LS-SVM Approach for Predicting Frictional Performance of Industrial Brake Pad Materials

N. S. M. Eltayb 1 and Abeer Hamdy2
1. British University in Egypt, Elshorouk City, Egypt
2. British University in Egypt, Electronics Research Institute, Egypt
Abstract—Modeling frictional performance of a break pad material is difficult and requires the use of complex numerical models. The current work utilizes one of the Artificial Intelligence techniques, Least Squares Support Vector Machine (LS-SVM), to model the nonlinear relationships between the input breaking conditions and the frictional and thermal performance of previously developed non-commercial brake pad materials. Experimental data were produced and used in training and testing the proposed LS-SVM models. The results indicate that LS-SVM constitutes a robust methodology and the proposed models could be used to predict the friction coefficients and the induced interface temperature of brake pad materials in order to reduce experimental time and cost. 

Index Terms—Support vector machine, Regression, Friction performance, Break pad materials, material Informatics, machine learning.

Cite: N. S. M. Eltayb and Abeer Hamdy, "LS-SVM Approach for Predicting Frictional Performance of Industrial Brake Pad Materials," International Journal of Mechanical Engineering and Robotics Research, Vol. 7, No. 2, pp. 105-112, March 2018. DOI: 10.18178/ijmerr.7.2.105-112
Copyright © 2016-2017 International Journal of Mechanical Engineering and Robotics Research, All Rights Reserved
E-mail: ijmerr@ejournal.net