Anticipating the friction coefcient of friction materials used in automobiles by means of machine learning without using a test instrument

Abstract

The most important factor for designs in which friction materials are used is the coeffcient of friction. The coeffcient of friction has been determined taking such variants as velocity, temperature, and pressure into account, which arise from various factors in friction materials, and by analyzing the effects of these variants on friction materials. Many test instruments have been produced in order to determine the coeffcient of friction. In this article, a study about the use of machine learning algorithms instead of test instruments in order to determine the coeffcient of friction is presented. Isotonic regression was selected as the machine learning method in determining the coeffcient of friction. The correlation coeffcient between the results of isotonic regression algorithms and the results taken from the test instruments was measured as 0.9999 and the root mean squared error was 0.0014 in the experiments conducted. Selection of the number of optimum samples was enabled by taking biasfvariance tradeoff into account, and this increased the performance of the classifier in use. The target of this study was to prevent the practice of time-consuming test activities by using machine learning methods instead of test instruments in determining the friction coeffcient. This presents a solution for decreasing the factors of time and cost.