Multi-sample joint localization method for intrusion sources around underground pipelines based on cross-correlation convolutional neural networks

Abstract

Abstract Improving the safety monitoring of underground pipelines is crucial for maintaining the structural integrity of critical infrastructure systems. This study introduces an innovative multi-sample joint localization method (MSJLM) based on cross-correlation convolutional neural networks (CC-CNNs) to identify intrusion sources in the vicinity of underground pipelines. Traditional approaches to detecting and locating pipeline intrusions often rely on a solitary sensor monitoring point, making them susceptible to errors and limitations. Presently, widely used distributed optical fiber testing methods tend to yield imprecise localization. In contrast, the MSJLM proposed in this study harnesses data from multiple samples effectively and combines them via correlation analyses to enhance precision and reliability. The CC-CNN framework used to process the collected data is demonstrated to be highly effective in extracting spatial features and recognizing patterns.