Journal Home > Volume 12 , Issue 6

The tribological properties of self-lubricating composites are influenced by many variables and complex mechanisms. Data-driven methods, including machine learning (ML) algorithms, can yield a better comprehensive understanding of complex problems under the influence of multiple parameters, typically for how tribological performances and material properties correlate. Correlation of friction coefficients and wear rates of copper/aluminum-graphite (Cu/Al-graphite) self-lubricating composites with their inherent material properties (composition, lubricant content, particle size, processing process, and interfacial bonding strength) and the variables related to the testing method (normal load, sliding speed, and sliding distance) were analyzed using traditional approaches, followed by modeling and prediction of tribological properties through five different ML algorithms, namely support vector machine (SVM), K-Nearest neighbor (KNN), random forest (RF), eXtreme gradient boosting (XGBoost), and least-squares boosting (LSBoost), based on the tribology experimental data. Results demonstrated that ML models could satisfactorily predict friction coefficient and wear rate from the material properties and testing method variables data. Herein, the LSBoost model based on the integrated learning algorithm presented the best prediction performance for friction coefficients and wear rates, with R2 of 0.9219 and 0.9243, respectively. Feature importance analysis also revealed that the content of graphite and the hardness of the matrix have the greatest influence on the friction coefficients, and the normal load, the content of graphite, and the hardness of the matrix influence the wear rates the most.


menu
Abstract
Full text
Outline
About this article

Modeling and prediction of tribological properties of copper/aluminum-graphite self-lubricating composites using machine learning algorithms

Show Author's information Huifeng NING1( )Faqiang CHEN1Yunfeng SU2( )Hongbin LI2,3Hengzhong FAN2Junjie SONG2Yongsheng ZHANG2( )Litian HU2
School of Electrical and Mechanical Engineering, Lanzhou University of Technology, Lanzhou 730050, China
State Key Laboratory of Solid Lubrication, Lanzhou Institute of Chemical Physics, Chinese Academy of Sciences, Lanzhou 730000, China
Center of Materials Science and Optoelectronics Engineering, University of Chinese Academy of Sciences, Beijing 100049, China

Abstract

The tribological properties of self-lubricating composites are influenced by many variables and complex mechanisms. Data-driven methods, including machine learning (ML) algorithms, can yield a better comprehensive understanding of complex problems under the influence of multiple parameters, typically for how tribological performances and material properties correlate. Correlation of friction coefficients and wear rates of copper/aluminum-graphite (Cu/Al-graphite) self-lubricating composites with their inherent material properties (composition, lubricant content, particle size, processing process, and interfacial bonding strength) and the variables related to the testing method (normal load, sliding speed, and sliding distance) were analyzed using traditional approaches, followed by modeling and prediction of tribological properties through five different ML algorithms, namely support vector machine (SVM), K-Nearest neighbor (KNN), random forest (RF), eXtreme gradient boosting (XGBoost), and least-squares boosting (LSBoost), based on the tribology experimental data. Results demonstrated that ML models could satisfactorily predict friction coefficient and wear rate from the material properties and testing method variables data. Herein, the LSBoost model based on the integrated learning algorithm presented the best prediction performance for friction coefficients and wear rates, with R2 of 0.9219 and 0.9243, respectively. Feature importance analysis also revealed that the content of graphite and the hardness of the matrix have the greatest influence on the friction coefficients, and the normal load, the content of graphite, and the hardness of the matrix influence the wear rates the most.

Keywords: self-lubricating composites, tribological properties, machine learning (ML), prediction

References(63)

