Identification of gear pitting based on the DCGAN and U2-Net models

PDF(1803 KB)

Journal of Vibration and Shock ›› 2025, Vol. 44 ›› Issue (10) : 301-310.

FAULT DIAGNOSIS ANALYSIS

Identification of gear pitting based on the DCGAN and U2-Net models

LIU Yu*, TAN Qinyi, GU Qiancheng

Author information +

History +

Abstract

Combined with the advantages of the reconstructed gear test bench to obtain the working tooth surface image of the gear online, the method of gear pitting identification based on machine vision is discussed, and the experimental research is carried out. In view of the scarcity of gear pitting data, the Deep Convolutional Generative Adversarial Network (DCGAN) model is used to realize the diversification and high-quality augmentation of the gear pitting samples. Based on the previous research of ourselves, the effective working tooth surface area of the gear is extracted, and the tooth surface tilt correction as well as distortion correction are realized. By introducing the efficient channel attention, the U2-Net model is improved, and the accurate segmentation of the interested region of the gear pitting image is realized. On this basis, by counting the historical pitting rate of gears, a gear pitting identification model based on image signals is constructed, and the gear pitting identification is realized. The results show that the gear pitting identification method based on machine vision technology is feasible, and the recognition accuracy based on DCGAN and U2-Net models can reach 93.56%. The research maybe provides a more direct and reliable method for gear pitting identification, and have certain reference value for the condition monitoring of mechanical equipment.

Key words

Gear / Pitting / Pattern Recognition / DCGAN / U2-Net

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

LIU Yu, TAN Qinyi, GU Qiancheng. Identification of gear pitting based on the DCGAN and U2-Net models[J]. Journal of Vibration and Shock, 2025, 44(10): 301-310

