小波包增强稀疏表征分类的管道堵塞故障识别
|
摘要
针对在声学主动检测埋地排水管道故障的过程中,不同程度堵塞信号及常规管道部件三通件信号等难以有效区分的问题,提出小波包增强稀疏表征分类(SRC)的堵塞故障识别方法。该方法首先对管道中采集的声学信号进行小波包分解,提取不同尺度分量的多个时频特征参数并筛选出更为有效的特征值,构建能全面表征不同程度堵塞与管道三通件信号的特征向量,然后利用特征向量分别构造字典和稀疏表征分类器。实验结果表明,该方法在少量样本情况下仍能有效识别排水管道内不同程度的堵塞故障及管道三通件,具有一定的工程实用价值。
Regarding to the active detection of blocking status of buried drainage pipeline, it is difficult to distinguish the different degrees of blockage and to eliminate the effects from the pipe components such as lateral connection, a novel method to identify the blockage using wavelet packet enhanced sparse representation classification(SRC) is proposed in this paper. Firstly, the acoustic signals collected in the pipeline are decomposed by wavelet packet, then multiple time frequency characteristic parameters are extracted from each scale component and more effective features are screened out. Secondly, the feature vectors that can effectively represent the signals are used to construct the dictionary and the sparse representation classifier. The experimental results have shown that the method can effectively identify the different degrees of blocking status and lateral connection in the drainage pipeline under a small number of samples, which has certain practical value for engineering applications.
Regarding to the active detection of blocking status of buried drainage pipeline, it is difficult to distinguish the different degrees of blockage and to eliminate the effects from the pipe components such as lateral connection, a novel method to identify the blockage using wavelet packet enhanced sparse representation classification(SRC) is proposed in this paper. Firstly, the acoustic signals collected in the pipeline are decomposed by wavelet packet, then multiple time frequency characteristic parameters are extracted from each scale component and more effective features are screened out. Secondly, the feature vectors that can effectively represent the signals are used to construct the dictionary and the sparse representation classifier. The experimental results have shown that the method can effectively identify the different degrees of blocking status and lateral connection in the drainage pipeline under a small number of samples, which has certain practical value for engineering applications.
引文
[1] HAO T,ROGERS C D F,METJE N,et al.Condition assessment of the buried utility service infrastructure [J].Tunnelling & Underground Space Technology Incorporating Trenchless Technology Research,2012(28):331-344.
[2] DATTA S,SARKAR S.A review on different pipeline fault detection methods[J].Journal of Loss Prevention in the Process Industries,2016(41):97-106.
[3] 张琛,赵荣珍,邓林峰.基于变分模态分解奇异值熵的滚动轴承微弱故障辨识方法[J].振动与冲击,2018,37(21):87-91,107.ZHANG CH,ZHAO R ZH,DENG L F.A weak fault identification method for rolling bearings based on variational mode decomposition singular value entropy[J].Journal of Vibration and Shock,2018,37(21):87-91,107.
[4] 石明江,罗仁泽,付元华.小波和能量特征提取的旋转机械故障诊断方法[J].电子测量与仪器学报,2015,29(8):1114-1120.SHI M J,LUO R Z,FU Y H.Rotating machinery fault diagnosis method based on wavelet and energy feature extraction[J].Journal of Electronic Measurement and Instrumentation,2015,29(8):1114-1120.
[5] 唐贵基,邓飞跃.基于改进谐波小波包分解的滚动轴承复合故障特征分离方法[J].仪器仪表学报,2015,36(1):143-151.TANG G J,DENG F Y.Combined fault feature separation method for rolling bearings based on improved harmonic wavelet packet decomposition[J].Chinese Journal of Scientific Instrument,2015,36(1):143-151.
[6] WRIGHT J,GANESH A,ZHOU Z,et al.Demo:Robust face recognition via sparse representation [C].IEEE International Conference on Automatic Face & Gesture Recognition,2009:1-2.
[7] 朱启兵,杨宝,黄敏.基于核映射稀疏表示分类的轴承故障诊断[J].振动与冲击,2013,32(11):30-34.ZHU Q B,YANG B,HUANG M.Bearing fault diagnosis based on sparse representation of kernel mapping[J].Journal of Vibration & Shock,2013,32(11):30-34.
[8] 杨清山,郭成安,金明录.基于Gabor多通道加权优化与稀疏表征的人脸识别方法[J].电子与信息学报,2011,33(7):1618-1624.YANG Q SH,GUO CH AN,JIN M L.Face recognition based on Gabor multichannel weighted optimization and sparse representation [J].Journal of Electronics & Information Technology,2011,33(7):1618-1624.
[9] KHAN M S.A stochastic based approach to model acoustic propagation in pipes with laterals[C].Southeastcon,IEEE,2017:1-8.
[10] 颜世玉,刘冲,赵海滨,等.基于小波包分解的意识脑电特征提取[J].仪器仪表学报,2012,33(8):1748-1752.YAN S Y,LIU CH,ZHAO H B,et al.Feature extraction of consciousness EEG based on wavelet packet decomposition[J].Chinese Journal of Scientific Instrument,2012,33(8):1748-1752.
[11] MASSARI C,YEH T C J,FERRANTE M,et al.A stochastic tool for determining the presence of partial blockages in viscoelastic pipelines:First experimental results [J].Procedia Engineering,2014(70):1112-1120.
