Abstract
A recent systematic experimental characterisation of technological thin films, based on elaborated design of experiments as well as probe calibration and correction procedures, allowed for the first time the determination of nanoscale friction under the concurrent influence of several process parameters, comprising normal forces, sliding velocities, and temperature, thus providing an indication of the intricate correlations induced by their interactions and mutual effects. This created the preconditions to undertake in this work an effort to model friction in the nanometric domain with the goal of overcoming the limitations of currently available models in ascertaining the effects of the physicochemical processes and phenomena involved in nanoscale contacts. Due to the stochastic nature of nanoscale friction and the relatively sparse available experimental data, meta-modelling tools fail, however, at predicting the factual behaviour. Based on the acquired experimental data, data mining, incorporating various state-of-the-art machine learning (ML) numerical regression algorithms, is therefore used. The results of the numerical analyses are assessed on an unseen test dataset via a comparative statistical validation. It is therefore shown that the black box ML methods provide effective predictions of the studied correlations with rather good accuracy levels, but the intrinsic nature of such algorithms prevents their usage in most practical applications. Genetic programming-based artificial intelligence (AI) methods are consequently finally used. Despite the marked complexity of the analysed phenomena and the inherent dispersion of the measurements, the developed AI-based symbolic regression models allow attaining an excellent predictive performance with the respective prediction accuracy, depending on the sample type, between 72% and 91%, allowing also to attain an extremely simple functional description of the multidimensional dependence of nanoscale friction on the studied variable process parameters. An effective tool for nanoscale friction prediction, adaptive control purposes, and further scientific and technological nanotribological analyses is thus obtained.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Bhushan B. Introduction to Tribology. 2nd edn. Chichester (UK): John Wiley & Sons, Ltd, 2013.
Bhushan B. Nanotribology and Nanomechanics I. Berlin (Germany): Springer, 2011.
Perčić M, Zelenika S, Mezić I, Peter R, Krstulović N. An experimental methodology for the concurrent characterization of multiple parameters influencing nanoscale friction. Friction 8(3): 577–593 (2020)
Du Q, Faber V, Gunzburger M. Centroidal Voronoi Tessellations: Applications and algorithms. SIAM Rev 41(4): 637–676 (1999)
Mandel J, Mansfield J E. The statistical analysis of experimental data. Phys Today 18(9): 66–68 (1965)
Kecman V. Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models. Cambridge (USA): MIT Press, 2001.
de Silva B M, Higdon D M, Brunton S L, Kutz J N. Discovery of physics from data: Universal laws and discrepancies. Front Artif Intell 3: 1–25 (2020)
Zaki M J, Meira W. Data Mining and Analysis, Cambridge (UK): Cambridge University Press, 2014.
Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning. 2nd edn. New York (USA): Springer-Verlag, 2009.
Billard L, Diday E. Symbolic Data Analysis: Conceptual Statistics and Data Mining. Chichester (UK): John Wiley & Sons, 2012.
Worzel B, Riolo R. Genetic Programming Theory and Practice. Boston (MA, USA): Springer US, 2003.
Koza J R. Human-competitive results produced by genetic programming. Genet Program Evolvable Mach 11(3–4): 251–284 (2010)
Langdon W B, Poli R. Foundations of Genetic Programming. Berlin Heidelberg (Germany): Springer-Verlag Berlin Heidelberg, 2002.
Schmidt M, Lipson H. Distilling free-form natural laws from experimental data. Science 324(5923): 81–85 (2009)
Witten I H, Frank E, Hall M A. Data Mining: Practical Machine Learning Tools and Techniques. 3rd edn. Amsterdam (the Netherlands): Elsevier, 2011.
Gentle J E. Random Number Generation and Monte Carlo Methods, New York (USA): Springer, 1998.
Information. http://www.gosumd.com/, 2020.
Draper N R, Smith H. Applied Regression Analysis. 3rd edn. New York (NY, USA): John Wiley & Sons, 1998.
