Application of basic machine learning algorithms in railway brake disc temperature prediction

Abstract

This article is focused on brake disc temperature prediction introducing basic machine learning algorithms to reach this goal. In the first part, the problematics of brake disc frictional heating is described. Next, the methods currently used for predicting/calculating are described as well as their pros and cons. In the following part, some basic machine learning algorithms are described only very briefly, since going into details of theories of those algorithms in this article would extend it significantly. In the last part, the experiment with small dataset is described and its results and future possible work are discussed.