[1]
Zhen J M, Cheng J, Tan H, Sun Q C, Zhu S Y, Yang J, Liu W M. Investigation of tribological characteristics of nickel alloy-based solid-lubricating composites at elevated temperatures under vacuum. Friction 9(5): 990–1001 (2021)
[2]
Usca Ü A, Şap S, Uzun M, Giasin K, Pimenov D Y. Evaluation of mechanical and tribological aspect of self-lubricating Cu-6Gr composites reinforced with SiC-WC hybrid particles. Nanomaterials (Basel) 12(13): 2154 (2022)
[3]
Li G C, Ma Y, He X L, Li W, Li P Y. Damping capacity of high strength-damping aluminum alloys prepared by rapid solidification and powder metallurgy process. Trans Nonferrous Met Soc China 22(5): 1112–1117 (2012)
[4]
Omrani E, Moghadam A D, Menezes P L, Rohatgi P K. Influences of graphite reinforcement on the tribological properties of self-lubricating aluminum matrix composites for green tribology, sustainability, and energy efficiency—A review. Int J Adv Manuf Technol 83(1): 325–346 (2016)
[5]
Singh J. Fabrication characteristics and tribological behavior of Al/SiC/Gr hybrid aluminum matrix composites: A review. Friction 4(3): 191–207 (2016)
[6]
Pan S H, Jin K Y, Wang T L, Zhang Z N, Zheng L, Umehara N. Metal matrix nanocomposites in tribology: Manufacturing, performance, and mechanisms. Friction 10(10): 1596–1634 (2022)
[7]
Sharma P, Khanduja D, Sharma S. Dry sliding wear investigation of Al6082/Gr metal matrix composites by response surface methodology. J Mater Res Technol 5(1): 29–36 (2016)
[8]
Pan T H, Zhang J, Zhang X, Zhao W H, Zhang H J, Lu B H. Milling force coefficients-based tool wear monitoring for variable parameter milling. Int J Adv Manuf Technol 120(7): 4565–4580 (2022)
[9]
Yu A D, Li Y F, Huang H Z, Tong H, Diao Q. Probabilistic fatigue life prediction of bearings via the generalized polynomial chaos expansion. J Mech Sci Technol 36(10): 4885–4894 (2022)
[10]
Pandiyan V, Akeddar M, Prost J, Vorlaufer G, Varga M, Wasmer K. Long short-term memory based semi-supervised encoder—Decoder for early prediction of failures in self-lubricating bearings. Friction 11(1): 109–124 (2023)
[11]
Altay O, Gurgenc T, Ulas M, Özel C. Prediction of wear loss quantities of ferro-alloy coating using different machine learning algorithms. Friction 8(1): 107–114 (2020)
[12]
Song Q G, Chang B B, Dong S S, Gu W F, Kang J H, Wang M C, Liu Z F. Machine learning and its influence on materials research and development. Materials Review 36(1A): (2022)
[13]
Yin N, Xing Z G, He K, Zhang Z N. Tribo-informatics approaches in tribology research: A review. Friction 11(1): 1–22 (2023)
[14]
Argatov I I, Chai Y S. An artificial neural network supported regression model for wear rate. Tribol Int 138: 211–214 (2019)
[15]
Hasan M S, Wong T, Rohatgi P K, Nosonovsky M. Analysis of the friction and wear of graphene reinforced aluminum metal matrix composites using machine learning models. Tribol Int 170: 107527 (2022)
[16]
Hasan M S, Kordijazi A, Rohatgi P K, Nosonovsky M. Machine learning models of the transition from solid to liquid lubricated friction and wear in aluminum-graphite composites. Tribol Int 165: 107326 (2022)
[17]
Hasan M S, Kordijazi A, Rohatgi P K, Nosonovsky M. Triboinformatic modeling of dry friction and wear of aluminum base alloys using machine learning algorithms. Tribol Int 161: 107065 (2021)
[18]
Li H Q, Liu Y Z, Zheng B C, Wang S, Yi Y L, Zhang Y Z, Li W. On the tribological behaviors of Cu matrix composites with different Cu-coated graphite content. J Mater Res Technol 25: 83–94 (2023)
[19]
Blau P J, Yust C S. Microfriction studies of model self-lubricating surfaces. Surf Coat Technol 62(1–3): 380–387 (1993)
[20]
Xiao J K, Wu Y Q, Zhang W, Chen J, Zhang C. Friction of metal-matrix self-lubricating composites: Relationships among lubricant content, lubricating film coverage, and friction coefficient. Friction 8(3): 517–530 (2020)
[21]
Bowden F P, Tabor D. Friction of non-metals. In The Friction and Lubrication of Solids. Bowden F P, Tabor D, Eds. Oxford: Oxford University Press, 2001: 161–175.
DOI
[22]
Pan S H, Saso T, Yu N, Sokoluk M, Yao G C, Umehara N, Li X C. New study on tribological performance of AA7075-TiB2 nanocomposites. Tribol Int 152: 106565 (2020)
[23]
