摘要
已有的基于音频的机械故障识别方法,大多是使用二维神经网络和音频信号的某个单一特征(如功率谱)进行故障检测,然而单一的音频特征在提取过程中可能会存在关键信息丢失的现象,且往往只能提取音频特征的单一维度(如空间上)信息,这极大限制了现有设备故障音频算法的有效性.为了探究解决上述问题的方法,本文提出一种包含不同音频特征的三维特征构建方式,利用不同的音频特征弥补特征提取过程中的关键信息;并且构建了三维扩张残差网络模型(DR-3DCNN),采用空洞卷积的方式增大模型对全局的关注,同时获取不同尺度的特征信息;充分利用不同特征之间的相关性,建立特征与原始音频数据的深层次关联;最后,采用公开的故障工业机器调查和检查数据集(MIMII)进行实验.实验结果表明,三维特征和DR-3DCNN相组合的方式,其机械故障识别分类效果有了显著提升,分类准确率好于以往单一音频特征的识别算法.
Most existing methods for mechanical fault recognition based on audio signals often use two-dimensional neural networks and a single audio feature(such as power spectrum)for fault detection.However,the extraction of a single audio feature may lead to the loss of critical information during the process.Moreover,it typically captures only a single dimension of audio feature information(such as spatial dimension),greatly limiting the effectiveness of current algorithms for device fault audio analysis.To address these issues,this study proposes a three-dimensional feature construction method that includes various audio features to compensate for the loss of critical information during feature extraction.Furthermore,a three-dimensional dilated residual network model(DR-3DCNN)is constructed,employing dilated convolutions to enhance the model’s global attention and capture features at different scales.By fully exploiting the correlations among different features,a deep-level association between features and original audio data is established.Finally,experiments are conducted using the publicly available industrial machine investigation and inspection dataset(MIMII).The experimental results demonstrate that the combination of three-dimensional features and DR-3DCNN significantly improves the classification performance of mechanical fault recognition,achieving higher classification accuracy than previous single audio feature recognition algorithms.
作者
景源
李孟鼎
JING Yuan;LI Meng-ding(Faculty of Information,Liaoning University,Shenyang 110036,China)
出处
《辽宁大学学报（自然科学版）》
CAS
2024年第3期220-231,共12页
Journal of Liaoning University：Natural Sciences Edition
关键词
机械故障识别
三维卷积网络(3DCNN)
三维特征构建
空洞卷积
mechanical fault identification
three-dimensional convolutional network(3DCNN)
three-dimensional feature construction
dilate convolution
