Condition Monitoring of Refrigeration Compressor Using Sound Signal Based on Convolutional Neural Networks

被引：0
|
作者：
Kuendee, Punyisa [1 ]
机构：
[1] Siam Univ, Grad Sch Engn, Dept Engn Management, 38 Phet Kasem Rd, Bangkok, Thailand
来源：
3RD INTERNATIONAL CONFERENCE ON BIG DATA AND INTERNET OF THINGS (BDIOT 2019) | 2018年
关键词：
Refrigeration compressor; Streaming sound data; Internet of things; Machine learning; Convolutional neural networks; MACHINE;
D O I：
10.1145/3361758.3361772
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
In this paper, the condition monitoring of refrigeration compressor used in ice making factory at Chonburi, Thailand is investigated. The streaming sound data collected from designed circuit with IoT technology is proposed. The 6-channel FFT spectrum training dataset with target dataset is introduced and used as input features for machine learning approaches such as ANN and CNN. In preliminary study, the target conditions are classified into 3 classes namely run open valve, run close valve and stop. The classification result demonstrates that the accuracy provided by ANN and CNN methods have similar values at approximately 99% in this study with comparison and evaluation.
引用
收藏
页码：105 / 109
页数：5
相关论文
共 50 条
  • [1] Tool Condition Monitoring for milling process using Convolutional Neural Networks
    Ferrisi, Stefania
    Zangara, Gabriele
    Izquierdo, David Rodriguez
    Lofaro, Danilo
    Guido, Rosita
    Conforti, Domenico
    Ambrogio, Giuseppina
    5TH INTERNATIONAL CONFERENCE ON INDUSTRY 4.0 AND SMART MANUFACTURING, ISM 2023, 2024, 232 : 1607 - 1616
  • [2] Using Convolutional Neural Networks to Classify Audio Signal in Noisy Sound Scenes
    Gubin, M. V.
    2018 GLOBAL SMART INDUSTRY CONFERENCE (GLOSIC), 2018,
  • [3] Sound Classification Using Convolutional Neural Networks
    Jaiswal, Kaustumbh
    Patel, Dhairya Kalpeshbhai
    2018 SEVENTH IEEE INTERNATIONAL CONFERENCE ON CLOUD COMPUTING IN EMERGING MARKETS (CCEM), 2018, : 81 - 84
  • [4] Condition monitoring of ball screw feed drives using convolutional neural networks
    Benker, Maximilian
    Zaeh, Michael F.
    CIRP ANNALS-MANUFACTURING TECHNOLOGY, 2022, 71 (01) : 313 - 316
  • [5] Bolt preload monitoring based on percussion sound signal and convolutional neural network (CNN)
    Yang, Zhuodong
    Huo, Linsheng
    NONDESTRUCTIVE TESTING AND EVALUATION, 2022, 37 (04) : 464 - 481
  • [6] Tool condition monitoring using spectral subtraction and convolutional neural networks in milling process
    Fatemeh Aghazadeh
    Antoine Tahan
    Marc Thomas
    The International Journal of Advanced Manufacturing Technology, 2018, 98 : 3217 - 3227
  • [7] Tool condition monitoring using spectral subtraction and convolutional neural networks in milling process
    Aghazadeh, Fatemeh
    Tahan, Antoine
    Thomas, Marc
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2018, 98 (9-12): : 3217 - 3227
  • [8] Comparison of Signal Processing Techniques for Condition Monitoring Based on Artificial Neural Networks
    Tiboni, M.
    Incerti, G.
    Remino, C.
    Lancini, M.
    ADVANCES IN CONDITION MONITORING OF MACHINERY IN NON-STATIONARY OPERATIONS (CMMNO 2018), 2019, 15 : 179 - 188
  • [9] Assessment of the Condition of Pipelines Using Convolutional Neural Networks
    Vankov, Yuri
    Rumyantsev, Aleksey
    Ziganshin, Shamil
    Politova, Tatyana
    Minyazev, Rinat
    Zagretdinov, Ayrat
    ENERGIES, 2020, 13 (03)
  • [10] Optical Monitoring based on Convolutional Neural Networks
    Tanimura, T.
    Kato, T.
    Watanabe, S.
    Hoshida, T.
    23RD OPTO-ELECTRONICS AND COMMUNICATIONS CONFERENCE (OECC2018), 2018,
12345