AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Friction Article
PDF (11.8 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Open Access

Comparison-embedded evidence-CNN model for fuzzy assessment of wear severity using multi-dimensional surface images

Tao SHAO1, Shuo WANG1, Qinghua WANG1, Tonghai WU1( ), Zhifu HUANG2
Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi’an Jiaotong University, Xi’an 710049, China
State Key Laboratory for Mechanical Behavior of Materials, Xi’an Jiaotong University, Xi’an 710049, China
Show Author Information

Graphical Abstract

Abstract

Wear topography is a significant indicator of tribological behavior for the inspection of machine health conditions. An intelligent in-suit wear assessment method for random topography is here proposed. Three-dimension (3D) topography is employed to address the uncertainties in wear evaluation. Initially, 3D topography reconstruction from a worn surface is accomplished with photometric stereo vision (PSV). Then, the wear features are identified by a contrastive learning-based extraction network (WSFE-Net) including the relative and temporal prior knowledge of wear mechanisms. Furthermore, the typical wear degrees including mild, moderate, and severe are evaluated by a wear severity assessment network (WSA-Net) for the probability and its associated uncertainty based on subjective logic. By integrating the evidence information from 2D and 3D-damage surfaces with Dempster–Shafer (D–S) evidence, the uncertainty of severity assessment results is further reduced. The proposed model could constrain the uncertainty below 0.066 in the wear degree evaluation of a continuous wear experiment, which reflects the high credibility of the evaluation result.

Keywords

contrastive learningwear severity assessmentsubjective logicDempster–Shafer (D–S) evidence theory

