基于近红外光谱技术的润滑油磨粒含量检测研究

doi:10.3964/j.issn.1000-0593(2025)03-0816-10

Abstract
References
Related Citation (15)

Download: PDF (4919 KB)
Export: BibTeX | EndNote (RIS)

Abstract The detection of wear particle content in engine lubricating oil is crucial for preventing engine wear. Accurately and rapidly detecting the wear particle content in lubricating oil can timely assess the wear condition of mechanical equipment. To rapidly and efficiently detect the wear particle content in the solid-liquid two-phase flow formed by lubricating oil wear particles, a method combining near-infrared spectroscopy with mathematical modeling algorithms for predicting the wear particle content is proposed. Through the near-infrared absorption spectroscopy experimental system built, the spectral data of wear particle concentration in the range of 6～15 μg·mL^-1 were collected by using a near-infrared spectrometer with a wavelength detection range of 900～2 500 nm under a total of 10 groups of working conditions under two kinds of metal wear particles, Fe and Cu, and five different particle sizes. To address the issue that spectral information at single-wavelength points cannot adequately explain the changes in wear particle concentration within the lubricating oil, the sample set partitioning based on joint x-y distances (SPXY) algorithm was employed to segment the spectral dataset. The partial least squares (PLS) model for predicting the wear particle content of lubricating oil was established, and the model prediction results under each working condition were analyzed. The results showed that wear particles could be effectively detected under each working condition, the highest coefficient of determination (R²) for the model was 0.831 8. Various data preprocessing methods were employed to correct the raw spectral data before modeling to address the issue of less-than-ideal prediction performance when using PLS modeling alone. The results showed that, except for a few abnormal conditions, the coefficient of determination R² for the models under other conditions was greater than 0.8, optimizing the predictive performance of the PLS model. To further optimize the prediction effect of the lubricating oil wear particle model, the lubricating oil wear particle genetic programming (GP) model and the lubricating oil wear particle genetic program-partial least squares (GP-PLS) model were established, respectively. Compared with the PLS optimization model, the GP model for predicting lubricating oil wear particle content was more robust and had a better prediction effect, and the highest R² reached 0.956 2. The mean fiducial error (MFE) was 14.73%. The GP-PLS model, compared to the GP model, achieved the highest R² of 0.943 0 and a maximum MFE of 10.86%, improvement in MFE, thereby enhancing the predictive accuracy of the model. Through research and analysis of wear particle content prediction models, it has been concluded that various models can effectively predict changes in wear particle content in lubricating oil. Among them, the GP-PLS model performs better predicting wear particle content changes. The research results indicate that using spectroscopic analysis combined with model algorithms to predict wear particle content in the solid-liquid two-phase flow of lubricating oil is feasible, providing an effective detection method for detecting mechanical wear faults in engine equipment.

Key words：Near-infrared spectrum; Wear particle detection; Partial least squares; Genetic programming

Received: 2024-02-23 Accepted: 2024-07-09

ZTFLH:

TK314

Corresponding Authors: ZHOU Yan E-mail: yan.zhou@mail.xjtu.edu.cn

Cite this article:

YIN Xiong,CUI Hong-shuai,LIU Xue-jing, et al. Study on the Detection of Wear Particle Content in Lubricating Oil Based on Near-Infrared Spectroscopy Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(03): 816-825.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2025)03-0816-10 OR https://www.gpxygpfx.com/EN/Y2025/V45/I03/816

[1] Wang J, Wang G, Cheng L. Engineering Failure Analysis, 2020, 109: 104299.
[2] WANG Yi-shou, WU Di-heng ZHU Ling, et al(王奕首, 吴迪恒, 朱凌, 等). Journal of Electronic Measurement and Instrumentation(电子测量与仪器学报), 2021, 35(3): 73.
[3] HOU Xian-jun, WANG Shi-cheng, MOHAMED KAMAL Ahmed Ali(侯献军, 王士成, MOHAMED KAMAL Ahmed Ali). Lubrication Engineering(润滑与密封), 2018, 43(6): 1.
[4] Seifert W W, Westcott V C. Wear, 1972, 21(1): 27.
[5] Walsh A. Spectrochimica Acta, 1955, 7: 108.
[6] Zhu X, Zhong C, Zhe J. Tribology International, 2017, 109: 473.
[7] SUN Yan-shan, YANG Hao, TONG Hai-bin, et al(孙衍山, 杨昊, 佟海滨, 等). Chinese Journal of Scientific Instrument(仪器仪表学报), 2017, 38(7): 1561.
[8] LI Yi-ning, ZHANG Pei-lin，YANG Yu-dong, et al(李一宁, 张培林, 杨玉栋, 等). Mechanical Science and Technology for Aerospace Engineering(机械科学与技术), 2016, 35(6): 853.
[9] Ning C, Hu F, Ouyang W, et al. Friction, 2023, 11(5): 685.
[10] NIE Peng, HAN Jiao, XU Tao, et al(聂鹏, 韩娇, 徐涛, 等). Instrument Technique and Sensor(仪表技术与传感器), 2016, (3): 4.
[11] GAO Zhen, ZHENG Chang-song, JIA Ran, et al(高震, 郑长松, 贾然, 等). Journal of Guangxi University(Nat. Sci. Ed.)[广西大学学报(自然科学版)], 2017, 42(2): 409.
[12] MA Wen-bo, SUN Yan-shan, ZENG Zhou-mo(马闻博, 孙衍山, 曾周末). Journal of Electronic Measurement and Instrumentation(电子测量与仪器学报), 2017, 31(12): 1984.
[13] JIA Bao-hui, DING Zi-hang, XIAO Hai-jian, et al(贾宝惠, 丁梓航, 肖海建, 等). Chinese Journal of Scientific Instrument(仪器仪表学报), 2022, 43(12): 49.
[14] LIU Zhen-zhen, LIU Yan, ZUO Hong-fu, et al(刘珍珍, 刘岩, 左洪福, 等). Transducer and Microsystem Technologies(传感器与微系统), 2023, 42(11): 19.
[15] GUAN Li-yuan, WANG Zhong, QI Ning, et al(管丽媛, 王钟, 祁宁, 等). Journal of Instrumental Analysis(分析测试学报), 2020, 39(6): 795.
[16] Zhou Y, Cui H S. Measurement Science and Technology, 2023, 34(3): 035501.
[17] Belopukhov V, Blinov A, Borovik S, et al. Energies, 2022, 15(13): 4896.
[18] LUAN Xin-xin, ZHAI Chen, AN Huan-jiong, et al(栾鑫鑫, 翟晨, 安焕炯, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2023, 43(9): 2818.
[19] Koza J R. Statistics and Computing, 1994, 4: 87.