基于△MFCC和KNN的挖掘设备声音识别

Research on Excavation Equipment Recognition Based on △MFCC and KNN Classifier

为保障电缆不受外力破坏,运用声音信号处理和模式识别技术,对挖掘设备声音信号进行识别。主要研究内容有:1声音信号的倒谱域特征参数分析:Mel频率倒谱系数(MFCC),一阶差分Mel频率倒谱系数(△MFCC);2采用KNN的识别算法进行测试。理论分析和实验结果表明,对于4种设备声音信号,△MFCC识别率可达86.69%,满足实际应用需求。提出的挖掘设备声音信号处理及识别算法具有通用性,可用于地下管道监测等领域。

This paper introduces the acoustic signal processing and the pattern recognition technology to identify the excavation equipment.The main research contents are： ①The frequency domain characteristic parameter extraction algorithm of acoustic signal：Mel-Frequency Cepstral Coefficients（MFCC）,the first order difference features of MFCC is △MFCC;② The KNN is employed as the classifier to test the acoustic signal.Theoretical analysis and experimental results show that the△MFCC recognition rate of the four kinds of excavation equipment acoustic signals is 86.69%,which can meet the application demands.