多源信息拟合摩擦系数的回归集成模型

孙悦, 何可, 张执南

清华大学学报(自然科学版) ›› 2022, Vol. 62 ›› Issue (12) : 1980-1988.

PDF(12491 KB)
PDF(12491 KB)
清华大学学报(自然科学版) ›› 2022, Vol. 62 ›› Issue (12) : 1980-1988. DOI: 10.16511/j.cnki.qhdxxb.2022.25.048
机械工程

多源信息拟合摩擦系数的回归集成模型

  • 孙悦, 何可, 张执南
作者信息 +

Multi-source information fitting regression integrated model of coefficient of friction

  • SUN Yue, HE Ke, ZHANG Zhinan
Author information +
文章历史 +

摘要

机器系统运动部件摩擦系数(coefficient of friction, COF)的实时监测是一项具有挑战性的难题, 智能感知和数据技术的发展为利用摩擦学关联信息对摩擦系数进行预测提供了可能性。该文利用摩擦磨损试验过程中的声音、振动等多源摩擦关联信息, 形成时间截面化的摩擦信息数据集, 针对摩擦系数拟合问题建立了K折交叉验证双层堆叠的回归集成模型, 定义了范围性评估的评价指标, 并通过多种载荷试验数据对模型进行了检验。结果表明所建立模型能够有效提炼摩擦信息的关联特性, 从而实现对摩擦系数的准确拟合及预测, 该方法对不同载荷条件数据具有通用性。

Abstract

Real-time monitoring of the friction coefficient of the moving parts of a machine system is a challenging problem. The development of intelligent perception and data technology provides the possibility to use tribological correlation information to predict the friction coefficient. This paper uses multi-source friction information such as sound during the friction and wear test to form a time-sectioned friction information data set, establishes a K-fold cross-validation double-stacked regression integration model, defines the evaluation indicators for scope evaluation, and the model was tested with a variety of load test data. The results showed that the model can effectively refine the correlation characteristics of friction information, so as to accurately fit and predict the friction coefficient, and has universality for data under different load conditions.

关键词

摩擦信息学 / 摩擦系数(COF) / 特征提取 / 回归模型 / 堆叠方法

Key words

triboinformatics / coefficient of friction (COF) / feature extraction / regression model / stacking method

引用本文

导出引用
孙悦, 何可, 张执南. 多源信息拟合摩擦系数的回归集成模型[J]. 清华大学学报(自然科学版). 2022, 62(12): 1980-1988 https://doi.org/10.16511/j.cnki.qhdxxb.2022.25.048
SUN Yue, HE Ke, ZHANG Zhinan. Multi-source information fitting regression integrated model of coefficient of friction[J]. Journal of Tsinghua University(Science and Technology). 2022, 62(12): 1980-1988 https://doi.org/10.16511/j.cnki.qhdxxb.2022.25.048

