Detection and Monitoring of Pitting Progression on Gear Tooth Flank Using Deep Learning
Source abstract
Abstract
Gears are essential machine elements that are exposed to heavy loads. In some cases, gearboxes are critical elements since they serve as machine drivers that must operate almost every day for a more extended period, such as years or even tens of years. Any interruption due to gear failures can cause significant losses, and therefore it is necessary to have a monitoring system that will ensure proper operation. Tooth surface damage is a common occurrence in operating gears. One of the most common types of damage to teeth surfaces is pitting. It is necessary for normal gear operations to regularly determine the occurrence and span of a damaged tooth surface caused by pitting. In this paper, we propose a machine vision system as part of the inspection process for detecting pitting and monitoring its progression. The implemented inspection system uses a faster R-CNN network to identify and position pitting on a specific tooth, which enables monitoring. Prediction confidence values of pitting damage detection are between 99.5–99.9%, while prediction confidence values for teeth recognized as crucial for monitoring are between 97–99%.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Gear and Bearing Dynamics Analysis · Advanced machining processes and optimization · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Mechanical Engineering, University of Niš, 18000 Niš, Serbia
Faculty of Security Studies, Educons University, 11000 Belgrade, Serbia
Department of Mechatronics and Machine Dynamics, Technical University Cluj-Napoca, 400114 Cluj-Napoca, Romania
References (35)
Show source-provided references
1. A machine vision algorithm for quality control inspection of gears10.1007/s00170-019-04426-2 ↗
2. Geometry optimization by FEM simulation of the automatic changing gear10.31181/rme200101199p ↗
3. The Selection of Optimal Reversible Two-Speed Planetary Gear Trains for Machine Tool Gearboxes
4. Optimization of two-speed planetary gearbox with brakes on single shafts10.31181/rme2001280122m ↗
5. Liu, H., Liu, H., Zhu, C., and Zhou, Y. (2019). A Review on Micropitting Studies of Steel Gears. Coatings, 9.10.3390/coatings9010042 ↗
6. Miltenović, A., Banić, M., Tanasković, J., Stefanović-Marinović, J., Rangelov, D., and Perić, M. (2022). Wear load capacity of crossed helical gears. Facta Univ. Ser. Mech. Eng., online first.
7. Experimental failure analysis of S-polymer gears10.1016/j.engfailanal.2020.104496 ↗
8. Prediction of Temperature Distribution in the Worm Gear Meshing
9. Pitting detection in worm gearboxes with vibration analysis10.1016/j.engfailanal.2014.04.028 ↗
10. Early Detection of Industrial-Scale Gear Tooth Surface Pitting Using Vibration Analysis10.1007/s11668-020-00874-1 ↗
11. In Situ Monitoring of Pitting Corrosion on Stainless Steel with Digital Holographic Surface Imaging10.1149/2.0061911jes ↗
12. Li, J., Li, X., He, D., and Qu, Y. (2019). A Novel Method for Early Gear Pitting Fault Diagnosis Using Stacked SAE and GBRBM. Sensors, 19.10.3390/s19040758 ↗
13. Li, X., Li, J., Qu, Y., and He, D. (2019). Gear Pitting Fault Diagnosis Using Integrated CNN and GRU Network with Both Vibration and Acoustic Emission Signals. Appl. Sci., 9.10.3390/app9040768 ↗
14. Gear pitting fault diagnosis using disentangled features from unsupervised deep learning
15. Spur Gear Tooth Pitting Propagation Assessment Using Model-based Analysis10.1007/s10033-017-0196-z ↗
16. Classification of gear pitting damage using vibration measurements10.1515/teme-2021-0010 ↗
17. Experimental Study on the Pitting Detection Capabilities for Spur Gears Using Acoustic Emission and Vibration Analysis Methods
18. The Suggestion of the Macrophoto Method for the Evaluation of the Gear Damages by Pitting
19. Allam, A., Moussa, M., Tarry, C., and Veres, M. (2021). Detecting Teeth Defects on Automotive Gears Using Deep Learning. Sensors, 21.10.3390/s21248480 ↗
20. Vision measurement of gear pitting based on DCGAN and U-Net10.1007/s12206-021-0601-5 ↗
21. Real-time detection method of gear contact fatigue pitting based on machine vision10.1364/AO.451861 ↗
22. Multipath Fusion Mask R-CNN with Double Attention and Its Application into Gear Pitting Detection10.1109/TIM.2021.3049276 ↗
23. Xi, D., Qin, Y., and Wang, Y. (2020). Vision Measurement of Gear Pitting Under Different Scenes by Deep Mask R-CNN. Sensors, 20.10.3390/s20154298 ↗
24. Xi, D., Qin, Y., and Wang, S. (2021). YDRSNet: An integrated Yolov5-Deeplabv3 + real-time segmentation network for gear pitting measurement. J. Intell. Manuf., 1–15.10.1007/s10845-021-01876-y ↗
25. Vullo, V. (2020). Gears—Volume 2: Analysis of Load Carrying Capacity and Strength Design, Springer Nature Switzerland AG.10.1007/978-3-030-38632-0 ↗
26. Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., and Girshick, R. (2022, February 25). Detectron 2. Available online: https://github.com/facebookresearch/detectron2.
27. Ren, S., He, K., Girshick, R., and Sun, J. (2016). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. arXiv.10.1109/TPAMI.2016.2577031 ↗
28. (2022, March 15). Hasty. Available online: https://hasty.ai.
29. Rehman, S.U., Tu, S., Rehman, O.U., Huang, Y., Magurawalage, C.M.S., and Chang, C.-C. (2018). Optimization of CNN through Novel Training Strategy for Visual Classification Problems. Entropy, 20.10.3390/e20040290 ↗
30. Effects of Hyper-parameters and Dataset on CNN Training
31. Hsia, C.-H., Chang, T.-H.W., Chiang, C.-Y., and Chan, H.-T. (2022). Mask R-CNN with New Data Augmentation Features for Smart Detection of Retail Products. Appl. Sci., 12.10.3390/app12062902 ↗
32. Object Detection classifier using Faster R-CNN Algorithm
33. Chen, P., and Elangovan, V. (2020). Object sorting using faster r-cnn. arXiv.10.5121/ijaia.2020.11603 ↗
34. Optimization technique combined with deep learning method for teeth recognition in dental panoramic radiographs10.1038/s41598-020-75887-9 ↗
35. Alganci, U., Soydas, M., and Sertel, E. (2020). Comparative Research on Deep Learning Approaches for Airplane Detection from Very High-Resolution Satellite Images. Remote Sens., 12.10.3390/rs12030458 ↗