Knowles J, Corne D, Deb K, Eds. Multiobjective Problem Solving from Nature. Berlin Heidelberg (Germany): Springer-Verlag Berlin Heidelberg, 2008.
Lotov A, Bushenkov VA, Kamenev GK. Interactive Decision Maps. Boston (USA): Springer US, 2004.
Waszczyszyn Z. Fundamentals of Artificial Neural Networks. In Neural Networks in the Analysis and Design of Structures. Z Waszczyszyn, Ed. Vienna (Austria): CISM International Centre for Mechanical Sciences 1999: 1–51.
Zhang C, Ma Y, Eds. Ensemble Machine Learning, New York (USA): Springer-Verlag New York, 2012.
Ma Y, Guo G, Eds. Support Vector Machines Applications. Cham (Switzerland): Springer International Publishing, 2014.
Kang D L, Wang X H, Zheng X J, Zhao Y P. Predicting the components and types of kerogen in shale by combining machine learning with NMR spectra. Fuel 290: 120006 (2021)
Information. https://arxiv.org/abs/1603.04467, 2015.
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, et al. Scikit-learn: Machine learning in Python. J Mach Learn Res 12(85): 2825–2830 (2011)
Ziebert C, Gahr K H Z. Microtribological properties of two-phase Al2O3 ceramic studied by AFM and FFM in air of different relative humidity. Tribol Lett 17(4): 901–909 (2004)
Koza J R. Genetic Programming. Cambridge (USA): MIT Press, 1992.
Ryan C, O’Neill M, Collins JJ, Eds. Handbook of Grammatical Evolution. Cham (Switzerland): Springer International Publishing, 2018.
Affenzeller M, Wagner S. Offspring Selection: A new self-adaptive selection scheme for genetic algorithms. In Adaptive and Natural Computing Algorithms. Ribeiro B, Albrecht R F, Dobnikar A, Pearson D W, Steele N C, Eds. Vienna (Austria): Springer, 2005: 218–221
Derjaguin B V, Muller V M, Toporov Y P. Effect of contact deformations on the adhesion of particles. J Colloid Interface Sci 53(2): 314–326 (1975)
Dagdeviren O E. Exploring load, velocity, and surface disorder dependence of friction with one-dimensional and two-dimensional models. Nanotechnology 29(31): 315704 (2018)
Ouyang W G, Ramakrishna S, Rossi A, Urbakh M, Spencer N, Arcifa A. Load and velocity dependence of friction mediated by dynamics of interfacial contacts. Phys Rev Lett 123(11): 116102 (2019)
Tambe N S, Bhushan B. Friction model for the velocity dependence of nanoscale friction. Nanotechnology 16(10): 2309–2324 (2005)
Al-Bender F, Lampaert V, Swevers J. Modeling of dry sliding friction dynamics: From heuristic models to physically motivated models and back. Chaos Interdiscip J Nonlinear Sci 14(2): 446–460 (2004)
Worden K, Wong C X, Parlitz U, Hornstein A, Engster D, Tjahjowidodo T, Al-Bender F, Rizos D, Fassois S D. Identification of pre-sliding and sliding friction dynamics: Grey box and black-box models. Mech Syst Signal Process 21(1): 514–534 (2007)
Carpick R W, Plesha M E. Development and integration of single-asperity nanotribology experiments & nanoscale interface finite element modeling for prediction and control of friction and damage in micro- and nano-mechnical systems. Madison (USA): University Wisconsin-Madison, 2007.