Zhou Q, Luo D W, Hua D P, Ye W T, Li S, Zou Q G, Chen Z Q, Wang H F. Design and characterization of metallic glass/graphene multilayer with excellent nanowear properties. Friction 10(11): 1913–1926 (2022)
[24]
Raj N, Radhika N. Tribological characteristics of LM13/Si3N4/gr hybrid composite at elevated temperature. Silicon 11(2): 947–960 (2019)
[25]
Singh K K, Singh S, Shrivastava A K. Study of tribological behavior of silicon carbide based aluminum metal matrix composites under dry and lubricated environment. Adv Mater Sci Eng 2016: 3813412 (2016)
[26]
Selvaraj V K, Jeyanthi S, Thiyagarajan R, Senthil Kumar M, Yuvaraj L, Ravindran P, Niveditha D M, Gebremichael Y B. Experimental analysis and optimization of tribological properties of self-lubricating aluminum hybrid nanocomposites using the taguchi approach. Adv Mater Sci Eng 2022: 4511140 (2022)
[27]
Ren Y, Huang Z B, Wang Y C, Zhou Q, Yang T, Li Q K, Jia Q, Wang H F. Friction-induced rapid amorphization in a wear-resistant (CoCrNi)88Mo12 dual-phase medium-entropy alloy at cryogenic temperature. Compos Part B Eng 263: 110833 (2023)
[28]
Pan S H, Yuan J, Linsley C, Liu J K, Li X C. Corrosion behavior of nano-treated AA7075 alloy with TiC and TiB2 nanoparticles. Corros Sci 206: 110479 (2022)
[29]
Sokoluk M, Cao C Z, Pan S H, Li X C. Nanoparticle-enabled phase control for arc welding of unweldable aluminum alloy 7075. Nat Commun 10(1): 98 (2019)
[30]
Pan S H, Yao G C, Sokoluk M, Guan Z Y, Li X C. Enhanced thermal stability in Cu-40 wt% Zn/WC nanocomposite. Mater Des 180: 107964 (2019)
[31]
Mahdavi S, Akhlaghi F. Effect of the graphite content on the tribological behavior of Al/gr and Al/30SiC/gr composites processed by in situ powder metallurgy (IPM) method. Tribol Lett 44(1): 1–12 (2011)
[32]
Kato H, Takama M, Iwai Y, Washida K, Sasaki Y. Wear and mechanical properties of sintered copper-tin composites containing graphite or molybdenum disulfide. Wear 255(1–6): 573–578 (2003)
[33]
Su Y F, Zhang Y S, Song J J, Hu L T. Tribological behavior and lubrication mechanism of self-lubricating ceramic/metal composites: The effect of matrix type on the friction and wear properties. Wear 372–373: 130–138 (2017)
[34]
Baradeswaran A, Perumal A E. Wear and mechanical characteristics of Al7075/graphite composites. Compos Part B Eng 56: 472–476 (2014)
[35]
Sharma P, Paliwal K, Garg R K, Sharma S, Khanduja D. A study on wear behaviour of Al/6101/graphite composites. J Asian Ceram Soc 5(1): 42–48 (2017)
[36]
Rajkumar K, Aravindan S. Tribological behavior of microwave processed copper-nanographite composites. Tribol Int 57: 282–296 (2013)
[37]
Yin Y G. Researeh on preparation and tribologieal properties of copper matrix with graphite self-lubricating materials. Ph.D. Thesis. Anhui (China): Hefei University of Techonlogy, 2006. (In Chinese)
[38]
Cao H J. The Study of preparation microstructure and properties of Cu-based self-lubricating composites. M.D. Thesis. Qinhuangdao (China): Yanshan University, 2011. (In Chinese)
[39]
Moustafa S F, El-Badry S A, Sanad A M, Kieback B. Friction and wear of copper-graphite composites made with Cu-coated and uncoated graphite powders. Wear 253(7–8): 699–710 (2002)
[40]
Jarząbek D M, Milczarek M, Wojciechowski T, Dziekoński C, Chmielewski M. The effect of metal coatings on the interfacial bonding strength of ceramics to copper in sintered Cu-SiC composites. Ceram Int 43(6): 5283–5291 (2017)
[41]
Yang X P. Research on preparation technology and the friction and wear properties of the bronze-copper coated graphite composite. M.D. Thesis. Shenyang (China): Northeastern University, 2013. (In Chinese)
[42]
Li Y Y, Zhang D T, Luo J M. P/M high aluminium-zinc alloy material and its tribological characteristics. The Chinese Journal of Nonferrous Metals 7(1): 120–124 (1997) (in Chinese)
[43]
Bhaskar S, Kumar M, Patnaik A. Silicon carbide ceramic particulate reinforced AA2024 alloy composite—Part I: Evaluation of mechanical and sliding tribology performance. Silicon 12(4): 843–865 (2020)
[44]
Ye W T, Xie M D, Huang Z B, Wang H M, Zhou Q, Wang L, Chen B, Wang H F, Liu W M. Microstructure and tribological properties of in situ carbide/CoCrFeNiMn high entropy alloy composites synthesized by flake powder metallurgy. Tribol Int 181: 108295 (2023)
