Abstract
The compressor is the core component of refrigeration equipment. This paper proposeed a method of anomaly vibration detection of refrigeration compressor based on autoencoder technology in order to solve the quality control problems in the production process of refrigeration compressor. The principle and process of anomaly vibration detection were given, based on autoencoder and the acquisition method of compressor vibration signal sample. The relationship was studied between the mean square error of the input and output of the autoencoder and the distribution of the signal samples. By means of the autoencoder model, the decision fundament of the abnormal vibration of the compressor was given. From two aspects of the autoencoder parameters and the number of training samples, this paper discussed the influence of three kind of autoencoder parameters including calculation iteration number, hidden layer number and training sample number on the detection accuracy. The study finds that the number of iterations and hidden layers has an impact on the detection accuracy, but no obvious law; the number of the training samples has a significant impact on the detection accuracy. It is an effective method to improve the accuracy of autoencoder to increase the number of training samples. The autoencoder can be used to detect anomaly vibration of refrigeration compressor.
Publication Date
4-28-2021
First Page
120
Last Page
123,128
DOI
10.13652/j.issn.1003-5788.2021.04.022
Recommended Citation
Yuan-tao, WANG; Tao, FENG; Qia, SUN; Jing, WANG; and Yi-han, WANG
(2021)
"Anomaly vibration detection method of the refrigeration compressor based on autoencoder,"
Food and Machinery: Vol. 37:
Iss.
4, Article 22.
DOI: 10.13652/j.issn.1003-5788.2021.04.022
Available at:
https://www.ifoodmm.cn/journal/vol37/iss4/22
References
[1] 谢雪松, 谢路杨, 都腾飞, 等. 基于改进型CEEMDAN和RBF神经网络的往复式压缩机阀片故障诊断研究[J]. 机械工程师, 2020(11): 90-92.
[2] 肖军, 舒悦, 谢传东, 等. 基于二叉树支持向量机的往复压缩机气阀故障诊断方法[J]. 流体机械, 2020, 48(10): 48-53.
[3] 裴悦琨, 连明月, 姜艳超, 等. 基于机器视觉的樱桃缺陷检测与识别[J]. 食品与机械, 2019, 35(12): 137-140.
[4] 杨志锐, 郑宏, 郭中原, 等. 基于网中网卷积神经网络的红枣缺陷检测[J]. 食品与机械, 2020, 36(2): 140-145.
[5] 程华利, 樊可清. 异音检测的机器学习方法及其在电机质检中的应用[J]. 测控技术, 2015, 34(4): 55-58, 62.
[6] 温浩, 刘力源. 基于小波包和SVM一类学习在电机异音检测中的应用[J]. 测控技术, 2015, 34(2): 35-38.
[7] 张新, 郑燕萍, AUGEIX Antoine, 等. 基于小波包分解与机器学习的汽车调光电机异音识别[J]. 森林工程, 2019, 35(1): 59-63.
[8] 常嘉树. 汽车零部件异音异响信号检测系统[J]. 国外电子测量技术, 2017, 36(9): 6-8.
[9] 李春阳, 李楠, 冯涛, 等. 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.
[10] YANG Bo-suk, HWANG Won-woo, KIM Dong-jo, et al. Condition classification of small reciprocating compressor for refrigerators using artificial neural networks and support vector machines[J]. Elsevier Ltd, 2005, 19(2): 371-390.
[11] HE Chang-bo, LI Hong-kun, LI Zhi-xiong, et al. An improved bistable stochastic resonance and its application on weak fault characteristic identification of centrifugal compressor blades[J]. Journal of Sound and Vibration, 2019, 442: 677-697.
[12] LI Ying, WANG Jin-dong, ZHAO Hai-yang, et al. Fault diagnosis method based on modified multiscale entropy and global distance evaluation for the valve fault of a reciprocating compressor[J]. Strojniski Vestnik-Journal of Mechanical Engineering, 2019, 65(2): 123-135.