References

[1] Amarnath M , Lee S K . Assessment of surface contact fatigue failure in a spur geared system based on the tribological and vibration parameter analysis[J]. Measurement, 2015, 76:32-44.
[2] Wang L, Zhang Z, Long H, et al. Wind Turbine Gearbox Failure Identification with Deep Neural Networks[J]. IEEE Transactions on Industrial Informatics, 2016, PP(99):1-1.
[3] Liu S, Song C, Zhu C , et al. Investigation on the influence of work holding equipment errors on contact characteristics of face-hobbed hypoid gear[J]. Mechanism & Machine Theory, 2019, 138:95-111.
[4] Feng K., Ji J., Li Y., et al. A novel cyclic-correntropy based indicator for gear wear monitoring[J]. Tribology International, 2022, 171,107528.
[5] Sánchez R V, Lucero P, Vásquez R E, et al. A comparative feature analysis for gear pitting level classification by using acoustic emission, vibration and current signals[J]. IFAC-PapersOnLine, 2018, 51(24): 346-352.
[6] Geröcs A, Korka Z I, Bloju A V, et al. Appraisal of gear pitting severity by vibration signal analysis[C]//IOP Conference Series: Materials Science and Engineering. IOP Publishing, 2020, 997(1): 012042.
[7] 林涛. 基于角加速度检测的齿轮点蚀辨识[D].重庆理工大学,2022.
LIN Tao. Identification of Gear Pitting Corrosion Based on Angular Acceleration Detection[D]. Chongqing University of Technology, 2022.
[8] 傅媛. 多源信息融合的齿轮点蚀诊断[D].重庆理工大学,2023.
FU Yuan. Gear Pitting Diagnosis Based on Multi-source Information Fusion[D]. Chongqing University of Technology, 2023.
[9] 高媛. 基于振动信号的旋转机械故障诊断算法研究[D].湖北工业大学,2021.
GAO Yuan. Research on Fault Diagnosis Algorithm of Rotating Machinery Based on Vibration Signal [D]. Hubei University of Technology,2021.
[10] 张卿.基于机器视觉的齿轮齿面粗糙度检测方法研究[D].湖南大学,2018.
ZHANG Qing. Research on Gear Surface Roughness Measurements Methods Based on Machine Vision [D]. Hunan University,2018.
[11] 魏效玲,崔岳,王晓鹏.基于机器视觉的轮齿缺陷检测研究[J].煤矿机械,2020,41(9):35-37.
WEI Xiao-ling, CUI Yue, WANG Xiao-peng. Research on Gear Tooth Defect Detection Based on Machine Vision [J]. Coal Mine Machinery, 2020,41(9):35-37.
[12] 俞莎莎,朱如鹏,李苗苗,等.基于机器视觉的齿面点蚀面积特征提取的研究[J].机械制造与自动化,2020,49(01):87-90.
YU Sha-sha, ZHU Ru-peng, LI Miao-miao, et al. Research on Extraction of Pitting Area Feature Based on Machine Vision[J]. Coal Mine Machinery, 2020,49(01):87-90.
[13] 李少波,姚勇,桂桂等.基于CNN与多通道声学信号的齿轮故障诊断[J].中国测试, 2019,45(10):1-5..
LI Shao-bo, YAO Yong, GUI Gui, et al. Gear Fault Diagnosis Based on CNN and Multi-channel Acoustic Signals[J]. China Measurement & Test, 2019,45(10):1-5.
[14] 张浩天.基于欠完备齿轮声学信号的故障诊断研究[D].沈阳理工大学,2021.
ZHANG Hao-tian. Fault Diagnosis Based on Incomplete Gear Acoustic Signal[D]. Shenyang Ligong University, 2021.
[15] 白瑞.基于声发射的旋转机械故障诊断[D].沈阳工业大学,2017.
BAI Rui. Rotating Machinery Fault Diagnosis based on Acoustic Emission Technology[D]. Shenyang University of Technology, 2017.
[16] 魏巍宏.基于振动监测和油液分析的齿轮箱多参数故障诊断方法优化研究[D].中国矿业大学,2019.
WEI Wei-hong. Optimization Study on Multi-parameter Fault Diagnosis Method of Gearbox Based on Vibration Monitoring and Oil Analysis [D]. China University of Mining and Technology,2019.
[17] Wu S Q , Li X M. Survey on research progress of generating adversarial networks[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(3): 377-388.
[18] Qin X, Zhang Z, Huang C, et al. U2-Net: Going deeper with nested U-structure for salient object detection[J]. Pattern recognition, 2020, 106: 107404.
[19] 黄鸿, 吕容飞, 陶俊利, 等. 基于改进 U-Net++ 的 CT 影像肺结节分割算法[J]. 光子学报, 2021, 50(2): 73-83.
HUANG Hong, LV Rong-fei, TAO Jun-li, et al. Segmentation of Lung Modules in CT Images Using Improved U-Net++[J]. Acta Photonica Sinica, 2021, 50(2): 73-83.
[20] Woo S, Park J, Lee J Y, et al. Cbam: Convolutional block attention module[C]//Proceedings of the European conference on computer vision. 2018: 3-19.
[21] Chetia R, Boruah S M B, Sahu P P. Quantum image edge detection using improved Sobel mask based on NEQR[J]. Quantum Information Processing, 2021, 20(1): 21
[22] 王志文. 基于树状循环生成器和注意力Deeplabv3的齿轮点蚀视觉测量研究[D].重庆大学,2021.
WANG Zhi-wen. Research on Visual Measurement of gear Pitting Based on Tree Cycle Generator and Attention Deeplabv3[D]. Chongqing University,2021.
[23] Li H, Zeng C K, Zhao P J, et al. Real-time detection method of gear contact fatigue pitting based on machine vision [J], Applied Optics, 2022, 61(13): 3609-3618.
[24] Illingworth J, Kittler J. A survey of the Hough transform[J]. Computer vision, graphics, and image processing, 1988, 44(1): 87-116.
[25] Nazaroff W W. Radon transport from soil to air[J]. Reviews of geophysics, 1992, 30(2): 137-160.
[26] Sentz K, Ferson S. Combination of evidence in Dempster-Shafer theory[J].Engineering, Mathematics， 2002.