11-08-2023 дата публикации
Номер: CN116577037A
Принадлежит:
The invention provides an air pipe leakage signal detection method based on a non-uniform frequency spectrogram. The method comprises the following steps: S1, collecting air pipe leakage sound or vibration data; s2, performing high-pass filtering on the acquired signal to suppress low-frequency noise; s3, carrying out fast Fourier transform on the acquired signal to find a high-frequency key feature interval; s4, performing non-uniform frequency expansion on the frequency domain signal to generate a spectrogram expressed by non-uniform frequency, processing characteristic signals in different frequency intervals by adjusting function parameters, and extracting key characteristics of the signals; and S5, constructing a DA-YOLO5 neural network model for training, and obtaining an air duct leakage signal detection model. According to the air pipe leakage signal detection method based on the non-uniform frequency spectrogram, the spectrogram expressed by the non-uniform frequency is generated ...
Подробнее