基于传感器阵列的机械故障声源定位系统
|
摘要
传统的机械故障诊断系统需要在被监测本体上安装传感器,只能定点定性监测,无法大范围监测,且可移植性差、智能性弱。针对此问题设计了基于四元声学传感器阵列的故障声源定位系统,能实现故障声源的识别及定位。首先,通过声学传感器采集机械设备运行过程中的声音信号,提取其Mel频率倒谱系数。然后,经BP神经网络对声音信号进行识别判断,若为故障声则采用广义互相关算法计算其时间延迟,进行定位。利用该系统对台式钻床空转、正常、磨损、崩刃四种工况进行识别定位测试,实验结果表明,该系统的工况识别准确率可达到89%,故障声源定位精度误差在6cm以内,具有较好的故障声源识别及定位功能。
Traditional mechanical devices fault diagnosis systems need to install sensors on the monitored machine,so that they can only qualitatively monitor in a fixed point. It usually has poor portability and intelligence. A failure sound source localization system based on acoustic sensor array is designed for this problem. Firstly,acoustic sensors are employed to collect the sound signal after the machine is run,the Mel frequency cepstrum coefficient feature vectors of the sound signal are extracted at the same time. Secondly,BP neural network is used to distinguish mechanical failure sounds from the collected acoustic signals. Then the difference of arrival time of the acoustic signals was calculated on the generalized crosscorrelation method to locate the position of mechanical failure. Lastly,performance tests carried out in a bench drill when four modes,the idling sound,normal sound,wear sound and the chipping sound are existed respectively. The experimental results indicate that the working state of bench drill can be recognized with a high accuracy of 89%,and the positioning error is less than 6 cm. This system has good performance for the identification and localization of the mechanical failure sound.
Traditional mechanical devices fault diagnosis systems need to install sensors on the monitored machine,so that they can only qualitatively monitor in a fixed point. It usually has poor portability and intelligence. A failure sound source localization system based on acoustic sensor array is designed for this problem. Firstly,acoustic sensors are employed to collect the sound signal after the machine is run,the Mel frequency cepstrum coefficient feature vectors of the sound signal are extracted at the same time. Secondly,BP neural network is used to distinguish mechanical failure sounds from the collected acoustic signals. Then the difference of arrival time of the acoustic signals was calculated on the generalized crosscorrelation method to locate the position of mechanical failure. Lastly,performance tests carried out in a bench drill when four modes,the idling sound,normal sound,wear sound and the chipping sound are existed respectively. The experimental results indicate that the working state of bench drill can be recognized with a high accuracy of 89%,and the positioning error is less than 6 cm. This system has good performance for the identification and localization of the mechanical failure sound.
引文
[1]夏勇,张振仁,商斌梁.基于图像处理与神经网络的内燃机故障诊断研究[J].内燃机学报,2001(4):356-360.(Xia Yong,Zhang Zhen-ren,Shang Bin-liang.Fault diagnosis for ICE based on image processing and neural networks[J].Transactions of CSICE,2001(4):356-360)
[2]魏维格,董辛旻,韩捷.基于图像识别的齿轮故障诊断方法研究[J].煤矿机械,2016(5):166-169.(Wei Wei-ge,Dong Xin-min,Han Jie.Research of gear fault diagnosis based on image recognition[J].Coal Mine Machine,2016(5):166-169.)
[3]王伟,邓辉文.基于MFCC参数和VQ的说话人识别系统[J].仪器仪表学报,2006(S3):2253-2255.(Wang Wei,Deng Wen-hui.Speaker recognition system using MFCC features and vector quantization[J].Chinese Journal of Scientific Instrument,2006(S3):2253-2255.)
[4]Horner AB,Beauchamp JW,So RHY.Evaluationofmel-bandand MFCC-based error metrics for correspondence to discrimination of spectrally altered musical instrument sounds[J].Journal of the Audio Engineering Society,2011,59(5):290-303.
