Using Machine Learning Radial Basis Function (RBF) Method for Predicting Lubricated Friction on Textured and Porous Surfaces
- 18 November 2020
- journal article
- research article
- Published by IOP Publishing in Surface Topography: Metrology and Properties
- Vol. 8 (4) , 044002
Abstract
The coefficient of friction (CoF) obtained from tribological tests conducted on textured and porous surfaces was analysed using the machine learning Radial Basis Function (RBF) method. Non-textured and non-porous samples were taken as reference surfaces. Test parameters, such as entrainment velocity and slide-roll ratio (SRR), along with geometric characteristics of surface features (e.g. texture width and depth, coverage area, circularity, spatial distribution and directionality, among others), were selected as training dataset for the machine learning RBF model. The surface features were divided into designed patterns (dimples and grooves) manufactured by laser texturing, and randomised cavities (surface pores) resulted from the sintering process. The principal outcomes of this study are the effective use of the machine learning RBF method for tribological applications, as well as a critical discussion on its feasibility for the experimental dataset selected and the preliminary results obtained. Main results show that the Hardy multiquadric radial basis function provided an overall correlation coefficient of 0.934 for 35 poles. The application of the suggested machine learning technique and methodology can be extended to other experimental results available in the literature to train more robust models for predicting tribological performances of textured and structured surfaces.Keywords
Funding Information
- Österreichische Forschungsförderungsgesellschaft (Austrian COMET Project K2)
- Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP grant N. 2016/25067-9 and 2017/21151-8)
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
This publication has 33 references indexed in Scilit:
- Prediction of tribological behavior of aluminum–copper based composite using artificial neural networkJournal of Alloys and Compounds, 2009
- Prediction on wear properties of polymer composites with artificial neural networksComposites Science and Technology, 2007
- Modelling of the prediction of tensile and density properties in particle reinforced metal matrix composites by using neural networksMaterials & Design (1980-2015), 2006
- Fundamental investigations on the spark plasma sintering/synthesis processMaterials Science and Engineering: A, 2005
- Learning methods for radial basis function networksFuture Generation Computer Systems, 2005
- Prediction on tribological properties of short fibre composites using artificial neural networksWear, 2002
- A new class of radial basis functions with compact supportMathematics of Computation, 2000
- Radial basis functionsActa Numerica, 2000
- Interpolation of scattered data: Distance matrices and conditionally positive definite functionsConstructive Approximation, 1986
- A Theory of Lubrication by MicroirregularitiesJournal of Basic Engineering, 1966