基于深度学习的洗衣机异常音检测

doi:10.6040/j.issn.1672-3961.0.2019.419

摘要/Abstract

摘要：

基于卷积神经网络框架，提出一种洗衣机异音识别模型，根据卷积神经网络显著特征提取能力和平移不变性，学习洗衣机的异音特征，实现生产线洗衣机的异音自动智能识别。给出完整的过程解决训练数据集的建立、数据样本不平衡等问题。提出一种用于数据增强的网络模型——音频深度卷积生成对抗网络解决训练样本的稀缺性问题。该模型对传统的深度卷积生成对抗网络进行改进，以更好地适应工业音频的生成。利用该模型能够对原始数据进行扩展，生成洗衣机异音增强数据集，在该数据集的基础上进行卷积神经网络训练，经测试准确率达到0.999。利用添加背景噪声信号的数据集测试洗衣机异音识别模型的泛化能力，正确识别率达到0.902，表明该网络在识别洗衣机异音方面具有良好的鲁棒性。

关键词: 音频分类, 卷积神经网络, 生成对抗网络, 深度学习

Abstract:

Based on the convolutional neural network (CNN) framework, a model for abnormal sounds recognition of washing machine was proposed. According to the remarkable feature extraction ability and translation invariance of convolutional neural network, the abnormal sound features of washing machines were learned, so as to achieve the purpose of the automatic intelligent recognition of abnormal sounds for washing machines in production line. This method provided a complete process to solve the problems of training datasets establishment and data imbalance. A network model for data augmentation called advanced deep convolution generated adversarial network (ADCGAN)was proposed to solve the problem of training data scarcity. The traditional deep convolution generated adversarial network (DCGAN) model was improved to better adapt to the generation of industrial sounds. This model could be used to extend the original data and generate the abnormal sound augmented datasets of washing machine. The augmented datasets was used to train the convolutional neural network, and the test accuracy reached 0.999. The generalization ability of abnormal sounds recognition model for washing machine network was tested by using the data set with background noise signal added. The correct recognition rate reached 0.902, which indicated that this network had good robustness in recognizing abnormal noises of washing machines.

Key words: audio classification, convolution neural network, generative adversarial networks, deep learning

中图分类号:

TP181

李春阳,李楠,冯涛,王朱贺,马靖凯. 基于深度学习的洗衣机异常音检测[J]. 山东大学学报 (工学版), 2020, 50(2): 108-117.

Chunyang LI,Nan LI,Tao FENG,Zhuhe WANG,Jingkai MA. Abnormal sound detection of washing machines based on deep learning[J]. Journal of Shandong University(Engineering Science), 2020, 50(2): 108-117.

