19th Asia-Pacific Vibration Conference (APVC2021)

107 / 2021-03-30 15:53:58

Visual recognition method of air leaking signal based on convolutional neural network

Visualization of acoustic signals,CNN,Leaking detection,real-time

Special Sessions > Applications of machine learning in vibration and noise problems

Acoustic signal detection to achieve high accuracy and real-time performance has always been an important issue in the field of acoustics. Convolutional neural network is a new type of artificial neural network method that combines artificial neural network and deep learning technology, and has been widely used in the field of image recognition. In this paper, using the visualization of acoustic signals combined with image recognition methods of convolutional neural networks, an artificial intelligence-based gas leaking signal detection method is proposed.This method converts the acoustic signal into a spectrogram, and uses the convolutional neural network as the input to train, and obtains a gas leaking recognition model with high recognition accuracy. The experimental results show that the model can be accurate, reliable, and real-time online detection of whether there is a gas leaking.