基于声波信号递归图的鸡蛋裂纹检测
|
摘要
针对基于声波信号的鸡蛋裂纹检测过程中易受到噪音干扰的问题,采集运输线上敲击鸡蛋产生的声波信号,对信号进行递归图分析,采用递归定量分析提取递归图的量化特征参数,用于鸡蛋壳裂纹的分类检测。分别构建基于支持向量机(support vector machine,SVM)、反向传播神经网络模型的鸡蛋裂纹分类检测模型,对300枚鸡蛋进行检测。结果表明,SVM检测模型效果较好;在SVM模型中,完好蛋和裂纹蛋的识别率分别达93.98%和95.52%,效果理想。
Aiming at the problem of noise interference in egg crack detection process,this paper collects the audio vibration signals of the eggs on the transportation.Drawing recurrence plot(RP)of audio vibration signals which are unprocessed and using recurrence quantification analysis(RQA)to extract the quantitative feature parameters of recurrence plot.These quantitative feature parameters are recurrence ratio,determinism,laminarity,entropy and maximum diagonal length.Using these parameters to detect whether eggs are cracked.Results showed that the accuracy of detection and classification of egg with cracks is very-well via a support vector machine(SVM),back propagation neural network(BPNN)models.300 eggs were detected in this study.The results showed that the SVM model was better,in the SVM model,the recognition rate of intact eggs and crack eggs was 93.98%and 95.52%
Aiming at the problem of noise interference in egg crack detection process,this paper collects the audio vibration signals of the eggs on the transportation.Drawing recurrence plot(RP)of audio vibration signals which are unprocessed and using recurrence quantification analysis(RQA)to extract the quantitative feature parameters of recurrence plot.These quantitative feature parameters are recurrence ratio,determinism,laminarity,entropy and maximum diagonal length.Using these parameters to detect whether eggs are cracked.Results showed that the accuracy of detection and classification of egg with cracks is very-well via a support vector machine(SVM),back propagation neural network(BPNN)models.300 eggs were detected in this study.The results showed that the SVM model was better,in the SVM model,the recognition rate of intact eggs and crack eggs was 93.98%and 95.52%
引文
[1]孙力.禽蛋品质在线智能化检测关键技术研究[D].镇江:江苏大学,2013:19-23.
[2]金程.鸡蛋蛋壳裂纹检测技术与装置研发[D].杭州:浙江大学,2015:25-28.
[3]陈红,王巧华,文友先.无损检测技术在禽蛋破损自动检测中的应用[J].食品与机械,2003(5):9-10.
[4]张超,卢伟,丁天华,等.禽蛋品质无损检测的研究现状及其展望[J].食品工业科技,2015,36(18):381-384.
[5]孙力,蔡健荣,李雅琪,等.禽蛋蛋壳品质无损检测方法研究进展[J].中国农业科技导报,2015,17(5):11-17.
[6]王巧华,邓小炎,文友先.鸡蛋敲击响应的奇异性特征与蛋壳裂纹多层检测[J].农业机械学报,2008,39(12):127-131.
[7]潘磊庆,屠康,刘明,等.基于声学响应和BP神经网络检测鸡蛋裂纹[J].南京农业大学学报,2010,33(6):115-118.
[8]王芳,谭佐军,谢静,等.基于声波信号的HHT和Multi-PCA无损检测鸡蛋蛋壳裂纹[J]华中农业大学学报,2017,36(4):102-109.
[9]LIN H,ZHAO J W,CHEN Q S,et al.Eggshell crack detection based on acoustic impulse response and supervised pattern recognition[J].Czech journal of food science,2009,27(6):393-402.
[10]DENG X Y,WANG Q H,CHEN H,et al.Eggshell crack detection using a wavelet-based support vector machine[J].Computers and electronics in agriculture,2010,70(1):135-143.
[11]罗慧,闫思蒙,卢伟,等.基于力-声学特性的鸡蛋微小裂纹在线检测方法[J].农业机械学报,2016,47(11):224-229.
[12]SUN L,CAI J R,LIN H,et al.On-line estimation of eggshell strength based on acoustic impulse response analysis[J].Innovative food science&emerging technologies,2013,18:220-225.
