进研究及应用[D].哈尔滨：东北农业大学，2011.
Liu Tian-shu. The research and application on BP neural network improvement[D], Harbin: Northeast Agricultural University, 2011.
[12] 周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京：清华大学出版社，2005.
ZHOU Kai-li, KANG Yao-hong. Neural network model and MATLAB simulation program design[M]. Beijing. Tsinghua University Press, 2005.
[13] 周洪波，基于人工神经网络的大坝变形监测正反分析研究[D].武汉：武汉大学，2004.
ZHOU Hong-bo, Research on Analysis and Back-analysis of Deformation Monitoring for Dam Based on Artificial Neural Network[D]. Wuhan: Wuhan University, 2004.
