Fault diagnosis of roller bearings using selected classifiers

Abstract

Minor roller bearing damage may lead to serious failures of the de-vice. Thus, it is very important to detect such damage as early as possible to prevent further damage. This paper presents a selection of several theoretical tools from the field of artificial intelligence and their application in roller bearings fault classification. The considered tools are: k-nearest neighbour algorithm, decision tree, support vector machine, feed forward neural network (multilayer perceptron), Bayesian network and neural network with radial basis functions. All numerical experiments presented in the paper were performed with the use of real-world dataset and WEKA (Waikato Environment for Knowledge Analysis) software, available at the server of the University of Waikato.