[12] 何志坚,周志雄.基于ELMD的样本熵及Boosting-SVM的滚动轴承故障诊断[J].振动与冲击,2016,35(18):190-195.HE ZH J,ZHOU ZH X.The Sample entropy based on ELMD and fault diagnosis of rolling bearing based on boosting-SVM[J].Journal of Vibration & Shock,2016,35(18):190-195.
[13] ZUREK S,GUZIK P,PAWLAK S,et al.On the relation between correlation dimension,approximate entropy and sample entropy parameters,and a fast algorithm for their calculation[J].Physica A Statistical Mechanics & Its Applications,2012,391(24):6601-6610.
[14] 施燕,陈荣荣,刘亚帆,等.具有显著提高准确率和鲁棒性的基于极限学习机的流量分类[J].电子测量技术,2016,39(8):53-57.SHI Y,CHEN R R,LIU Y F,et al.Traffic classification based on extreme learning machine with significantly improved accuracy and robustness[J].Electronic Measurement Technology,2016,39(8):53-57.
[15] 殷贤华,王宁,陈晶溪.基于太赫兹时域光谱系统的橡胶分类识别[J].国外电子测量技术,2016,35(6):19-23.YIN X H,WANG N,CHEN J X.Rubber classification identification based on terahertz time-domain spectroscopy system[J].Foreign Electronic Measurement Technology,2016,35(6):19-23.
[2] DATTA S,SARKAR S.A review on different pipeline fault detection methods[J].Journal of Loss Prevention in the Process Industries,2016(41):97-106.
[3] 张琛,赵荣珍,邓林峰.基于变分模态分解奇异值熵的滚动轴承微弱故障辨识方法[J].振动与冲击,2018,37(21):87-91,107.ZHANG CH,ZHAO R ZH,DENG L F.A weak fault identification method for rolling bearings based on variational mode decomposition singular value entropy[J].Journal of Vibration and Shock,2018,37(21):87-91,107.
[4] 石明江,罗仁泽,付元华.小波和能量特征提取的旋转机械故障诊断方法[J].电子测量与仪器学报,2015,29(8):1114-1120.SHI M J,LUO R Z,FU Y H.Rotating machinery fault diagnosis method based on wavelet and energy feature extraction[J].Journal of Electronic Measurement and Instrumentation,2015,29(8):1114-1120.
[5] 唐贵基,邓飞跃.基于改进谐波小波包分解的滚动轴承复合故障特征分离方法[J].仪器仪表学报,2015,36(1):143-151.TANG G J,DENG F Y.Combined fault feature separation method for rolling bearings based on improved harmonic wavelet packet decomposition[J].Chinese Journal of Scientific Instrument,2015,36(1):143-151.
[6] WRIGHT J,GANESH A,ZHOU Z,et al.Demo:Robust face recognition via sparse representation [C].IEEE International Conference on Automatic Face & Gesture Recognition,2009:1-2.
[7] 朱启兵,杨宝,黄敏.基于核映射稀疏表示分类的轴承故障诊断[J].振动与冲击,2013,32(11):30-34.ZHU Q B,YANG B,HUANG M.Bearing fault diagnosis based on sparse representation of kernel mapping[J].Journal of Vibration & Shock,2013,32(11):30-34.
[8] 杨清山,郭成安,金明录.基于Gabor多通道加权优化与稀疏表征的人脸识别方法[J].电子与信息学报,2011,33(7):1618-1624.YANG Q SH,GUO CH AN,JIN M L.Face recognition based on Gabor multichannel weighted optimization and sparse representation [J].Journal of Electronics & Information Technology,2011,33(7):1618-1624.
[9] KHAN M S.A stochastic based approach to model acoustic propagation in pipes with laterals[C].Southeastcon,IEEE,2017:1-8.
[10] 颜世玉,刘冲,赵海滨,等.基于小波包分解的意识脑电特征提取[J].仪器仪表学报,2012,33(8):1748-1752.YAN S Y,LIU CH,ZHAO H B,et al.Feature extraction of consciousness EEG based on wavelet packet decomposition[J].Chinese Journal of Scientific Instrument,2012,33(8):1748-1752.
[11] MASSARI C,YEH T C J,FERRANTE M,et al.A stochastic tool for determining the presence of partial blockages in viscoelastic pipelines:First experimental results [J].Procedia Engineering,2014(70):1112-1120.
[12] 何志坚,周志雄.基于ELMD的样本熵及Boosting-SVM的滚动轴承故障诊断[J].振动与冲击,2016,35(18):190-195.HE ZH J,ZHOU ZH X.The Sample entropy based on ELMD and fault diagnosis of rolling bearing based on boosting-SVM[J].Journal of Vibration & Shock,2016,35(18):190-195.
[13] ZUREK S,GUZIK P,PAWLAK S,et al.On the relation between correlation dimension,approximate entropy and sample entropy parameters,and a fast algorithm for their calculation[J].Physica A Statistical Mechanics & Its Applications,2012,391(24):6601-6610.
[14] 施燕,陈荣荣,刘亚帆,等.具有显著提高准确率和鲁棒性的基于极限学习机的流量分类[J].电子测量技术,2016,39(8):53-57.SHI Y,CHEN R R,LIU Y F,et al.Traffic classification based on extreme learning machine with significantly improved accuracy and robustness[J].Electronic Measurement Technology,2016,39(8):53-57.
[15] 殷贤华,王宁,陈晶溪.基于太赫兹时域光谱系统的橡胶分类识别[J].国外电子测量技术,2016,35(6):19-23.YIN X H,WANG N,CHEN J X.Rubber classification identification based on terahertz time-domain spectroscopy system[J].Foreign Electronic Measurement Technology,2016,35(6):19-23.