Optimization and prediction of tribological behaviour of filled polytetrafluoroethylene composites using Taguchi Deng and hybrid support vector regression models

Musa Alhaji Ibrahim; Hüseyin Çamur; Mahmut A Savaş; S I Abba

doi:10.1038/s41598-022-14629-5

Optimization and prediction of tribological behaviour of filled polytetrafluoroethylene composites using Taguchi Deng and hybrid support vector regression models

Sci Rep. 2022 Jun 21;12(1):10393. doi: 10.1038/s41598-022-14629-5.

Authors

Musa Alhaji Ibrahim^{1

2}, Hüseyin Çamur³, Mahmut A Savaş³, S I Abba⁴

Affiliations

¹ Mechanical of Engineering Department, Faculty of Engineering, Kano University of Science and Technology, Wudil KM 50, Kano, Gaya Road, Wudil P.M.B 3244, Kano, Kano, Nigeria. musaibrahim@kustwudil.edu.ng.
² Mechanical Engineering Department, Faculty of Engineering, Near East University, via Mersin 10, 99138, Nicosia, Turkey. musaibrahim@kustwudil.edu.ng.
³ Mechanical Engineering Department, Faculty of Engineering, Near East University, via Mersin 10, 99138, Nicosia, Turkey.
⁴ Interdisciplinary Research Center for Membrane and Water Security, King Fahd University of Petroleum and Minerals, Dhahran, 31261, Saudi Arabia.

Abstract

This study presents optimization and prediction of tribological behaviour of filled polytetrafluoroethylene (PTFE) composites using hybrid Taguchi and support vector regression (SVR) models. To achieve the optimization, Taguchi Deng was employed considering multiple responses and process parameters relevant to the tribological behaviour. Coefficient of friction (µ) and specific wear rate (K_s) were measured using pin-on-disc tribometer. In this study, load, grit size, distance and speed were the process parameters. An L₂₇ orthogonal array was applied for the Taguchi experimental design. A set of optimal parameters were obtained using the Deng approach for multiple responses of µ and K_S. Analysis of variance was performed to study the effect of individual parameters on the multiple responses_. To predict µ and Ks, SVR was coupled with novel Harris Hawks' optimization (HHO) and swarm particle optimization (PSO) forming SVR-HHO and SVR-PSO models respectively, were employed. Four model evaluation metrics were used to appraise the prediction accuracy of the models. Validation results revealed enhancement under optimal test conditions. Hybrid SVR models indicated superior prediction accuracy to single SVR model. Furthermore, SVR-HHO outperformed SVR-PSO model. It was found that Taguchi Deng, SVR-PSO and SVR-HHO models led to optimization and prediction with low cost and superior accuracy.