A method, device and system for classifying and identifying leakage acoustic signals

Abstract

The present application discloses a method for classifying and identifying leakage acoustic signals, which is used for leakage detection of pipelines. Leaking the sound signal to obtain the voiceprint image of the leakage sound signal; wherein, the abscissa in the voiceprint image is time, the ordinate is frequency, and the gray value is the amplitude; input the voiceprint image to the convolution A neural network classification model; classifying and identifying the voiceprint image to obtain the classification and identification result of the leakage sound signal; the method transforms the one-dimensional discrete signal of the pipeline leakage sound signal to obtain the voiceprint image of the leakage sound signal, Then use the convolutional neural network classification model to classify and identify the voiceprint image, and judge whether there is leakage and the type of leakage according to the classification and identification processing structure, which solves the technical problem that requires manual analysis and judgment and is relatively subjective. The technical effect of improving the accuracy of judgment is achieved.

Description

technical field [0001] The invention relates to the technical field of pipeline leakage detection, in particular to a pipeline leakage acoustic signal detection method, device and system. Background technique [0002] Due to various complex reasons such as corrosion, the water supply pipe network will leak, which not only causes waste of water resources, but also pollutes the water body in the pipe network, and also causes land subsidence and other hazards. Therefore, it is necessary to detect and locate the leakage of the water supply network. At present, sensors are usually widely deployed in the water supply pipe network to monitor the leakage points of the water supply pipe network. [0003] However, in the process of implementing the technical solutions in the embodiments of the present application, the inventors of the present application found that the above-mentioned technology has at least the following technical problems: [0004] In the above solution, the senso...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a method, device and system for classification and identification of acoustic leakage signals, which transform the one-dimensional discrete signal of the acoustic leakage signal of the pipeline to obtain the voiceprint image of the acoustic leakage signal, and then use the convolutional neural network classification model to classify the The voiceprint image is classified and identified, and whether there is leakage and the type of leakage is judged according to the classification and identification processing structure, which solves the technical problem that requires manual analysis and judgment and is relatively subjective, and achieves the technical effect of improving the accuracy of judgment

Images