[13]丁天华,卢伟,张超,等.基于Welch法功率谱和广义回归神经网络的禽蛋裂纹辨识[J].食品科学,2015,36(14):156-160.
[14]张超,卢伟,丁为民,等.基于扫频振动的禽蛋裂纹检测方法[J].食品发酵与工业,2015,41(6):181-186.
[15]JIN C,XIE L J,YING Y B.Eggshell crack detection based on the time-domain acoustic signal of rolling eggs on a step-plate[J].Journal of food engineering,2015,153:53-62.
[16]杨冬风,马秀莲.基于分形纹理分析的蛋壳裂纹识别[J].吉林大学学报(工学版),2011,41(增刊1):348-352.
[17]贺静,王树才.基于DSP实时图像分割算法的鸡蛋蛋壳破损检测[J].湖南科技学院学报,2010,31(4):55-58,82.
[18]DEHROUYEH M H,OMID M,AHAMDI H,et al.Grading and quality inspection of defected eggs using machine vision[J].International journal of advanced science and technology,2010,17:23-31.
[19]潘磊庆,屠康,詹歌,等.基于计算机视觉和声学响应信息融合的鸡蛋裂纹检测[J].农业工程学报,2010,26(11):332-337.
[20]吴兰兰,王巧华,祝志慧,等.融合梯度幅值和置信度的鸡蛋裂纹图像检测[J].华中农业大学学报,2016,35(6):136-141.
[21]张淑清,李莎莎,张立国,等.基于微分熵与RQA的电能质量扰动分析[J].仪器仪表学报,2015,36(11):2411-2419.
[22]蒋爱华,周璞,章艺,等.基于相空间重构离心泵基础振动的研究[J].农业工程学报,2014,30(2):56-62.
[23]LITAK G,SYTA A,GAJEWSKI J,et al.Detecting and indentifying non-stationary courses in the ripping head power consumption by recurrence plots[J]Meccanica,2010,45(4):603-608.
[24]AHUJA R K,MAGNANTI T L,ORLIN J B.Network flows:theory,algorithms,and applications[M].New Jersey:Prentice Hall,1993.
[25]胡瑜,陈涛.基于C-C算法的混沌吸引子的相空间重构技术[J].电子测量与仪器学报,2012,26(5):425-430.
[26]MA Z,WEN G,JIANG C.EEMD independent extraction for mixing features of rotating machinery reconstructed in phase space[J].Sensors,2015,15(4):8550-8569.
[27]司莉,毕贵红,魏永刚,等.基于RQA与SVM的声发射信号检测识别方法[J].振动与冲击,2016,35(2):97-103,123.
[28]张淑清,包红燕,李盼,等.基于RQA与GG聚类的滚动轴承故障识别[J].中国机械工程,2015(10):1385-1389.
[29]张丽燕,鲍长春,刘鑫,等.基于非线性音频特征分类的频带扩展方法[J].通信学报,2013,34(8):120-131.
[30]陈超,沈飞,严如强.改进LSSVM迁移学习方法的轴承故障诊断[J].仪器仪表学报,2017,38(1):33-40.
[31]梅劲华.动态禽蛋自动敲击发声装置及蛋壳裂纹声学检测的研究[D].武汉:华中农业大学,2011:9-10.
[2]金程.鸡蛋蛋壳裂纹检测技术与装置研发[D].杭州:浙江大学,2015:25-28.
[3]陈红,王巧华,文友先.无损检测技术在禽蛋破损自动检测中的应用[J].食品与机械,2003(5):9-10.
[4]张超,卢伟,丁天华,等.禽蛋品质无损检测的研究现状及其展望[J].食品工业科技,2015,36(18):381-384.
[5]孙力,蔡健荣,李雅琪,等.禽蛋蛋壳品质无损检测方法研究进展[J].中国农业科技导报,2015,17(5):11-17.
[6]王巧华,邓小炎,文友先.鸡蛋敲击响应的奇异性特征与蛋壳裂纹多层检测[J].农业机械学报,2008,39(12):127-131.
[7]潘磊庆,屠康,刘明,等.基于声学响应和BP神经网络检测鸡蛋裂纹[J].南京农业大学学报,2010,33(6):115-118.
