A combination of support vector machine and k-nearest neighbors for machine fault detection

Abstract

This article presents a combination of support vector machine (SVM) and k-nearest neighbor (k-NN) to monitor rotational machines using vibrational data. The system is used as triage for human analysis and, thus, a very low false negative rate is more important than high accuracy. Data are classified using a standard SVM, but for data within the SVM margin, where misclassifications are more like, a k-NN is used to reduce the false negative rate. Using data from a month of operations of a predictive maintenance company, the system achieved a zero false negative rate and accuracy ranging from 75% to 84% for different machine types such as induction motors, gears, and rolling-element bearings. © 2013 Copyright Taylor and Francis Group, LLC.