电子测量与仪器学报

周静雷,贺家琛,崔琳.CNN-GRU 和 SSA-VMD 在扬声器异常声分类中的应用[J].电子测量与仪器学报,2023,37(3):161-168

CNN-GRU 和 SSA-VMD 在扬声器异常声分类中的应用

Application of CNN-GRU and SSA-VMD in loudspeaker abnormal sound classification

DOI：

中文关键词: 扬声器异常声变分模态分解卷积神经网络门控循环单元麻雀搜索算法

英文关键词:loudspeaker abnormal sound variational mode decomposition convolutional neural networks gated recurrent unit sparrow search algorithm

基金项目:国家自然科学基金青年项目(61901347)、陕西省教育厅科技计划项目(18JK0342)资助

作者	单位
周静雷	1.西安工程大学电子信息学院
贺家琛	1.西安工程大学电子信息学院
崔琳	1.西安工程大学电子信息学院

Author	Institution
Zhou Jinglei	1.College of Electronics and Information,Xi′an Polytechnic University
He Jiachen	1.College of Electronics and Information,Xi′an Polytechnic University
Cui Lin	1.College of Electronics and Information,Xi′an Polytechnic University

摘要点击次数: 706

全文下载次数: 563

中文摘要:

为了提高扬声器异常声分类的平均准确率,提出用卷积神经网络加门控循环单元(convolutional neural network plus gated recurrent unit, CNN-GRU) 和麻雀搜索算法优化变分模态分解 ( sparrow search algorithm optimization variational modal decomposition,SSA-VMD)模型进行扬声器异常声分类。在特征提取方面,用 SSA-VMD 模型,确定 VMD 中二次惩罚因子(α)和模态分解数(k)的最优取值问题,借此提高特征提取精度,减少提取时间,最后再利用 VMD 提取扬声器响应信号的特征;在分类网络方面,用 CNN-GRU 网络来进行扬声器异常声分类,以 CNN 为基础特征提取网络,再用 GRU 网络进行更深层特征提取, 达到提高扬声器平均分类准确率的目标。试验结果表明,经 SSA-VMD 模型优化参数后,VMD 可以更有效提取特征,且分解时间缩短 59. 8%;CNN-GRU 模型具有更高和更稳定的识别率,其平均分类准确率为 99. 2%。

英文摘要:

In order to improve the average accuracy of loudspeaker abnormal sound classification, a convolutional neural network plus gated current unit (CNN-GRU) and sparrow search algorithm optimization variational modal decomposition ( SSA-VMD) model was proposed to classify loudspeaker abnormal sound. In the aspect of feature extraction, the SSA-VMD model was used to determine the optimal value of the second penalty factor (α) and modal decomposition number (k) in VMD, so as to improve the accuracy of feature extraction and reduce the extraction time. Finally, the VMD was used to extract the characteristics of the loudspeaker response signal. In terms of classification network, the CNN-GRU network was used to classify the abnormal sound of loudspeakers, the CNN-based feature extraction network was used, and the GRU network was used for deeper feature extraction to achieve the goal of improving the average classification accuracy of loudspeakers. The experimental results show that after optimizing the parameters of SSA-VMD model, VMD can extract features more effectively, and the decomposition time was reduced by 59. 8%. The CNN-GRU model has a higher and more stable recognition rate, with an average classification accuracy of 99. 2%.

查看全文查看/发表评论下载PDF阅读器