参考文献

[1] WANG X C, MO J L, YANG J Z, et al. Experimental and numerical study on the effect of surface texturing on squeal noise of brake disc materials[J]. Journal of Vibration and Shock, 2015, 34(24): 182-187. (in Chinese) 王晓翠, 莫继良, 阳江舟, 等. 织构表面影响制动盘材料尖叫噪声的试验及有限元分析[J]. 振动与冲击, 2015, 34(24): 182-187.
[2] SHEVCHIK S A, ZANOLI S, SAEIDI F, et al. Monitoring of friction-related failures using diffusion maps of acoustic time series[J]. Mechanical Systems and Signal Processing, 2021, 148: 107172.
[3] SCHMITZ T L, ACTION J E, ZIEGERT J C, et al. The difficulty of measuring low friction: Uncertainty analysis for friction coefficient measurements[J]. Journal of Tribology, 2005, 127(3): 673-678.
[4] MARIAN M, TREMMEL S. Current trends and applications of machine learning in tribology—A review[J]. Lubricants, 2021, 9(9): 86.
[5] CIULLI E. Tribology and industry: From the origins to 4.0[J]. Frontiers in Mechanical Engineering, 2019, 5: 55.
[6] ZHANG Z N, YIN N, CHEN S, et al. Tribo-informatics: Concept, architecture, and case study[J]. Friction, 2021, 9(3): 642-655.
[7] HASAN S, KORDIJAZI A, ROHATGI P K, et al. Triboinformatics approach for friction and wear prediction of Al-graphite composites using machine learning methods[J]. Journal of Tribology, 2022, 144(1): 011701.
[8] CHEN G X, ZHOU Z R, XIE Y B. Current state and progress of the research of friction-induced noise[J]. Tribology, 2000, 20(6): 478-481. (in Chinese) 陈光雄, 周仲荣, 谢友柏. 摩擦噪声研究的现状和进展[J]. 摩擦学学报, 2000, 20(6): 478-481.
[9] RASTEGAEV I, MERSON D, VINOGRADOV A. Real time acoustic emission methodology in effective tribology testing[J]. International Journal of Microstructure and Materials Properties, 2014, 9(3-5): 360-373.
[10] XING P F, LI G B, GAO H T, et al. Experimental investigation on identifying friction state in lubricated tribosystem based on friction-induced vibration signals[J]. Mechanical Systems and Signal Processing, 2020, 138: 106590.
[11] CAO W, ZHANG H, WANG N, et al. The gearbox wears state monitoring and evaluation based on on-line wear debris features[J]. Wear, 2019, 426-427: 1719-1728.
[12] VELLORE A, GARCIA S R, JOHNSON D A, et al. Ambient and nitrogen environment friction data for various materials & surface treatments for space applications[J]. Tribology Letters, 2021, 69(1): 10.
[13] FENG B, ZHANG D S, YANG J, et al. A novel time-varying friction compensation method for servomechanism[J]. Mathematical Problems in Engineering, 2015, 2015: 269391.
[14] XIE Y B. Three axioms in tribology[J]. Tribology, 2001, 21(3): 161-166. (in Chinese) 谢友柏. 摩擦学的三个公理[J]. 摩擦学学报, 2001, 21(3): 161-166.
[15] KOUPRIANOFF D, YADROITSAVA I, DU PLESSIS A, et al. Monitoring of laser powder bed fusion by acoustic emission: Investigation of single tracks and layers[J]. Frontiers in Mechanical Engineering, 2021, 7: 678076.
[16] FENG P P, BORGHESANI P, SMITH W A, et al. A review on the relationships between acoustic emission, friction and wear in mechanical systems[J]. Applied Mechanics Reviews, 2020, 72(2): 020801.
[17] LIU T, LI G B, WEI H J, et al. Experimental observation of cross correlation between tangential friction vibration and normal friction vibration in a running-in process[J]. Tribology International, 2016, 97: 77-88.
[18] KHAN M A, BASIT K, KHAN S Z, et al. Experimental assessment of multiple contact wear using airborne noise under dry and lubricated conditions[J]. Proceedings of the Institution of Mechanical Engineers, Part J: Journal of Engineering Tribology, 2017, 231(12): 1503-1516.
[19] SAWCZUK W, ULBRICH D, KOWALCZYK J, et al. Evaluation of wear of disc brake friction linings and the variability of the friction coefficient on the basis of vibroacoustic signals[J]. Sensors, 2021, 21(17): 5927.
[20] WANG A Y, MO J L, WANG X C, et al. Effect of surface roughness on friction-induced noise: Exploring the generation of squeal at sliding friction interface[J]. Wear, 2018, 402-403: 80-90.
[21] HSIAO C. Panel data analysis—Advantages and challenges[J]. TEST, 2007, 16(1): 1-22.
[22] ZHAN Y, LI Q J, YANG G W, et al. Panel data models for pavement friction of major preventive maintenance treatments [J]. International Journal of Geomechanics, 2019, 19(8): 04019081.
[23] RUGGIERO A, D'AMATO R, CALVO R, et al. Measurements of the friction coefficient: Discussion on the results in the framework of the time series analysis[M]// HLOCH S, KLICHOVÁ D, KROLCZYK G M, et al. Advances in Manufacturing Engineering and Materials. Cham: Springer, 2019: 443-455.
[24] SÁNCHEZ FERNÁNDEZ L P. Discretization accuracy of continuous signal peak values in limited bandwidth systems[J]. Computación y Sistemas, 2021, 25(1): 173-183.
[25] IRAQI A, VIDIC N S, REDFERN M S, et al. Prediction of coefficient of friction based on footwear outsole features[J]. Applied Ergonomics, 2020, 82: 102963.
[26] KAMARTHI S V, KUMARA S R T, COHEN P H. Flank wear estimation in turning through wavelet representation of acoustic emission signals[J]. Journal of Manufacturing Science and Engineering, 2000, 122(1): 12-19.
[27] JAIN P H, BHOSLE S P. Study of effects of radial load on vibration of bearing using time-Domain statistical parameters[J]. IOP Conference Series: Materials Science and Engineering, 2021, 1070: 012130.

基金

张执南,副教授,E-mail:zhinanz@sjtu.edu.cn

PDF(12491 KB)

Accesses

Citation

Detail

段落导航
相关文章

/