Machine learning (ML) techniques are used to predict the coefficient of friction of an epoxy polymer resin (SU-8) and its composite coatings deposited on a silicon wafer. Filler type and the number of cycles are taken as the input parameters. The filler types included, two solid fillers namely, graphite and talc, and a liquid filler such as Perfluoropolyether (PFPE). Six variations of the SU8 coatings were developed based on the different combinations of filers used and tested. The experimental data generated for these different coatings for varying number of cycles (0 to 499) was used to train the different ML algorithms like ANN, SVM, CART, and RF to predict the coefficient of friction. The performance of these ML techniques was compared by calculating mean absolute error (MAE), root means square error (RMSE), and square of the correlation coefficient (R2). The ANN algorithm was observed to have the best (R2) metrics while the other ML techniques SVM, CART, and RF had a satisfactory performance with some inaccuracies seen for the CART algorithm for the data set under consideration.
HaoYZhangD. Silicon-based MEMS process and standardization. Proc 7th Int Conf Solid-State Integr Circuits Technol2004; 3: 1835–1838.
2.
MaboudianRAshurstWRCarraroC. Tribological challenges in micromechanical systems. Tribol Lett2002; 12: 95–100.
3.
LauKHGiridharAHarikrishnanS,et al.Releasing high aspect ratio SU-8 microstructures using AZ photoresist as a sacrificial layer on metallized Si substrates. Microsyst Technol2013; 19: 1863–1871.
4.
KatiyarJKSinhaSKHirayamaT,et al.Tribological analysis of tip-cantilever made of SU-8, talc and PFPE composite. Tribol Mater Surf Interfaces2020; 14: 92–101.
5.
BertschARenaudP. Special issue: 15 years of SU8 as MEMS material. Micromachines (Basel)2015; 6: 790–792.
6.
BaeJ-SOhC-SNamJ-E,et al.A tensile test technique for the freestanding PMMA thin films. Curr Appl Phys2009; 9: S107–S109.
7.
SpikesH. Tribology research in the twenty-first century. Tribol Int2001; 34: 789–799.
8.
KimSHAsayDBDuggerMT. Nanotribology and MEMS. Nano Today2007; 2: 22–29.
9.
SaravananPSatyanarayanaNMinhDH,et al.An in-situ heating effect study on tribological behavior of SU-8 + PFPE composite. Wear2013; 307: 182–189.
10.
SaravananPSatyanarayanaNSinhaSK. Wear durability study on self-lubricating SU-8 composites with perfluoropolyther, multiply-alkylated cyclopentane and base oil as the fillers. Tribol Int2013; 64: 103–115.
11.
SaravananPSatyanarayanaNSinhaSK. Self-lubricating SU-8 nanocomposites for microelectromechanical systems applications. Tribol Lett2013; 49: 169–178.
12.
JiguetSBertschAJudelewiczM,et al.SU-8 nanocomposite photoresist with low stress properties for microfabrication applications. Microelectron Eng2006; 83: 1966–1970.
13.
JiguetSJudelewiczMMischlerS,et al.Effect of filler behavior on nanocomposite SU8 photoresist for moving micro-parts. Microelectron Eng2006; 83: 1273–1276.
14.
JiguetSJudelewiczMMischlerS,et al.SU-8 nanocomposite coatings with improved tribological performance for MEMS. Surf Coatings Technol2006; 201: 2289–2295.
15.
HirwaniJKSinhaSK. Mechanical and Tribological Studies of SU-8 Composites Filled With UHMWPE and Gum Acacia Under Dry and Bovine Serum Albumin Lubricated Conditions. J Tribol2021; 143. https://doi.org/10.1115/1.4047585
16.
BatooliLMaldonadoSGJudelewiczM,et al.Novel SU-8/ionic liquid composite for tribological coatings and MEMS. Micromachines (Basel)2015; 6: 611–621.
17.
RathaurASKatiyarJKPatelVK. Thermo-mechanical and tribological properties of SU-8/h-BN composite with SN150/perfluoropolyether filler. Friction2020; 8: 151–163.
18.
ArshadKAHirwaniJKSinhaSK. Effects of UHMWPE filler on the tribological and mechanical properties of biocompatible epoxies. Tribol Trans2020; 63: 382–392.
19.
HirwaniJKNishimuraRShinmoriH,et al.Epoxy (SU-8) polymer composites with ultra-high molecular weight polyethylene and hyaluronic acid fillers for hip prosthetic implant application. Tribol Int2022; 167: 107399.
20.
KatiyarJKSinhaSKKumarA. In situ lubrication of SU-8/talc composite with base oil (SN150) and perfluoropolyether as fillers. Tribol Lett2016; 64: 5.
21.
KatiyarJKSinhaSKKumarA. Friction and wear durability study of epoxy-based polymer (SU-8) composite coatings with talc and graphite as fillers. Wear2016; 362–363: 199–208.
