Machine’s Condition Monitoring and Fault Diagnostics using Thermal Imaging

Abstract

In this study, two approaches have been proposed to validate machine condition monitoring and diagnosis using thermal imaging. An experimental test rig that represents the machine in real condition was setup to produce thermal images and monitor the conditions as well. The first approach subjected to fault diagnosis of rotating machine based on thermal image investigation using image histogram features is proposed in this work. Herein, the machine learning and statistical approach are adopted along with thermal image signal to machine condition diagnosis. The result shows that classification process of histogram thermal image features by support vector machine and other classifiers can serve machine fault diagnosis. Another proposed method, intelligent diagnosis system (IDS), is to classify the different machine’s condition from infrared thermography. The multi-step feature selections algorithms are employed as the core of IDS. Finally, comparative assessment of IDS shows that two types of classifier fed with identical features set obtained after multi step feature selection processes, may result in an accurate system able to assist diagnosis of different machine conditions