Liquid-filled pipeline leak detection and localization based on multi-scale residual networks

Abstract

Effective ways to improve the accuracy of liquid-filled pipeline leak detection are one of the key issues that need to be addressed urgently in a conservation-oriented society. Recently, pipeline leak detection methods based on deep learning have developed rapidly. To improve the learning ability of convolutional neural network for pipeline leak signal features and leak detection accuracy, a Multi-Scale Residual Networks (MSRN) model is proposed in this paper for liquid-filled pipeline leak detection and localization. The model uses convolutional kernels of different scales to extract multiscale features of pipeline leakage signals based on deep residual networks (DRNs) and uses fully connected layers to fuse the features, thus improving the accuracy of pipeline leakage detection and localization. Among them, the large convolution kernel can acquire the low-frequency information of the signal due to its sizeable perceptual field, the medium convolution kernel can capture the local and global features of the signal, and the small convolution kernel is more sensitive to the high-frequency information of the signal. Meanwhile, a pipeline leakage test platform is built to evaluate the proposed model. The test results show that the accuracy of leak detection and localization of MSRN model is 98.3%, which is better than that of single-scale DRN model. In addition, the proposed MSRN model is verified to have good generalization and noise immunity through testing and analyzing the leakage signals under different pressures and background noises.

Research on acoustic methods for buried PE pipeline detection based on LSTM neural networks

“…Zhao et al introduced a multi-scale residual network for detecting and localizing leaks in liquid pipelines, leveraging convolutional kernels of varying scales within deep residual networks and employing fully connected layers to fuse features, thereby enhancing accuracy in leak detection and localization [15]. Yu et al proposed a ZSL model Feature-generative adversarial network (GAN)-zero-shot learning (ZSL) fused with a generative adversarial network for ultrasonic detection to identify pipeline weld defects by integrating artificial semantic features with ultrasonic inspection signal features in a common semantic space, utilizing a Feature-GAN network to generate unseen class features and enhance feature generation with stronger discriminative power [16].…”