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 (4.4 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

Optimized Mask-RCNN model for particle chain segmentation based on improved online ferrograph sensor

Shuo WANG, Miao WAN, Tonghai WU( ), Zichen BAI, Kunpeng WANG
Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi’an Jiaotong University, Xi’an 710049, China
Show Author Information

Abstract

Ferrograph-based wear debris analysis (WDA) provides significant information for wear fault analysis of mechanical equipment. After decades of offline application, this conventional technology is being driven by the online ferrograph sensor for real-time wear state monitoring. However, online ferrography has been greatly limited by the low imaging quality and segmentation accuracy of particle chains when analyzing degraded lubricant oils in practical applications. To address this issue, an integrated optimization method is developed that focuses on two aspects: the structural re-design of the online ferrograph sensor and the intelligent segmentation of particle chains. For enhancing the imaging quality of wear particles, the magnetic pole of the online ferrograph sensor is optimized to enable the imaging system directly observe wear particles without penetrating oils. Furthermore, a light source simulation model is established based on the light intensity distribution theory, and the LED installation parameters are determined for particle illumination uniformity in the online ferrograph sensor. On this basis, a Mask-RCNN-based segmentation model of particle chains is constructed by specifically establishing the region of interest (ROI) generation layer and the ROI align layer for the irregular particle morphology. With these measures, a new online ferrograph sensor is designed to enhance the image acquisition and information extraction of wear particles. For verification, the developed sensor is tested to collect particle images from different degraded oils, and the images are further handled with the Mask-RCNN-based model for particle feature extraction. Experimental results reveal that the optimized online ferrography can capture clear particle images even in highly-degraded lubricant oils, and the illumination uniformity reaches 90% in its imaging field. Most importantly, the statistical accuracy of wear particles has been improved from 67.2% to 94.1%.

Keywords

wear particle analysisonline ferrographyparticle image acquisitionparticle chain segmentation

