基于MFCC和SVM的车窗电机异常噪声辨识方法研究

摘要
图/表
参考文献(17)
相关文章 (15)

全文: PDF (996 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要为提高车窗电机异常噪声特征提取的有效性及分类识别的准确性，提出一种以优化的梅尔频率倒谱系数(Mel Frequency Cepstrum Coefficient, MFCC)为特征值，以支持向量机(Support Vector Machine，SVM)为噪声辨识模型的电机异常噪声辨识方法。在MFCC提取方法基础上，针对频谱泄漏，用Hanning自卷积窗代替Hanning窗，获得优化的MFCC，并将其作为特征值输入到SVM进行异常噪声辨识。为提高SVM判别准确率，采用人工蜂群算法实现SVM参数选择优化。实验结果表明，该方法能够有效判别电机是否存在异响，准确率达到91%。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	刘思思
	谭建平
	易子馗

关键词 ：车窗电机噪声, 梅尔倒谱系数, 支持向量机, 汉宁自卷积窗, 人工蜂群算法

Abstract：In order to improve the efficiency and accuracy of classification and recognition of vehicle window motor abnormal noise，a new method based on the optimal MFCC taken as characteristic values and a SVM taken as the noise identification model was proposed.On the basis of MFCC extraction method,Hanning window was replaced with Hanning self-convolution windows aiming at spectrum leakage,and the optimized MFCC taken as characteristic values were input into SVM to identify abnormal noises.At the same time,the artificial bee colony algorithm was used to optimize the parameters of SVM and improve the accuracy of SVM.The test results showed that the proposed method can effectively distinguish the presence of the abnormal noise of a vehicle window motor,the accuracy reaches 91%.

Key words： vehicle window motor noise MFCC SVM Hanning self-convolution windows artificial bee colony algorithm

收稿日期: 2015-12-23 出版日期: 2017-02-25

引用本文:

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(5): 102-107.
LIU Sisi,TAN Jianping,YI Zikui. A window motor abnormal noiseidentification method based on MFCC and SVM. JOURNAL OF VIBRATION AND SHOCK, 2017, 36(5): 102-107.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2017/V36/I5/102

[1]Y.S.Wang , G.Q.Shen , Y.F.Xing. A sound quality model for objective synthesis evaluation of vehicle interior noise based on artificial neural network[J].Mechanical Systems and SignalProcessing,2014,45(1): 255-266.
[2]Glowacz A. Diagnostics of DC and Induction Motors Based on the Analysis of Acoustic Signals[J]. Measurement Science Review,2014,14(5):257-262.
[3]杨开华. 雨刮电机在线检测与故障诊断系统开发[D].成都:西南交通大学,2011.
Yang Kaihua. The development of on-line detection and fault diagnosis system for vehicle wiper DC motor[D]. Chengdu: Southwest Jiaotong University,2011.
[4] 蒋伟康，严莉. 基于神经网络的电机噪声性能在线检测技术研究[J]. 振动与冲击,2004,23(04):53-57.
Jiang Wei kang, Yan Li. Research on the on-line detection technology of motor noise performance based on Neural Network[J].JOURNAL OF VIBRATION ANDSHOCK,
2004,23(04):53-57.
[5] 赵学智，叶邦彦，陈统坚. 基于自适应小波特征提取一体化神经网络的空调电机振动噪声识别[J]. 振动与冲击,2007, 26(12):160-165.
Zhao Xuezhi,Ye Bangyan, Chen Tong jian. Identification of vibration and noise of air conditioner motor based on adaptive wavelet feature extraction[J].JOURNAL OF VIBRATION AND SHOCK,2007,26(12):160-165.
[6]张伟，蒋伟康.基于心理声学分析的车内异常噪声辨识[J].汽车工程，2003，25（6）：603-605.
Zhang Wei Jiang Wei kang. Abnormal noise identification of vehicle based on psycho acoustic analysis [J]. Automotive Engineering，2003，25（6）：603-605.
[7]李志忠，滕光辉.基于改进MFCC的家禽发声特征提取方法[J].农业工程学报,2008,24（11）：202-205.
Li Zhi zhong , Teng Guanghui. A method for improving the voice characteristics of poultry based on improved MFCC [J]. Transactions of CSAE,2008,24（11）：202-205.
[8] 张文英，郭兴明，翁渐. 改进的高斯混合模型在心音信号分类识别中应用[J]. 振动与冲击,2014,33(06):29-34.
Zhang Wenying ,Guo Xingming,Weng Jian.Application of improved GMM in classification and recognition of heart sound[J].JOURNAL OF VIBRATION AND SHOCK,2014,33(06):29-34.
[9]吕宵云. 基于MFCC和GMM的异常声音识别算法研究[D].成都:西南交通大学,2010.
Lv Xiaoyun. Resarch on abnormal audio recognition algorithm based on MFCC and GMM [D].Chengdu: Southwest Jiaotong University,2010.
[10]滕艺丹.电动剃须刀音频质量检测方法的研究[D].哈尔滨：哈尔滨工业大学，2013.
Teng Yidan. Research on audio quality detection methods of electric shavers [D].Harbin: Harbin Institute Of Technology，2013.
[11] Vapnik V N. The nature of statistical learning theory[M]. New York: Springer-Verlag,1995.
[12] Chappelle O, Vapnik V, Bouquet O, et al. Choosing multiple parameters for support vector machines [J]. Machine Learning,2002, 46(1):131-159.
[13] 高鹏毅. BP神经网络分类器优化技术研究[D].武汉：华中科技大学，2012.
Gao Pengyi. Study on The Optimization of Back propagation Neural Network Classifier[D].Wuhan: Huazhong University of Science and Technology，2012.
[14]彭璐.支持向量机分类算法研究与应用[D].长沙：湖南大学,2007.
Peng Lu. Research on classification algorithm of support vector machine and its application [D].Changsha: Hunan University,2007.
[15]徐晓明.SVM参数寻优及其在分类中的应[D].大连：大连海事大学，2014.
Xu Xiaoming .SVM parameter optimization and its application in the classification[D].Dalian：Dalian Maritime University,2014.
[16] 温和，滕召胜，卿柏元. Hanning自卷积窗及其在谐波分析中的应用[J]. 电工技术学报,2009,24(02):164-169.
Wen He ,Teng Zhaosheng, Qing Boyuan. Hanning Self-Convolution Windows and Its Application to Harmonic Analysis [J].TRANSACTIONS OF CHINA ELECTROTECHNICAL SOCIETY,2009,24(02):164-169.
[17]刘路.基于改进支持向量机和纹理图像分析的旋转机械故障诊断[D].天津：天津大学，2011.
Liu Lu. Rotating machinery fault diagnosis based on improved support vector machine and texture image analysis[D].Tianjin: Tianjin University，2011.