Fault diagnosis of electric impact drills using thermal imaging

Fault diagnosis enables to make savings related to maintenance. The presented work describes fault diagnosis method based on analysis of thermal images. An original method for feature extraction of thermal images BCAoID (Binarized Common Areas of Image Differences) is proposed. Thermal images of three electric impact drills (EID) were used for an analysis: healthy EID, EID with faulty fan (10 broken fan blades), EID with damaged gear train. Features of thermal images were extracted using the BCAoID. The computed features were analyzed using the Nearest Neighbor classifier and the backpropagation neural network. The recognition results of the performed analysis were in the range of 97.91-100%. Fault diagnosis based on thermal images can find application for protecting of rotating machinery and engines.

Automated summary

Fault diagnosis based on thermal images can help save maintenance costs. The method proposed in this work extracts features from thermal images using the BCAoID method, achieving high recognition accuracy for different faults in electric impact drills. This approach can be applied for protecting rotating machinery and engines.