Validation of the Validity of Spectrogram Contour Neural Network - Applied to Inrush Current Classification of Transformer

In this study, in order to effectively analyze the state of the devices using one-dimensional time-series data generated from industrial devices, a new learning method was designed based on Short-Time Fourier Transform (STFT), and its validity was verified. The proposed learning method is a method of extracting contour lines with a preset threshold before applying a 2D spectrogram image to a deep neural network. As such, the contour transformation of the spectrogram image of the frequency distribution is to extract the characteristics of the frequency, so it will be effective in improving the performance of learning. In order to verify the validity of the proposed contour neural network, Learning was conducted as a pre-study, using the time series values of the chaotic system with nonlinear high-dimensional characteristics as a data set, and it was confirmed that the learning rate rapidly increased at a specific contour line. © 2021 The Korean Institute of Electrical Engineers.