Ventilation diagnosis of minigrinders using thermal images

A technique of analysis of thermal images of minigrinders is presented in the paper. The following states of minigrinders were analyzed: healthy minigrinder (HM), minigrinder with 2 blocked air vents (M2BAV), and minigrinder with 4 blocked air vents (M4BAV). The thermal imaging camera was shivering vertically (0-1.5 [m/ s2]). Two methods are proposed for the computation of essential areas of thermal images: DTILE (Differences of Thermal Images using Local Entropy), and DPTILE (Differences of Power of Thermal Images using Local Entropy). The computed areas are compared to each other using the Nearest Neighbor. Moreover, verification of the analysis of thermal images was carried out for the convolutional neural networks GoogLeNet and ResNet-50. The analyzed approaches were proper for fault diagnosis. The efficiency of recognition is equal to 100% for the three analyzed classes. The presented approach can be also used in the industry.