图/表 15

图1

图2

图3

图4

图5

图6

图7

表1

图8

图9

图10

表2

图11

图12

表3

参考文献 31

1	MADAIN M, AL-MOSAIDEN A, AL-KHASSAWENEH M. Fault diagnosis in vehicle engines using sound recognition techniques[C]// Proceedings of the 2010 IEEE Conference on Electro/Information Technology. New York, USA: IEEE, 2010: 1-4.
2	WANG Y, NEVES L, METZE F. Audio-based multi-media event detection using deep recurrent neural networks[C]//the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). New York, USA: IEEE, 2016: 2742-2746.
3	PARASCANDOLO G, HUTTUNEN H, VIRTANEN T. Recurrent neural networks for polyphonic sound event detection in real life recordings[C]//the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). NewYork, USA: IEEE, 2016: 6440-6444.
4	ZHANG H M, MCLOUGHLIN I, SONG Y. Robust sound event recognition using convolutional neural networks[C]//the 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). New York, USA: IEEE, 2016: 559-563.
5	PHAN H, HERTEL L, MAASS M, et al. Robust audio event recognition with 1-max pooling convolutional neural networks[C]//Proceedings of the 17th Annual Conference of the International Speech Communication Association (INTERSPEECH).San Francisco, USA: Interspeech, 2016: 3653-3657.
6	PICZAK K J. Environmental sound classification with convolutional neural networks[C]//the 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP). Boston, USA: IEEE, 2015: 1-6.
7	JEON S, SHIN JW, LEE YJ, et al. Empirical study of drone sound detection in real-life environment with deep neural networks[J]. arXiv: Sound, 2017.https://arxiv.org/abs/1701.05779.
8	SALAMON J, BELLO J. P. Feature learning with deep scattering for urban sound analysis[C]// 25th 2015 23rd European Signal Processing Conference(EUSIP-CO).Nice, France: IEEE, 2015: 724-728.
9	JIA F , LEI Y G , GUO L , et al. A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines[J]. Neurocom-puting, 2017, 272, 619- 628.
10	STOWELL D, CLAYTON D. Acoustic event detection for multiple overlapping similar sources[C]//2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA).New York, USA: IEEE, 2015: 1-5.
11	SADLIER D A , O'CONNOR N E . Event detection in field sports video using audio-visual features and a support vector machine[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2005, 15 (10): 1225- 1233. doi: 10.1109/TCSVT.2005.854237
12	LI B, HE M Y, CHENG X L, et al. Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN[C]//Proceedings of 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). New York, USA: IEEE, 2017: 601-604.
13	XU Y F , ZHANG Y , WANG H G , et al. Deep convolutional neural networks and data augmentation for environmental sound classification[J]. IEEE Signal Processing Letters, 2017, 24 (3): 279- 283.
14	NARASIMHAN R, FERN X L, RAICH R. Simultaneous segmentation and classification of bird song using CNN[C]//2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).New Orleans, USA: IEEE, 2017: 146-150.
15	ANTONIOU A, STORKEY A, EDWARDS H. Data augmentation generative adversarial networks[J]. arXiv: Computer Vision and Pattern Recognition, 2018. https://arxiv.org/abs/1711.04340v3.
16	GOODFELLOW I, POUGET-ABADIE J, MIRZA M. Generative Adversarial Networks[J]. arXiv: Machine Learning, 2014.https://arxiv.org/abs/1406.2661.
17	DENTON E, CHINTALA S, FERGUS R. Deep generative image models using a laplacian pyramid of adversarial networks[C]// 28th International Conference on Neural Information Processing. California, USA: NIPS, 2015: 1486-1494.
18	POUYANFAR S, TAO Y, MOHAN A. Dynamic sampling in convolutional neural networks for imbalanced data classification[C]// 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR). New York, USA: IEEE, 2018: 112-117.
19	RADFORD A, METZ L, CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[J]. arXiv: Computer Vision and Pattern Recognition, 2015. https://arxiv.org/abs/1511.06434.
20	STOWELL D, WOOD M, STYLIANOU Y, et al. Bird detection in audio: A survey and a challenge[C]// 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP). New York, USA: IEEE, 2016: 1-6.
21	ABDEL-HAMID O , MOHAMED A , JIANG H , et al. Convolutional neural networks for speech recognition[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014, 22 (10): 1533- 1545. doi: 10.1109/TASLP.2014.2339736
22	GLOROT X, BORDES A, BENGIO Y. Deep sparse rectifier neural networks[C]// Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS).Ft.Lauderdale, USA: Neural Networks, 2011: 315-323.
23	IOFFE S, SZEGEDY C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]// Proceedings of 32nd International Conference on International Conference on Machine Learning. New York, USA: ACM, 2015: 448-456.
24	SALIMANS T, GOODFELLOW I, ZAREMBA W, et al. Improved techniques for training GANs[J]. arXiv: Neural and Evolutionary Computing, 2016. https://arxiv.org/abs/1606.03498v1.
25	SALAMON J , BELLO J . Deep convolutional neural net-works and data augmentation for environmental sound classification[J]. IEEE Signal Processing Letters, 2017, 24 (3): 279- 283.
26	CUI X D, GOEL V, KINGSBURY B. Data augmentation for deep neural network acoustic modeling[C]// 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). New York, USA: IEEE, 2014: 1469-1477.
27	KONG Q Q, XU Y, MARK D. Joint detection and classification convolutional neural network on weakly labelled bird audio detection[C]// Proceedings of 2017 25th European Signal Processing Conference (EUSIPCO). Kos: Greece, IEEE, 2017: 1749-1753.
28	TANG B , TU Y , ZHANG S Y . Digital signal modulation classification with data augmentation using generative adversarial nets in cognitive radio networks[J]. IEEE Access, 2018, (6): 15713- 15722.
29	MESAROS A, HEITTOLA T, VIRTANEN T. TUT database for acoustic scene classification and sound event detection[C]//Proceedings of 2016 24th European Signal Processing Conference (EUSIPCO).Hungary, Budapest: IEEE, 2016: 1128-1132.
30	ZHENG Q H , YANG M Q , YANG J J . Improvement of generalization ability of deep CNN via implicit regularization in two-stage training process[J]. IEEE Access, 2018, (6): 15844- 15869.
31	MCLOUGHLIN I , ZHANG H M , XIE Z P . Robust sound event classification using deep neural networks[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015, 23 (3): 540- 552. doi: 10.1109/TASLP.2015.2389618