Xu Y, Jackson R L. Boundary element method (BEM) applied to the rough surface contact vs. BEM in computational mechanics. Friction 7(4): 359–371 (2019)
Brodnik Zugelj B, Kalin M. Submicron-scale experimental analyses of the multi-asperity contact behaviour of various steels, an aluminium alloy and a polymer. Tribol Int 141: 105955 (2020)
Santhapuram R R, Nair A K. Frictional properties of multi-asperity surfaces at the nanoscale. Comput Mater Sci 136: 253–263 (2017)
Buzio R, Boragno C, Biscarini F, Buatier de Mongeot F, Valbusa U. The contact mechanics of fractal surfaces. Nat Mater 2(4): 233–236 (2003)
You J M, Chen T N. A static friction model for the contact of fractal surfaces. Proc Inst Mech Eng Part J: J Eng Tribol 224(5): 513–518 (2010)
Johnson K L. A Continuum Mechanics Model of Adhesion and Friction in a Single Asperity Contact. In Micro/Nanotribology and Its Applications. Bhushan B, Ed. Dordrecht (the Netherlands): Springer, 1997: 151–168
Mergel J C, Sahli R, Scheibert J, Sauer R A. Continuum contact models for coupled adhesion and friction. J Adhesion 95(12): 1101–1133 (2019)
Barber J R. Multiscale surfaces and Amontons’ law of friction. Tribol Lett 49(3): 539–543 (2013)
Waddad Y, Magnier V, Dufrénoy P, De Saxcé G. Multiscale thermomechanical modeling of frictional contact problems considering wear — Application to a pin-on-disc system. Wear 426–427: 1399–1409 (2019)
Information. https://www.molbnl.it/, 2020.
Acknowledgements
The work described in this paper is enabled by using the equipment funded via the EU European Regional Development Fund project entitled “Research Infrastructure for Campus-based Laboratories at the University of Rijeka — RISK” (Project RC.2.2.06-0001), as well as via the support of the University of Rijeka, Croatia, grant entitled “Advanced mechatronics devices for smart technological solutions” (Grant uniri-tehnic-18-32).
Author information
Authors and Affiliations
Corresponding author
Additional information
Marko PERČIĆ. He earned his M.Sc. degree in 2012 and his D.Sc. degree in 2020 at the Faculty of Engineering of the University of Rijeka, Croatia. He is currently a postdoc at the Faculty of Engineering, Head of the Laboratory for Artificial Intelligence in Mechatronics at the Center for Artificial Intelligence and Cybersecurity, and a staff member of the Centre for Micro- and Nanosciences and Technologies of the University of Rijeka. His research interests are in experimental nanotribology, atomic force microscopy, thin films, mathematical modeling, and data mining.
Saša ZELENIKA. He graduated from the University of Rijeka, Croatia, and attained his D.Sc. degree at the Polytechnic University of Turin, Italy. He was Head of Mechanical Engineering at the Paul Scherrer Institute in Switzerland. From 2004, he is a faculty member of the University of Rijeka, Faculty of Engineering (since 2015 full professor with tenure) where he was Dean’s Assistant, Department Head, and is Laboratory Head. In 2012–2014, he was Assistant and then Deputy Minister at the Croatian Ministry of Science, Education and Sports. Currently, he is Rector’s Assistant, Head of the Scientific Council, and Deputy Head of the Centre for Micro- and Nanoscience and Technologies at the University of Rijeka. He is a member of the Croatian Academy of Engineering. His research interests encompass precision engineering as well as micro- and nanosystems technologies.
Igor MEZIĆ. He graduated from the University of Rijeka, Croatia and got his Ph.D. degree from Caltech. He was a postdoctoral fellow at the University of Warwick, UK, joined the University of California (UC), Santa Barbara, USA, and moved to Harvard University before returning to UC Santa Barbara, where he became a full professor in 2003. He holds numerous awards and honors in the fields of physics, mathematics (Sloan Fellowship), and engineering. He is a Fellow of the American Physical Society and of the Society for Industrial and Applied Mathematics. He holds 8 US patents, and 3 technological companies (Ecorithm, iFluidics, and Aimdyn) were founded on the basis of his patents and algorithms. He is currently a professor at the Department of Mechanical Engineering at UC Santa Barbara and a Chief Scientist at Packetsled, Inc. His research interests are in developments in operator theory, machine learning, and artificial intelligence.
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/.
About this article
Cite this article
Perčić, M., Zelenika, S. & Mezić, I. Artificial intelligence-based predictive model of nanoscale friction using experimental data. Friction 9, 1726–1748 (2021). https://doi.org/10.1007/s40544-021-0493-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40544-021-0493-5