Hot Strip Mill Gearbox Monitoring and Diagnosis Based on Convolutional Neural Networks Using the Pseudo-Labeling Method

被引:2
|
作者
Seo, Myung-Kyo [1 ]
Yun, Won-Young [2 ]
机构
[1] POSCO Pohang Iron & Steel Co Ltd, Pohang 37859, South Korea
[2] Pusan Natl Univ, Dept Ind Engn, Busan 46241, South Korea
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 01期
关键词
hot strip mill; gearbox; fault detection; continuous wavelet transform; convolutional neural networks; pseudo-labeling; deep learning; supervised learning; condition monitoring system; MACHINERY DIAGNOSTICS;
D O I
10.3390/app14010450
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
The steel industry is typical process manufacturing, and the quality and cost of the products can be improved by efficient operation of equipment. This paper proposes an efficient diagnosis and monitoring method for the gearbox, which is a key piece of mechanical equipment in steel manufacturing. In particular, an equipment maintenance plan for stable operation is essential. Therefore, equipment monitoring and diagnosis to prevent unplanned plant shutdowns are important to operate the equipment efficiently and economically. Most plant data collected on-site have no precise information about equipment malfunctions. Therefore, it is difficult to directly apply supervised learning algorithms to diagnose and monitor the equipment with the operational data collected. The purpose of this paper is to propose a pseudo-label method to enable supervised learning for equipment data without labels. Pseudo-normal (PN) and pseudo-abnormal (PA) vibration datasets are defined and labeled to apply classification analysis algorithms to unlabeled equipment data. To find an anomalous state in the equipment based on vibration data, the initial PN vibration dataset is compared with a PA vibration dataset collected over time, and the equipment is monitored for potential failure. Continuous wavelet transform (CWT) is applied to the vibration signals collected to obtain an image dataset, which is then entered into a convolutional neural network (an image classifier) to determine classification accuracy and detect equipment abnormalities. As a result of Steps 1 to 4, abnormal signals have already been detected in the dataset, and alarms and warnings have already been generated. The classification accuracy was over 0.95 at d=4, confirming quantitatively that the status of the equipment had changed significantly. In this way, a catastrophic failure can be avoided by performing a detailed equipment inspection in advance. Lastly, a catastrophic failure occurred in Step 9, and the classification accuracy ranged from 0.95 to 1.0. It was possible to prevent secondary equipment damage, such as motors connected to gearboxes, by identifying catastrophic failures promptly. This case study shows that the proposed procedure gives good results in detecting operation abnormalities of key unit equipment. In the conclusion, further promising topics are discussed.
引用
收藏
页数:19
相关论文
共 50 条
  • [1] Iterative ensemble pseudo-labeling for convolutional neural networks
    Yildiz, Serdar
    Amasyali, Mehmet Fatih
    [J]. SIGMA JOURNAL OF ENGINEERING AND NATURAL SCIENCES-SIGMA MUHENDISLIK VE FEN BILIMLERI DERGISI, 2024, 42 (03): : 862 - 874
  • [2] Multispecies bioacoustic classification using transfer learning of deep convolutional neural networks with pseudo-labeling
    Zhong, Ming
    LeBien, Jack
    Campos-Cerqueira, Marconi
    Dodhia, Rahul
    Ferres, Juan Lavista
    Velev, Julian P.
    Aide, T. Mitchell
    [J]. APPLIED ACOUSTICS, 2020, 166 (166)
  • [3] A Semi-Supervised Learning Method for Spiking Neural Networks Based on Pseudo-Labeling
    Nguyen, Thao N. N.
    Veeravalli, Bharadwaj
    Fong, Xuanyao
    [J]. 2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [4] Gearbox fault diagnosis based on Convolutional Neural Networks
    Chen, Z.
    Li, W.
    Gryllias, K.
    [J]. PROCEEDINGS OF INTERNATIONAL CONFERENCE ON NOISE AND VIBRATION ENGINEERING (ISMA2018) / INTERNATIONAL CONFERENCE ON UNCERTAINTY IN STRUCTURAL DYNAMICS (USD2018), 2018, : 941 - 953
  • [5] Using pseudo-labeling to improve performance of deep neural networks for animal identification
    Ferreira, Rafael E. P.
    Lee, Yong Jae
    Dorea, Joo R. R.
    [J]. SCIENTIFIC REPORTS, 2023, 13 (01):
  • [6] Using pseudo-labeling to improve performance of deep neural networks for animal identification
    Rafael E. P. Ferreira
    Yong Jae Lee
    João R. R. Dórea
    [J]. Scientific Reports, 13 (1)
  • [7] A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox
    Jing, Luyang
    Zhao, Ming
    Li, Pin
    Xu, Xiaoqiang
    [J]. MEASUREMENT, 2017, 111 : 1 - 10
  • [8] SOUND EVENT DETECTION BY CONSISTENCY TRAINING AND PSEUDO-LABELING WITH FEATURE-PYRAMID CONVOLUTIONAL RECURRENT NEURAL NETWORKS
    Koh, Chih-Yuan
    Chen, You-Siang
    Liu, Yi-Wen
    Bai, Mingsian R.
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 376 - 380
  • [9] Gearbox Fault Diagnosis Using Convolutional Neural Networks And Support Vector Machines
    Chen, Zhuyun
    Liu, Chenyu
    Gryllias, Konstantinos
    Li, Weihua
    [J]. 2019 27TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2019,
  • [10] Fault Diagnosis for Planetary Gearbox Based on EMD and Deep Convolutional Neural Networks
    Hu, Niaoqing
    Chen, Huipeng
    Cheng, Zhe
    Zhang, Lun
    Zhang, Yu
    [J]. Jixie Gongcheng Xuebao/Journal of Mechanical Engineering, 2019, 55 (07): : 9 - 18