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

学习速率η	Dropout概率系数p	平滑参数	批量大小	迭代次数
0.000 1	0.6	0.25	200	20 000

模型	测试精度
CNN	0.999
RNN	0.687
DNN	0.992
SVM	0.681
LSTM	0.995
MLP	0.994

数据集	测试精度
原始数据集	0.923
加噪数据集(SNR=10 dB)	0.902
增强训练集	0.999

[1]	宋士奇,朴燕,蒋泽新. 基于改进YOLOv3的复杂场景车辆分类与跟踪[J]. 山东大学学报 (工学版), 2020, 50(2): 27-33.
[2]	蔡国永,林强,任凯琪. 基于域对抗网络和BERT的跨领域文本情感分析[J]. 山东大学学报 (工学版), 2020, 50(1): 1-7,20.
[3]	陈德蕾,王成,陈建伟,吴以茵. 基于门控循环单元与主动学习的协同过滤推荐算法[J]. 山东大学学报 (工学版), 2020, 50(1): 21-27,48.
[4]	梁志祥,刘晓明,牟颖,刘玉田. 基于深度学习的新能源爬坡事件预测方法[J]. 山东大学学报 (工学版), 2019, 49(5): 24-28.
[5]	刘玉田, 孙润稼, 王洪涛, 顾雪平. 人工智能在电力系统恢复中的应用综述[J]. 山东大学学报 (工学版), 2019, 49(5): 1-8.
[6]	张继,金翠,王洪元,陈首兵. 基于奇异值分解行人对齐网络的行人重识别[J]. 山东大学学报 (工学版), 2019, 49(5): 91-97.
[7]	万鹏. 基于F-PointNet的3D点云数据目标检测[J]. 山东大学学报 (工学版), 2019, 49(5): 98-104.
[8]	李力钊,蔡国永,潘角. 基于C-GRU的微博谣言事件检测方法[J]. 山东大学学报 (工学版), 2019, 49(2): 102-106, 115.
[9]	侯霄雄,许新征,朱炯,郭燕燕. 基于AlexNet和集成分类器的乳腺癌计算机辅助诊断方法[J]. 山东大学学报 (工学版), 2019, 49(2): 74-79.
[10]	张成彬,赵慧,曹宗钰. 基于深度学习的车身网络KWP2000协议漏洞挖掘[J]. 山东大学学报 (工学版), 2019, 49(2): 17-22.
[11]	权稳稳,林明星. CNN特征与BOF相融合的水下目标识别算法[J]. 山东大学学报 (工学版), 2019, 49(1): 107-113.
[12]	梁蒙蒙,周涛,夏勇,张飞飞,杨健. 基于PSO-ConvK卷积神经网络的肺部肿瘤图像识别[J]. 山东大学学报 (工学版), 2018, 48(5): 77-84.
[13]	张璞,刘畅,王永. 基于特征融合和集成学习的建议语句分类模型[J]. 山东大学学报 (工学版), 2018, 48(5): 47-54.
[14]	何正义,曾宪华,郭姜. 一种集成卷积神经网络和深信网的步态识别与模拟方法[J]. 山东大学学报(工学版), 2018, 48(3): 88-95.
[15]	谢志峰,吴佳萍,马利庄. 基于卷积神经网络的中文财经新闻分类方法[J]. 山东大学学报(工学版), 2018, 48(3): 34-39.