22.
KatiyarJKMohammedAS. Physical, tribological and mechanical properties of polymer composite coating on silicon wafer. Tribol Int2022; 165: 107307.
23.
MilosevicMValášekPRuggieroA. Tribology of natural fibers composite materials: an overview. Lubricants2020; 8: 42.
24.
GrützmacherPGProfitoFJRosenkranzA. Multi-scale surface texturing in tribology—current knowledge and future perspectives. Lubricants2019; 7: 95.
25.
DemirbaşTBaykaraMZ. Nanoscale tribology of graphene grown by chemical vapor deposition and transferred onto silicon oxide substrates. J Mater Res2016; 31: 1914–1923.
26.
LuoDBFridriciVKapsaP. A systematic approach for the selection of tribological coatings. Wear2011; 271: 2132–2143.
27.
ZhangZYinNChenS,et al.Tribo-informatics: concept, architecture, and case study. Friction2021; 9: 642–655.
28.
Satish KumarDRajmohanM. Optimizing wear behavior of epoxy composites using response surface methodology and artificial neural networks. Polym Compos2019; 40: 2812–2818.
29.
RaySKumar RoutAKumar SahooA. A comparative analysis of the abrasion wear characteristics of industrial wastes filled glass/polyester composites based on the design of experiment and neural network. Polym Compos2021; 42: 424–438.
30.
VelmuruganCSubramanianRThirugnanamS,et al.Experimental study and prediction using ANN on mass loss of hybrid composites. Ind Lubr Tribol2012; 64: 138–146.
31.
GangwarSPathakVK. Dry sliding wear characteristics evaluation and prediction of vacuum casted marble dust (MD) reinforced ZA-27 alloy composites using hybrid improved bat algorithm and ANN. Mater Today Commun2020; 25: 101615.
32.
ChangLZhangZYeL,et al.CHAPTER 3 - Synergistic effects of nanoparticles and traditional tribo-fillers on sliding wear of polymeric hybrid composites. In: SchlarbAKFriedrichK (eds) Tribology of polymeric nanocomposites - friction and wear of bulk materials and coatings. Elsevier, 2008, pp. 35–61. https://doi.org/10.1016/S1572-3364(08)55003-8.
33.
ArgatovIIChaiYS. An artificial neural network supported regression model for wear rate. Tribol Int2019; 138: 211–214.
34.
AgarwalMKumar SinghMSrivastavaR,et al.Microstructural measurement and artificial neural network analysis for adhesion of tribolayer during sliding wear of powder-chip reinforcement based composites. Measurement2021; 168: 108417.
35.
RamprasadRBatraRPilaniaG,et al.Machine learning in materials informatics: recent applications and prospects. Npj Comput Mater2017; 3: 54.
36.
BorjaliAMonsonKRaeymaekersB. Predicting the polyethylene wear rate in pin-on-disc experiments in the context of prosthetic hip implants: deriving a data-driven model using machine learning methods. Tribol Int2019; 133: 101–110.
37.
HasanMSKordijaziARohatgiPK,et al.Machine learning models of the transition from solid to liquid lubricated friction and wear in aluminum-graphite composites. Tribol Int2022; 165: 107326.
38.
HasanMSKordijaziARohatgiPK,et al.Triboinformatics approach for friction and wear prediction of Al-graphite composites using machine learning methods. J Tribol2022; 144: 1–13.
39.
BhaumikSKamarajM. Artificial neural network and multi-criterion decision making approach of designing a blend of biodegradable lubricants and investigating its tribological properties. Proc Inst Mech Eng Part J J Eng Tribol2021; 235: 1575–1589.
40.
SamadMASatyanarayanaNSinhaSK. Effect of air–plasma Pre-treatment of si substrate on adhesion strength and tribological properties of a UHMWPE film. J Adhes Sci Technol2010; 24: 2557–2570.
Simon H. Neural networks: A comprehensive foundation. 2nd ed. Upper Saddle River, NJ: Prentice Hall, 199, pp. 1–823.
43.
GyurovaLAFriedrichK. Artificial neural networks for predicting sliding friction and wear properties of polyphenylene sulfide composites. Tribol Int2011; 44: 603–609.
44.
LiSShaoMDuanC,et al.Tribological behavior prediction of friction materials for ultrasonic motors using Monte Carlo-based arti fi cial neural network. J Appl Polym Sci2019; 136: 47157.
45.
SmolaAJSchölkopfB. A tutorial on support vector regression. Stat Comput2004; 14: 199–222.
46.
Maimon OZ and Rokach L. Data mining with decision trees: theory and applications. Series in Machine Perception and Artificial Intelligence, World Sci, 2014, vol. 81, pp. 1–328.
47.
BreimanL. Random forests. Mach Learn2001; 45: 5–32.
