An AI-based monitoring system for external disturbance detection and classification near a buried pipeline. (1st August 2023)

• Record Type: Journal Article
• Authors: Chen, Haobin; Wong, Ron Chik-Kwong; Park, Simon; Hugo, Ron
• Is Part Of: Mechanical systems and signal processing. Volume 196(2023)
• Publication Date: 2023-08-01
• Subjects: Monitoring system -- Buried pipeline -- Disturbance indicator -- Hilbert spectral analysis -- Support vector machine -- Convolutional neural network; Structural dynamics -- Periodicals; Vibration -- Periodicals; Constructions -- Dynamique -- Périodiques; Vibration -- Périodiques; Structural dynamics; Vibration; Periodicals; 621
• DOI: 10.1016/j.ymssp.2023.110346
• Languages: English
• ISSNs: 0888-3270

Abstract

Abstract: External threats including excavation, drilling, construction, vandalism, or sabotage can result in pipeline leak or rupture. To improve pipeline safety, an AI-based monitoring system for buried pipeline external disturbance detection and classification is proposed. The system is designed to detect and recognize potential threats prior to the occurrence of damage, offering localized continuous non-invasive structural health monitoring. In the proposed system, an accelerometer measures the operational vibration of the buried pipeline due to excitation by both internal flow turbulence and external disturbances. In this paper, the characteristics of both internal and external disturbances are investigated including pressure perturbations, drilling, jumping, running, and walking. The designed monitoring system consists of two processing phases. In the first phase, a disturbance indicator is developed using common time–frequency analysis techniques to generate a Spectral Index Function (SIF) and a Severity Index (SI), and these are used as inputs to a Quadratic Support Vector Machine (Q-SVM) classifier. Four classifications are used and overall accuracies of above 99% are achieved. In the second phase, contributions due to normal operating conditions are removed using a wavelet denoising technique. Morphological features of external disturbances are represented by grayscale images created by performing Hilbert Spectral Analysis (HSA) on wavelet denoised time series. A four-layer Convolutional Neural Network (CNN) classifier with inception modules is designed to perform the classification task. The results show that external disturbances can be successfully classified with high accuracy (96.1%). The robustness of the monitoring system is examined using data sets collected from different accelerometer locations. The results show that the designed monitoring system has a high level of robustness.