References

[1]
Zhang Z N, Yin N, Chen S, Liu C L. Tribo-informatics: Concept, architecture, and case study. Friction 9(3): 642–655 (2021)
Crossref Google Scholar
[2]
Jia R, Wang L Y, Zheng C S, Chen T. Online wear particle detection sensors for wear monitoring of mechanical equipment—A review. IEEE Sens J 22(4): 2930–2947 (2022)
Crossref Google Scholar
[3]
Nugraha R D, Chen S, Yin N, Wu T H, Zhang Z N. Running-in real-time wear generation under vary working condition based on Gaussian process regression approximation. Measurement 181: 109599 (2021)
Crossref Google Scholar
[4]
Wang S, Wu T H, Shao T, Peng Z X. Integrated model of BP neural network and CNN algorithm for automatic wear debris classification. Wear 426–427: 1761–1770 (2019)
Crossref Google Scholar
[5]
Cao W, Dong G N, Xie Y B, Peng Z X. Prediction of wear trend of engines via on-line wear debris monitoring. Tribol Int 120: 510–519 (2018)
Crossref Google Scholar
[6]
Bai Y, Liu Y, Yang L L, Fan B, Zhang P, Feng S. A wear particle sensor using multiple inductive coils under a toroidal magnetic field. IEEE Access 9: 6250–6258 (2021)
Crossref Google Scholar
[7]
Hamilton A, Cleary A, Quail F. Development of a novel wear detection system for wind turbine gearboxes. IEEE Sens J 14(2): 465–473 (2014)
Crossref Google Scholar
[8]
Feng S, Fan B, Mao J H, Xie Y B. Prediction on wear of a spur gearbox by on-line wear debris concentration monitoring. Wear 336–337: 1–8 (2015)
Crossref Google Scholar
[9]
Wu T H, Wang J Q, Peng Y P, Zhang Y L. Description of wear debris from on-line ferrograph images by their statistical color. Tribol Trans 55(5): 606–614 (2012)
Crossref Google Scholar
[10]
Li B, Xi Y H, Feng S, Mao J H, Xie Y B. A direct reflection OLVF debris detector based on dark-field imaging. Meas Sci Technol 29(6): 065104 (2018)
Crossref Google Scholar
[11]
Wu T H, Mao J H, Wang J T, Wu J Y, Xie Y B. A new on-line visual ferrograph. Tribol Trans 52(5): 623–631 (2009)
Crossref Google Scholar
[12]
Yang L F, Wu T H, Wang K P, Wu H K, Kwok N. Optimum color and contrast enhancement for online ferrography image restoration. J Nondestruct Eval Diagn Progn Eng Syst 2(3): 031003 (2019)
Crossref Google Scholar
[13]
Li B, Wu W, Zhou M, Xi Y H, Wei H X, Mao J H. A full field-of-view online visual Ferrograph debris detector based on reflected light microscopic imaging. IEEE Sens J 21(15): 16584–16597 (2021)
Crossref Google Scholar
[14]
Fan B, Liu Y, Zhang C, Wang J G, Zhang P, Mao J H. A deposition rate-based index of debris concentration and its extraction method for online image visual ferrography. Tribol Trans 64(6): 1035–1045 (2021)
Crossref Google Scholar
[15]
Feng S, Zeng Q H, Fan B, Luo J F, Xiao H, Mao J H. Wear debris segmentation of reflection ferrograms using lightweight residual U-net. IEEE Trans Instrum Meas 70: 1–11 (2021)
Crossref Google Scholar
[16]
Wu H K, Wu T H, Peng Y P, Peng Z X. Watershed-based morphological separation of wear debris chains for on-line ferrograph analysis. Tribol Lett 53(2): 411–420 (2014)
Crossref Google Scholar
[17]
Wang J Q, Zhang L, Lu F X, Wang X L. The segmentation of wear particles in ferrograph images based on an improved ant colony algorithm. Wear 311(1–2): 123–129 (2014)
Crossref Google Scholar
[18]
Peng Y P, Cai J H, Wu T H, Cao G Z, Kwok N, Peng Z X. WP-DRnet: A novel wear particle detection and recognition network for automatic ferrograph image analysis. Tribol Int 151: 106379 (2020)
Crossref Google Scholar
[19]
Hong W, Cai W J, Wang S P, Tomovic M M. Mechanical wear debris feature, detection, and diagnosis: A review. Chin J Aeronaut 31(5): 867–882 (2018)
Crossref Google Scholar
[20]
Luo X Q, Liu Z Z, Zhai H Q, Hou Y J, Feng G W, Li X L. Optimized design of the detection coils for the metal foreign object detection system applied to wireless power transfer. Energy Rep 8: 883–890 (2022)
Crossref Google Scholar
[21]
Chen F C, Zheng J N, Ma H Y, Zhang W, Fan L L, Zhang F X, Li M, Ali Abaker Omer A, Zhang X Y, Liu W. Pulsed-lighting LED luminaire for agriculture with a geometrical optical solution. Opt Express 31(4): 5609 (2023)
Crossref Google Scholar
[22]
Itoh H, Oda M, Mori Y, Misawa M, Kudo S E, Imai K, Ito S, Hotta K, Takabatake H, Mori M, et al. Unsupervised colonoscopic depth estimation by domain translations with a Lambertian-reflection keeping auxiliary task. Int J Comput Assist Radiol Surg 16(6): 989–1001 (2021)
Crossref Google Scholar
[23]
Memon M A, Siddique M D, Mekhilef S, Mubin M. Asynchronous particle swarm optimization-genetic algorithm (APSO-GA) based selective harmonic elimination in a cascaded H-bridge multilevel inverter. IEEE Trans Ind Electron 69(2): 1477–1487 (2022)
Crossref Google Scholar
[24]
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
[25]
Zhang P, Liu X M, Yuan J, Liu C L. YOLO5-spear: A robust and real-time spear tips locator by improving image augmentation and lightweight network for selective harvesting robot of white asparagus. Biosyst Eng 218: 43–61 (2022)
Crossref Google Scholar
[26]
He K M, Gkioxari G, Dollar P, Girshick R. Mask R-CNN. IEEE Trans Pattern Anal Mach Intell 42(2): 386–397 (2020)
Crossref Google Scholar
[27]
Egala R, Jagadeesh G V, Setti S G. Experimental investigation and prediction of tribological behavior of unidirectional short castor oil fiber reinforced epoxy composites. Friction 9(2): 250–272 (2021)
Crossref Google Scholar
[28]
Wang C X, Wang X X, Wang Y W, Hu S C, Chen H Y, Gu X H, Yan J C, He T. FastDARTSDet: Fast differentiable architecture joint search on backbone and FPN for object detection. Appl Sci 12(20): 10530 (2022)
Crossref Google Scholar
[29]
Peng Y P, Wu T H, Wang S, Du Y, Kwok N, Peng Z X. A microfluidic device for three-dimensional wear debris imaging in online condition monitoring. Proc Inst Mech Eng Part J J Eng Tribol 231(8): 965–974 (2017)
Crossref Google Scholar
[30]
Hu X B, Song J, Liao Z H, Liu Y H, Gao J, Menze B, Liu W Q. 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
[31]
Wu H, Liu G Z. A dynamic infrared object tracking algorithm by frame differencing. Infrared Phys Technol 127: 104384 (2022)
Crossref Google Scholar
[32]
Li J B, Luo W, Wang Z L, Fan S X. Early detection of decay on apples using hyperspectral reflectance imaging combining both principal component analysis and improved watershed segmentation method. Postharvest Biol Technol 149: 235–246 (2019)
Crossref Google Scholar
[33]
Cao W, Chen W, Dong G N, Wu J Y, Xie Y B. Wear condition monitoring and working pattern recognition of piston rings and cylinder liners using on-line visual ferrograph. Tribol Trans 57(4): 690–699 (2014)
Crossref Google Scholar
Friction
Volume 12 Issue 6,
June 2024
Pages 1194-1213
DOI: 10.1007/s40544-023-0800-4
Cite this article:
WANG S, WAN M, WU T, et al. Optimized Mask-RCNN model for particle chain segmentation based on improved online ferrograph sensor. Friction, 2024, 12(6): 1194-1213. https://doi.org/10.1007/s40544-023-0800-4

246

Views

9

Downloads

2

Crossref

2

Web of Science

2

Scopus

0

CSCD

Altmetrics
Received: 14 March 2023
Revised: 27 June 2023
Accepted: 07 July 2023
Published: 20 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