Thermal image based fault diagnosis for rotating machinery

Infrared imaging is crucial for condition monitoring as the thermographic patterns will differ depending on the fault or machine condition. Currently, a limited number of machine faults have been studied using thermal imaging. Therefore, this paper proposes a novel automatic fault detection system using infrared imaging, focussing on bearings of rotating machinery. The set of bearing faults monitored contain faults for which state-of-the-art techniques have no general solutions such as bearing-lubricant starvation. For each fault, several recordings are made using different bearings to ensure generalization of the fault-detection system. The system contains two image-processing pipelines, each with their own respective purposes. The first pipeline focusses on detecting rotor imbalance, regardless of the bearing faults. The second pipeline focusses on the bearing faults, regardless of whether the machine is balanced or not. Within the first pipeline, imbalance is detected by differencing the consecutive image frames which are subsequently summarized by their distribution along the image axes. For the second pipeline, three features are introduced which are the standard deviation of the temperature, the Gini coefficient, and the Moment of Light. The final system is able to distinguish between all eight different conditions with an accuracy of 88.25%. (C) 2015 Elsevier B.V. All rights reserved.