A data mining approach for fault diagnosis: An application of anomaly detection algorithm

• Published in: Measurement : journal of the International Measurement Confederation Vol. 55; pp. 343 - 352
• Main Authors: Purarjomandlangrudi, Afrooz, Ghapanchi, Amir Hossein, Esmalifalak, Mohammad
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.09.2014
• Subjects: Anomaly detection; Data mining; Fault diagnosis; Machine learning; Support Vector Machine; Fault diagnosis; Support Vector Machine; Data mining; Anomaly detection; Machine learning
• ISSN: 0263-2241; 1873-412X
• DOI: 10.1016/j.measurement.2014.05.029

•A data mining approach called anomaly detection was presented for fault detection.•Two features, kurtosis and Non-Gaussianity Score (NGS) are extracted from raw data.•Both anomaly detection and SVM techniques are applied on these features.•Results show AD has the ability to detect the incipient faults sooner than the SVM.•AD has higher accuracy and sensitivity than the SVM in fault diagnosis. Rolling-element bearing failures are the most frequent problems in rotating machinery, which can be catastrophic and cause major downtime. Hence, providing advance failure warning and precise fault detection in such components are pivotal and cost-effective. The vast majority of past research has focused on signal processing and spectral analysis for fault diagnostics in rotating components. In this study, a data mining approach using a machine learning technique called anomaly detection (AD) is presented. This method employs classification techniques to discriminate between defect examples. Two features, kurtosis and Non-Gaussianity Score (NGS), are extracted to develop anomaly detection algorithms. The performance of the developed algorithms was examined through real data from a test to failure bearing. Finally, the application of anomaly detection is compared with one of the popular methods called Support Vector Machine (SVM) to investigate the sensitivity and accuracy of this approach and its ability to detect the anomalies in early stages.