In order to solve the technical problems of distributed acoustic sensor(DAS)system in many kinds of acoustic signal recognition, In this paper, an implementation path of acoustic signal machine recognition technology is proposed, which realizes the voice print and acoustic wave restoration of DAS machine recognition, and improves the quality of recognition and restoration.. Methods by preprocessing the optical fiber signal caused by sound, including signal framing, windowing, short-time Fourier transform and signal enhancement, the signal was transformed into a spectrogram, and the convolution neural network (CNN) was used to train the 13400 datas collected from the scene to machine judge the four types of acoustic signals: mechanical excavation, manual operation, vehicle passing and gas leakage Type. According to 800 test datas, the accuracy, recall and F1 value of the model are 96.4%, 96.5% and 96.0% respectively, and the average recognition speed is 30s. The feasibility of CNN model to realize and improve the quality of DAS machine voice print recognition and acoustic reduction was verified by field tests.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.