[8]王芳,谭佐军,谢静,等.基于声波信号的HHT和Multi-PCA无损检测鸡蛋蛋壳裂纹[J]华中农业大学学报,2017,36(4):102-109.
[9]LIN H,ZHAO J W,CHEN Q S,et al.Eggshell crack detection based on acoustic impulse response and supervised pattern recognition[J].Czech journal of food science,2009,27(6):393-402.
[10]DENG X Y,WANG Q H,CHEN H,et al.Eggshell crack detection using a wavelet-based support vector machine[J].Computers and electronics in agriculture,2010,70(1):135-143.
[11]罗慧,闫思蒙,卢伟,等.基于力-声学特性的鸡蛋微小裂纹在线检测方法[J].农业机械学报,2016,47(11):224-229.
[12]SUN L,CAI J R,LIN H,et al.On-line estimation of eggshell strength based on acoustic impulse response analysis[J].Innovative food science&emerging technologies,2013,18:220-225.
[13]丁天华,卢伟,张超,等.基于Welch法功率谱和广义回归神经网络的禽蛋裂纹辨识[J].食品科学,2015,36(14):156-160.
[14]张超,卢伟,丁为民,等.基于扫频振动的禽蛋裂纹检测方法[J].食品发酵与工业,2015,41(6):181-186.
[15]JIN C,XIE L J,YING Y B.Eggshell crack detection based on the time-domain acoustic signal of rolling eggs on a step-plate[J].Journal of food engineering,2015,153:53-62.
[16]杨冬风,马秀莲.基于分形纹理分析的蛋壳裂纹识别[J].吉林大学学报(工学版),2011,41(增刊1):348-352.
[17]贺静,王树才.基于DSP实时图像分割算法的鸡蛋蛋壳破损检测[J].湖南科技学院学报,2010,31(4):55-58,82.
[18]DEHROUYEH M H,OMID M,AHAMDI H,et al.Grading and quality inspection of defected eggs using machine vision[J].International journal of advanced science and technology,2010,17:23-31.
[19]潘磊庆,屠康,詹歌,等.基于计算机视觉和声学响应信息融合的鸡蛋裂纹检测[J].农业工程学报,2010,26(11):332-337.
[20]吴兰兰,王巧华,祝志慧,等.融合梯度幅值和置信度的鸡蛋裂纹图像检测[J].华中农业大学学报,2016,35(6):136-141.
[21]张淑清,李莎莎,张立国,等.基于微分熵与RQA的电能质量扰动分析[J].仪器仪表学报,2015,36(11):2411-2419.
[22]蒋爱华,周璞,章艺,等.基于相空间重构离心泵基础振动的研究[J].农业工程学报,2014,30(2):56-62.
[23]LITAK G,SYTA A,GAJEWSKI J,et al.Detecting and indentifying non-stationary courses in the ripping head power consumption by recurrence plots[J]Meccanica,2010,45(4):603-608.
[24]AHUJA R K,MAGNANTI T L,ORLIN J B.Network flows:theory,algorithms,and applications[M].New Jersey:Prentice Hall,1993.
[25]胡瑜,陈涛.基于C-C算法的混沌吸引子的相空间重构技术[J].电子测量与仪器学报,2012,26(5):425-430.
[26]MA Z,WEN G,JIANG C.EEMD independent extraction for mixing features of rotating machinery reconstructed in phase space[J].Sensors,2015,15(4):8550-8569.
[27]司莉,毕贵红,魏永刚,等.基于RQA与SVM的声发射信号检测识别方法[J].振动与冲击,2016,35(2):97-103,123.
[28]张淑清,包红燕,李盼,等.基于RQA与GG聚类的滚动轴承故障识别[J].中国机械工程,2015(10):1385-1389.
[29]张丽燕,鲍长春,刘鑫,等.基于非线性音频特征分类的频带扩展方法[J].通信学报,2013,34(8):120-131.
[30]陈超,沈飞,严如强.改进LSSVM迁移学习方法的轴承故障诊断[J].仪器仪表学报,2017,38(1):33-40.
[31]梅劲华.动态禽蛋自动敲击发声装置及蛋壳裂纹声学检测的研究[D].武汉:华中农业大学,2011:9-10.