References

[1]
He Z, Li J Y, Liu Y M, Yan J W. Single-grain cutting based modeling of abrasive belt wear in cylindrical grinding. Friction 8(1): 208–220 (2020)
Crossref Google Scholar
[2]
Popov V L, Pohrt R. Adhesive wear and particle emission: Numerical approach based on asperity-free formulation of Rabinowicz criterion. Friction 6(3): 260–273 (2018)
Crossref Google Scholar
[3]
Pan R, Chen Y D, Lan H, E S J, Ren R. Investigation into the evolution of the microcosmic surface of bainitic wheel steel material suffering polygonal wear. Wear 504: 204430 (2022)
Crossref Google Scholar
[4]
Hu X, Song J, Liao Z, Liu Y, Gao J, Menze B, Liu W. Morphological residual convolutional neural network (M-RCNN) for intelligent recognition of wear particles from artificial joints. Friction 10(4): 560–572 (2022)
Crossref Google Scholar
[5]
Nugraha R D, He K, Liu A, Zhang Z N. Short-term cross-sectional time-series wear prediction by deep learning approaches. J Comput Inf Sci Eng 23(2): 021007 (2022)
Crossref Google Scholar
[6]
Amezquita-Sanchez J P, Adeli H. Signal processing techniques for vibration-based health monitoring of smart structures. Arch Comput Methods in Eng 23(1): 1–15 (2016)
Crossref Google Scholar
[7]
Shi S, Guo D, Luo J. Micro/atomic-scale vibration induced superlubricity. Friction 9(5): 1163–1174 (2021)
Crossref Google Scholar
[8]
Towsyfyan H, Gu F, Ball A D, Liang B. Tribological behaviour diagnostic and fault detection of mechanical seals based on acoustic emission measurements. Friction 7(6): 572–586 (2019)
Crossref Google Scholar
[9]
Pandiyan V, Prost J, Vorlaufer G, Varga M, Wasmer K. Identification of abnormal tribological regimes using a microphone and semi-supervised machine-learning algorithm. Friction 10(4): 583–596 (2022)
Crossref Google Scholar
[10]
Shen M X, Li B, Li S X, Xiong G Y, Ji D H, Zhang Z N. Effect of particle concentration on the tribological properties of NBR sealing pairs under contaminated water lubrication conditions. Wear 456: 203381 (2020)
Crossref Google Scholar
[11]
Wen Y, Tang J, Zhou W, Li L, Zhu C. New analytical model of elastic-plastic contact for three-dimensional rough surfaces considering interaction of asperities. Friction 10(2): 217–231 (2022)
Crossref Google Scholar
[12]
Shen M X, Li B, Ji D H, Xiong G Y, Zhao L Z, Zhang J, Zhang Z N. Effect of particle size on tribological properties of rubber/steel seal pairs under contaminated water lubrication conditions. Tribol Lett 68(1): 1–15 (2020)
Crossref Google Scholar
[13]
Wang Q, Wang S, Li B, Zhu K, Wu T H. In-situ 3D reconstruction of worn surface topography via optimized photometric stereo. Measurement 190: 110679 (2022)
Crossref Google Scholar
[14]
Yagi K, Tango H, Izumi T, Tohyamac M, Saitod K, Sugimuraa J. In-situ observation of influence of metal types on wear process in dry conditions. Wear 488: 204162 (2022)
Crossref Google Scholar
[15]
Wang S, Wu T, Wang K, Peng Z X, Kwok N, Sarkodie-Gyan T. 3-D particle surface reconstruction from multiview 2-D images with structure from motion and shape from shading. IEEE Trans Ind Electron 68(2): 1626–1635 (2020)
Crossref Google Scholar
[16]
Martínez-Arellano G, Terrazas G, Ratchev S. Tool wear classification using time series imaging and deep learning. Int J Adv Manuf Tech 104(9): 3647–3662 (2019)
Crossref Google Scholar
[17]
Perčić M, Zelenika S, Mezić I. Artificial intelligence-based predictive model of nanoscale friction using experimental data. Friction 9(6): 1726–1748 (2021)
Crossref Google Scholar
[18]
Kang J X, Lu Y J, Luo H B, Li J, Hou Y T, Zhang Y F. Wear assessment model for cylinder liner of internal combustion engine under fuzzy uncertainty. Mech Ind 22: 29 (2021)
Crossref Google Scholar
[19]
Cabanettes F, Rosén B G. Topography changes observation during running-in of rolling contacts. Wear 315(1–2): 78–86 (2014)
Crossref Google Scholar
[20]
Suh A Y, Polycarpou A A, Conry T F. Detailed surface roughness characterization of engineering surfaces undergoing tribological testing leading to scuffing. Wear 255(1–6): 556–568 (2003)
Crossref Google Scholar
[21]
Gonzalez-Arias C, Viáfara C C, Coronado J J, Martinezc F. Automatic classification of severe and mild wear in worn surface images using histograms of oriented gradients as descriptor. Wear 426: 1702–1711 (2019)
Crossref Google Scholar
[22]
Chang H, Borghesani P, Smith W A, Peng Z X. Application of surface replication combined with image analysis to investigate wear evolution on gear teeth—A case study. Wear 430: 355–368 (2019)
Crossref Google Scholar
[23]
Xu C, Wu T H, Huo Y W, Yang H B. In-situ characterization of three dimensional worn surface under sliding-rolling contact. Wear 426: 1781–1787 (2019)
Crossref Google Scholar
[24]
Wang H, Li S, Song L, Cui L. A novel convolutional neural network based fault recognition method via image fusion of multi-vibration-signals. Comput Ind 105: 182–190 (2019)
Crossref Google Scholar
[25]
LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 521(7553): 436–444 (2015)
Crossref Google Scholar
[26]
Lei Y, Jia F, Lin J, Xing S, Ding S X. An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data. IEEE Trans Ind Electron 63(5): 3137–3147 (2016)
Crossref Google Scholar
[27]
Chang H, Borghesani P, Peng Z. Automated assessment of gear wear mechanism and severity using mould images and convolutional neural networks. Tribol Int 147: 106280 (2020)
Crossref Google Scholar
[28]
Cheng C, Li J, Liu Y, Nie M, Wang W. Deep convolutional neural network-based in-process tool condition monitoring in abrasive belt grinding. Comput Ind 106: 1–13 (2019)
Crossref Google Scholar
[29]
Unal O, Maleki E, Karademir I, Husem F, Efe Y, Das T. The formation of gradient nanostructured medium carbon steel via mild, moderate, and severe ultrasonic nanocrystal surface modification options: Assessment on wear and friction performance. Mater Sci Eng B 285: 115970 (2022)
Crossref Google Scholar
[30]
Cong R, Lei J, Fu H, Cheng M, Lin W, Huang Q. Review of visual saliency detection with comprehensive information. IEEE T Circ Syst Vid Tech 29(10): 2941–2959 (2018)
Crossref Google Scholar
[31]
Dong L, Zhang W, Xu W. Underwater image enhancement via integrated RGB and LAB color models. Signal Process: Image 104: 116684 (2022)
Crossref Google Scholar
[32]
Yang P, Song W, Zhao X, Zheng R, Qingge L. An improved Otsu threshold segmentation algorithm. Int J Comput Sci Eng 22(1): 146–153 (2020)
Crossref Google Scholar
[33]
Zhao Y, Zhang X, Feng W, Xu J. Deep learning classification by ResNet-18 based on the real spectral dataset from multispectral remote sensing images. Remote Sens 14(19): 4883 (2022)
Crossref Google Scholar
[34]
Lee S, Park Y T, d’Auriol B J. A novel feature selection method based on normalized mutual information. Appl Intell 37(1): 100–120 (2012)
Crossref Google Scholar
[35]
Chatzimparmpas A, Martins R M, Kerren A. t-viSNE: Interactive assessment and interpretation of t-SNE projections. IEEE Trans Vis Comput Graphics 26(8): 2696–2714 (2020)
Crossref Google Scholar
[36]
Audun J. Subjective Logic: A formalism for reasoning under uncertainty. Berlin (GER): Springer, 2018.
Friction
Volume 12 Issue 6,
June 2024
Pages 1098-1118
DOI: 10.1007/s40544-023-0752-8
Cite this article:
SHAO T, WANG S, WANG Q, et al. Comparison-embedded evidence-CNN model for fuzzy assessment of wear severity using multi-dimensional surface images. Friction, 2024, 12(6): 1098-1118. https://doi.org/10.1007/s40544-023-0752-8

181

Views

16

Downloads

0

Crossref

0

Web of Science

0

Scopus

0

CSCD

Altmetrics
Received: 11 December 2022
Revised: 15 January 2023
Accepted: 27 February 2023
Published: 01 December 2023
© The author(s) 2023.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.

The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
Return