[5]常飞,乔欣,张申.基于MFCC特征提取的故障预测与评价方法[J].计算机应用研究,2015(6):1716-1719.(Chang Fei,Qiao Xin,Zhang Shen.Method of failure prediction and evaluation based on MFCC feature extraction[J].Application Researchof Computers,2015(6):1716-1719.
[6]禹建丽,卞帅.基于BP神经网络的变压器故障诊断模型[J].系统仿真学报,2014,26(6):1343-1349.(Shu Jian-li,Bian shuai.Fault diagnosis model of transformer based on BPneural network[J].Jourmal of System Simulation,2014,26(6):1343-1349.)
[7]胡耀斌,厉善元,胡良斌.基于神经网络的滚动轴承故障诊断方法的研究[J].机械设计与制造,2012(2):187-189.(Hu Yao-bin,Li Shan-yuan,Hu Liang-bin.Fault diagnosis of rolling bearing based on neural network[J].Machinery Design and Manufacture,2012(2):187-189.)
[8]Valin J M,Michaud F,Rouat J.Robust sound source localization usinga microphone array on a mobile robot[C].//International Conference on Intelligent Robots and Systems.IEEE,2016(2):1228-1233.
[9]居太亮.基于麦克风阵列的声源定位算法研究[D].成都:电子科技大学,2006.(Ju Tai-liang.Research on speech source localization methods based on microphone array[D].Chengdu:University of Electronic Science and Technology of China,2006.)
[10]Pourmohammad A,Ahadi S M.Real time high accuracy 3-D PHAT-based sound source localization using a simple 4-microphone arrangement[J].IEEE Systems Journal,2012,6(3):455-467.
[2]魏维格,董辛旻,韩捷.基于图像识别的齿轮故障诊断方法研究[J].煤矿机械,2016(5):166-169.(Wei Wei-ge,Dong Xin-min,Han Jie.Research of gear fault diagnosis based on image recognition[J].Coal Mine Machine,2016(5):166-169.)
[3]王伟,邓辉文.基于MFCC参数和VQ的说话人识别系统[J].仪器仪表学报,2006(S3):2253-2255.(Wang Wei,Deng Wen-hui.Speaker recognition system using MFCC features and vector quantization[J].Chinese Journal of Scientific Instrument,2006(S3):2253-2255.)
[4]Horner AB,Beauchamp JW,So RHY.Evaluationofmel-bandand MFCC-based error metrics for correspondence to discrimination of spectrally altered musical instrument sounds[J].Journal of the Audio Engineering Society,2011,59(5):290-303.
[5]常飞,乔欣,张申.基于MFCC特征提取的故障预测与评价方法[J].计算机应用研究,2015(6):1716-1719.(Chang Fei,Qiao Xin,Zhang Shen.Method of failure prediction and evaluation based on MFCC feature extraction[J].Application Researchof Computers,2015(6):1716-1719.
[6]禹建丽,卞帅.基于BP神经网络的变压器故障诊断模型[J].系统仿真学报,2014,26(6):1343-1349.(Shu Jian-li,Bian shuai.Fault diagnosis model of transformer based on BPneural network[J].Jourmal of System Simulation,2014,26(6):1343-1349.)
[7]胡耀斌,厉善元,胡良斌.基于神经网络的滚动轴承故障诊断方法的研究[J].机械设计与制造,2012(2):187-189.(Hu Yao-bin,Li Shan-yuan,Hu Liang-bin.Fault diagnosis of rolling bearing based on neural network[J].Machinery Design and Manufacture,2012(2):187-189.)
[8]Valin J M,Michaud F,Rouat J.Robust sound source localization usinga microphone array on a mobile robot[C].//International Conference on Intelligent Robots and Systems.IEEE,2016(2):1228-1233.
[9]居太亮.基于麦克风阵列的声源定位算法研究[D].成都:电子科技大学,2006.(Ju Tai-liang.Research on speech source localization methods based on microphone array[D].Chengdu:University of Electronic Science and Technology of China,2006.)
[10]Pourmohammad A,Ahadi S M.Real time high accuracy 3-D PHAT-based sound source localization using a simple 4-microphone arrangement[J].IEEE Systems Journal,2012,6(3):455-467.