[45]
Omrani E, Moghadam A D, Kasar A K, Rohatgi P, Menezes P L. Tribological performance of graphite nanoplatelets reinforced Al and Al/Al2O3 self-lubricating composites. Materials (Basel) 14(5): 1183 (2021)
[46]
Rajkumar K, Aravindan S. Tribological performance of microwave-heat-treated copper–graphite composites. Tribol Lett 37(2): 131–139 (2010)
[47]
Tabandeh-Khorshid M, Omrani E, Menezes P L, Rohatgi P K. Tribological performance of self-lubricating aluminum matrix nanocomposites: Role of graphene nanoplatelets. Eng Sci Technol Int J 19(1): 463–469 (2016)
[48]
Basavarajappa S, Chandramohan G, Mukund K, Ashwin M, Prabu M. Dry sliding wear behavior of Al2219/SiCp-Gr hybrid metal matrix composites. J Mater Eng Perform 15(6): 668–674 (2006)
[49]
Du C K. Research on preparation and tribologyical properties of copper matrix with graphite self-lubricating materials. M.D. Thesis. Hefei (China): Hefei University of Techonlogy, 2007. (In Chinese)
[50]
Bhaskar S, Kumar M, Patnaik A. Silicon carbide ceramic particulate reinforced AA2024 alloy composite—Part I: Evaluation of mechanical and sliding tribology performance. Silicon 12(4): 843–865 (2020)
[51]
Rajkumar K, Aravindan S. Effect of sliding speed on tribological properties of microwave sintered copper-graphite composites. Appl Mech Mater 592–594: 1305–1309 (2014)
[52]
Singh S, Singh G, Kumar L, Singh S. Microstructural analysis and tribological behavior of aluminum alloy reinforced with hybrid alumina/nanographite particles. Proc Inst Mech Eng Part J J Eng Tribol 229(5): 597–608 (2015)
[53]
Kumar A, Rana R S, Purohit R, Namdev A, Saxena K K, Kumar A. Optimization of dry sliding wear behavior of Si3N4 and Gr reinforced Al-Zn-Mg-Cu composites using taguchi method. J Mater Res Technol 19: 4793–4803 (2022)
[54]
Ravindran P, Manisekar K, Narayanasamy R, Narayanasamy P. Tribological behaviour of powder metallurgy-processed aluminium hybrid composites with the addition of graphite solid lubricant. Ceram Int 39(2): 1169–1182 (2013)
[55]
Ma W L, Lu J J. Effect of sliding speed on surface modification and tribological behavior of copper–graphite composite. Tribol Lett 41(2): 363–370 (2011)
[56]
Cao H Q, Qian Z Y, Zhang L, Xiao J K, Zhou K C. Tribological behavior of Cu matrix composites containing graphite and tungsten disulfide. Tribol Trans 57(6): 1037–1043 (2014)
[57]
Zheng W D, Zhang H R, Hu H Q, Liu Y, Li S Z, Ding G T, Zhang J C. Performance prediction of perovskite materials based on different machine learning algorithms. The Chinese Journal of Nonferrous Metals 29(4): 803–809 (2019) (in Chinese)
[58]
Lin H, Li L X, Wang H. Survey on research and application of support vector machines in intelligent transportation system. Journal of Frontiers of Computer Science & Technology 14(6): 901–917 (2020) (in Chinese)
[59]
Shao Y H, Deng N Y, Huang L W, Liu L M. Key issues of support vector machines and future prospects. Sci Sin-Math 50(9): 1233 (2020)
[60]
Chang S, Zhang Y C. Improved random forest algorithm based on out-of-bag prediction and extended space. Computer Engineering 48(3): 1–9 (2022)
[61]
Zhang W G, Zhang R H, Wu C Z, Goh A T C, Lacasse S, Liu Z Q, Liu H L. State-of-the-art review of soft computing applications in underground excavations. Geosci Front 11(4): 1095–1106 (2020)
[62]
Su M T, Zhang Z Y, Zhu Y, Zha D L. Data-driven natural gas spot price forecasting with least squares regression boosting algorithm. Energies 12(6): 1094 (2019)
[63]
Duan X J, Fang Z, Yang T, Guo C Y, Han Z K, Sarker D, Hou X M, Wang E H. Maximizing the mechanical performance of Ti3AlC2-based MAX phases with aid of machine learning. J Adv Ceram 11(8): 1307–1318 (2022)
Publication history
Copyright
Acknowledgements
Rights and permissions

Publication history

Received: 21 August 2023
Revised: 06 November 2023
Accepted: 18 November 2023
Published: 02 April 2024
Issue date: June 2024

Copyright

© The author(s) 2023.

Acknowledgements

We acknowledge the financial support of the National Key R&D Program of China (Grant No. 2022YFB3809000), and the Intellectual Property Program of Gansu (Grant No. 22ZSCQ043).

Rights and permissions

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