A Study on Gear Defect Detection via Frequency Analysis Based on DNN

In this paper, we introduce a gear defect detection system using frequency analysis based on deep learning. The existing diagnosis systems acoustic use spectrogram, scalogram, and MFCC (Mel-Frequency Cepstral Coefficient) images as inputs to the convolutional neural network (CNN) model diagnose defects. However, visualized data input CNN models requires lot of computation time. Although computing power has improved, there is situation in which processor with low performance used for reasons such cost-effectiveness. only sums bands are (DNN) fault. This diagnoses defects few specific bands, so it ignores unnecessary does not require high when diagnosing because uses relatively simple learning classification. We evaluate proposed through experiments verify that real-time gears possible compared model. result showed 95.5% accuracy 1000 test data, took 18.48 ms, verified capability low-spec environment. expected be effectively various sound-based facilities at cost.