Percussion inspection voice recognition of railway tunnel voids based on ensemble methods

GAO Lei,LIU Zhenkui,ZHANG Haoyu,WEI Xiaoyue,ZHANG Kui

Journal of Vibration and Shock ›› 2022, Vol. 41 ›› Issue (14) : 58-63.

PDF(1067 KB)
PDF(1067 KB)
Journal of Vibration and Shock ›› 2022, Vol. 41 ›› Issue (14) : 58-63.

Percussion inspection voice recognition of railway tunnel voids based on ensemble methods

  • GAO Lei,LIU Zhenkui,ZHANG Haoyu,WEI Xiaoyue,ZHANG Kui
Author information +
History +

Abstract

The percussion inspection method of voids behind tunnel lining is widely used in railway tunnel at present, but the identification and data recording are completed manually. In order to recognize the percussion inspection voice in railway tunnel intelligently, the voice files which were collected from the tunnel percussion inspection were preprocessed, 645 groups of voice samples were selected, and the 24-dimensional Mel frequency cepstrum coefficients (MFCC) were extracted as the acoustic feature parameters of the voice samples. The classification model for the voice of tunnel percussion inspection was established by training the parameters with the ensemble methods (gradient boosting decision tree). Finally, the model was applied to the actual railway tunnel to recognise voids according to percussion inspection voice. The case study shows that the GBDT ensemble methods model has higher accuracy and less operation time, compared with the optimized support vector machine (CV-SVM) model and the improved radial basis function neural network (PSO-RBF) model. It has stronger stability when processing abnormal data, can accurately diagnose the existence of voids behind the lining according to the percussion inspection voice.
Key words: railway tunnel; voice recognition; mel frequency cepstral coefficents; gradient boosting decision tree; support vector machine; improved RBF neural network

Key words

railway tunnel / voice recognition / mel frequency cepstral coefficents / gradient boosting decision tree / support vector machine / improved RBF neural network

Cite this article

Download Citations
GAO Lei,LIU Zhenkui,ZHANG Haoyu,WEI Xiaoyue,ZHANG Kui. Percussion inspection voice recognition of railway tunnel voids based on ensemble methods[J]. Journal of Vibration and Shock, 2022, 41(14): 58-63

References

[1] 李振,李德建,彭富强.山岭隧道背后多空洞对衬砌结构影响分析[J].铁道科学与工程学报,2016,13(01):138-145.
LI Zhen,LI Dejian,PENG Fuqiang. Analysis of multple voids behind mountain tunnel the lining structure[J]. Journal of Railway Science and Engineering, 2016,13(01):138-145.
[2] Yu-zeng Lyu,Hong-hua Wang,Jun-bo Gong. GPR Detection of Tunnel Lining Cavities and Reverse-time Migration Imaging[J]. Applied Geophysics, 2020 (prepublish).
[3] 覃晖,唐玉,谢雄耀,王峥峥.基于支持向量机的隧道衬砌空洞机器识别方法[J].现代隧道技术,2020,57(02):13-19.
QIN Hui,TANG Yu,XIE Xiongyao, WANG Zhengzheng. Machine Recognition Method of Tunnel Lining Voids Based on SVM Algorithm[J]. Modern Tunnelling Technology,2020,57(02):13-19.
[4] KURAHASHIS,MIKAMIK,KITAMURAT,et al.Demonstration of 25 Hz inspection speed laser remote sensing for internal concrete defects[ J ]. Journal of Applied RemoteSensing,2018,12(1): 1-11.
[5] 王石磊,高岩,齐法琳,等.铁路运营隧道检测技术综述[J].交通运输工程学报,2020,20(05):41-57.
WANG Shi lei, GAO Yan, QI Fa lin, et al. Review on inspection technology of railway operation tunnels[J]. Journal of Traffic and Transportation Engineering, 2020,20(5): 41-57.
[6] 刘思思,谭建平,易子馗.基于MFCC和SVM的车窗电机异常噪声辨识方法研究[J].振动与冲击,2017,36(05):102-107. LIU Sisi, TAN Jianping, YI Zikui.A window motor abnormal noise identification method based on MFCC and SVM [J] .Journal of Vibration and Shock,2017,36(05):102-107.
[7] 王培力,王瑞荣,高鹏,等.MFCC与支持向量机在钱塘江涌潮检测中的应用[J].传感技术学报,2016,29(11):1773-1778.
WANG Peili, WANG Ruirong,GAO Peng,et al. Application of Support Vector Machine and MFCC in the Detection of Qiantang River Tidal Bore[J].Chinese Journal of sensors and Actuators,2016,29(11):1773-1778.
[8] 薛忠军,王佳妮,张肖宁.基于Fisher函数的水泥路面板底脱空判别方法[J].振动与冲击,2013,32(17):155-160.
XUE Zhongjun, WANG Jiani,ZHANG Xiaoning. Discrimina- tion method for cement road slab void based on fisher function[J].Journal of Vibration and Shock, 2013,32(17): 155-160.
[9] 黎煊,赵建,高云,等.基于连续语音识别技术的猪连续咳嗽声识别[J].农业工程学报,2019,35(06):174-180.
Li Xuan, Zhao Jian, Gao Yun, et al. Pig continuous cough sound recognition based on continuous speech recognition technology[J]. Transactions of the Chinese Society of Agricultural Engineering , 2019, 35(6): 174-180.
[10] 郝洪涛,倪凡凡,丁文捷.基于声音信号的托辊故障诊断方法[J].噪声与振动控制,2019,39(03):187-192.
Hao Hongtao, Ni Fanfan, Ding Wenjie. Fault Diagnosis Method of Rollers based on Sound Signals[J]. Noise and vibration control,2019,39(03):187-192.
[11] 李宏全,郭兴明,郑伊能.基于EMD和MFCC的舒张期心杂音的分类识别[J].振动与冲击,2017,36(11):8-13.
LI Hongquan,GUO Xingming,ZHENG Yineng. Classification and recognition of diastolic heart murmurs based on EMD and MFCC[J]. Journal of Vibration and Shock, 2017,36(11):8-13.
[12] Kudakwashe Zvarevashe,Oludayo Olugbara. Ensemble Learning of Hybrid Acoustic Features for Speech Emotion Recognition[J]. Algorithms,2020,13(3).
[13] 李根.基于梯度提升决策树的高速公路交织区汇入模型[J].东南大学学报(自然科学版),2018,48(03):563-567.
Li Gen. Merging model in freeway weaving section based on gradient boosting decision tree[J]. Journal of Southeast University (Natural Science Edition) ,2018,48(03):563-567.
[14] Edson Duarte,Jacques Wainer. Empirical comparison of cross-validation and internal metrics for tuning SVM hyperparameters[J]. Pattern Recognition Letters,2017,88.
[15] 高磊,刘振奎,张昊宇.基于混合PSO-RBF神经网络的铁路隧道岩爆分级预测[J].铁道科学与工程学报,2021,18(02):450-458.
GAO Lei, LIU Zhenkui, ZHANG Haoyu. Prediction of rockburst classification of railway tunnel based on hybrid PSO-RBF neural network[J]. Journal of Railway Science and Engineering,2021,18(02):450-458.
[16] Jin-zhou Feng,Yu Wang,Jin, et al. Comparison between logistic regression and machine learning algorithms on survival prediction of traumatic brain injuries[J]. Journal of Critical Care,2019,54.
PDF(1067 KB)

435

Accesses

0

Citation

Detail

Sections
Recommended

/