A Vision-Based Approach for Precise Wear Evaluation of Abrasive Belts with Irregular Morphology in Flexible Grinding
Source abstract
Abstract
Abrasive belt wear has an important impact on the dimensional accuracy and surface quality of parts. Accurate quantitative measurement of abrasive belt wear is an important basis for optimizing grinding process parameters, but also a very challenging task for abrasive belts with randomly distributed abrasive particles. In this paper, a quantitative method of determining wear state based on the life cycle surface images of the abrasive belt is proposed to evaluate its material removal ability in the grinding process. For blunted abrasive particles with extremely irregular shapes, TransUNet with a hybrid encoding of a CNN and transformer is adopted to obtain strong representation of complex features and high-precision segmentation boundaries. Three other U-net-based semantic segmentation networks are compared to prove the effectiveness of the trained TransUNet model. The number and area of blunted abrasive particles were calculated by connected domain and statistical methods. The proportion of worn abrasive particles and the wear area ratio when the service life of the abrasive belt is exhausted are about 74.29% and 3.06%, respectively.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Surface Polishing Techniques · Advanced machining processes and optimization · Erosion and Abrasive Machining
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mechanical and Precision Instrumental Engineering, Xi’an University of Technology, Xi’an 710048, China
Funding
National Natural Science Foundation of China · Natural Science Foundation of Shaanxi Province · State Market Regulation
References (27)
Show source-provided references
1. Research on robotic belt grinding method of blisk for obtaining high surface integrity features with variable inclination angle force control10.1016/j.rcim.2023.102680 ↗
2. A review of surface quality control technology for robotic abrasive belt grinding of aero-engine blades10.1016/j.measurement.2023.113381 ↗
3. Effects of feed direction on material removal behavior in belt grinding of titanium alloys10.1016/j.jmapro.2023.07.078 ↗
4. Robotic compliant grinding of curved parts based on a designed active force-controlled end-effector with optimized series elastic component10.1016/j.rcim.2023.102646 ↗
5. Grain shape-protrusion-based modeling and analysis of material removal in robotic belt grinding10.1016/j.jmapro.2023.12.055 ↗
6. Modeling and analysis of material removal depth contour for curved-surfaces abrasive belt grinding
7. Analysis of abrasive grain size effect of abrasive belt on material removal performance of GCr15 bearing steel10.1016/j.triboint.2022.107536 ↗
8. Wear evolution of electroplated diamond abrasive belt and corresponding surface integrity of Inconel 718 during grinding10.1016/j.triboint.2022.107972 ↗
9. Wear behavior of alumina abrasive belt and its effect on surface integrity of titanium alloy during conventional and creep-feed grinding10.1016/j.wear.2022.204581 ↗
10. An online belt wear monitoring method for abrasive belt grinding under varying grinding parameters10.1016/j.jmapro.2019.12.034 ↗
11. A deep transfer learning method for monitoring the wear of abrasive belts with a small sample dataset10.1016/j.jmapro.2021.12.022 ↗
12. A novel sound-based belt condition monitoring method for robotic grinding using optimally pruned extreme learning machine
13. Acoustic signal-based tool condition monitoring in belt grinding of nickel-based superalloys using RF classifier and MLR algorithm10.1007/s00170-018-2270-9 ↗
14. In-process tool condition monitoring in compliant abrasive belt grinding process using support vector machine and genetic algorithm10.1016/j.jmapro.2017.11.014 ↗
15. The effect of abrasive grain’s wear and contact conditions on surface texture in belt finishing10.1016/j.wear.2006.11.037 ↗
16. Comprehensive investigation on mechanisms of dry belt grinding on AISI52100 hardened steel10.1016/j.triboint.2018.01.019 ↗
17. Abrasiveness properties assessment of coated abrasives for precision belt grinding10.1016/j.surfcoat.2008.08.058 ↗
18. Investigation of conditions leading to critical transitions between abrasive belt wear modes for rail grinding10.1016/j.wear.2021.204048 ↗
19. Investigation on abrasive wear mechanism of single diamond grain in flexible scribing titanium alloy10.1016/j.diamond.2021.108631 ↗
20. A machine vision method for measurement of machining tool wear10.1016/j.measurement.2021.109683 ↗
21. Novel monitoring method for material removal rate considering quantitative wear of abrasive belts based on LightGBM learning algorithm10.1007/s00170-021-06988-6 ↗
22. Tool wear and its mechanism in turning aluminum alloys with image processing and machine learning methods10.1016/j.triboint.2023.109207 ↗
23. A U-Net-based intelligent approach for belt morphology quantification and wear monitoring
24. A Unet-inspired spatial-attention transformer model for segmenting gear tooth surface defects10.1016/j.aei.2024.102933 ↗
25. U-Net: Convolutional Networks for Biomedical Image Segmentation
26. An improved u-net for image segmentation of iron roughnecks on offshore oil drilling platforms10.1016/j.measurement.2025.117689 ↗
27. Chen, J.N., Lu, Y.Y., Yu, Q.H., Luo, X.D., Adeli, E., Wang, Y., Lu, L., Yuille, A.L., and Zhou, Y.Y. (2021). TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation. arXiv.