Image Histogram Features Based Thermal Image Retrieval to Pattern Recognition of Machine Condition

Abstract

Thermal image investigation has exposed up to date and remote diagnosis of machine condition which is very important part of industry maintenance. By using thermal image, the information of machine condition can be investigated; it is easier than other conventional methods of machine condition monitoring. In the current work, the behaviour of thermal image is investigated with different condition of machine. A test-rig that represents the machine in industry was set up to produce thermal image data in experiment. Some significant features have been extracted and selected by means of PCA and ICA and other irrelevant features have been discarded. The aim of this study is to retrieve thermal image by means of selecting proper feature to recognize the fault pattern of the machine. The result shows that classification process of thermal image features by SVM and other classifier can serve for machine fault diagnosis.