Title: Location distribution detection of urban drainage pipeline based on deep learning feature

Authors: Weishan Chen; Zhigang Zhou

Addresses: College of Architectural and Civil Engineering, Guangzhou Panyu Polytechnic, Guang'zhou, 511487, China ' Department of Research and Development, Dragon Spring Technology Co., Ltd, Guang'zhou, 510399, China

Abstract: In order to improve the accuracy and efficiency of drainage pipeline location distribution detection, a new urban drainage pipeline location distribution detection method based on depth learning feature is proposed in this paper. Firstly, the main contents of drainage pipeline location data are analysed, and the drainage pipeline data are collected by acoustic detection method. Secondly, the dual tree complex wavelet method is used to extract the location distribution characteristics of urban drainage pipelines. Finally, the deep convolution neural network is used to train the location distribution characteristics to complete the detection results of urban drainage pipeline location distribution. The experimental results show that compared with the traditional detection methods, the detection accuracy of this method is higher and the time is shorter.

Keywords: deep learning features; urban drainage belt; position distribution detection.

DOI: 10.1504/IJRIS.2023.128369

International Journal of Reasoning-based Intelligent Systems, 2023 Vol.15 No.1, pp.48 - 53

Received: 26 Apr 2022
Accepted: 21 Jun 2022
Published online: 18 Jan 2023 *