Condition Classification of Water-Filled Underground Siphon Using Acoustic Sensors

Abstract

Siphons have been widely used in water supply systems and sewage networks. However, it is difficult to implement non-destructive testing due to structural complexity and limited accessibility. In this paper, a novel condition classification method for water-filled underground siphons is proposed, which uses the acoustic signals received from acoustic sensors installed in the siphon. The proposed method has the advantages of simpler operation, lower cost, and higher detection efficiency. The acoustic wave forms in the siphons reflect on the system characteristics. Seven typical conditions of a water-filled underground siphon were investigated, and a series of experiments were conducted. Acoustic signals were recorded and transformed into acoustic pressure responses for further analysis. The variational mode decomposition (VMD) and the acoustic energy flow density were used for signal processing and feature extraction. The acoustic energy flux density eigenvectors were input to three different classifiers to classify the siphon conditions. The results demonstrate that the proposed acoustic-based approach can effectively classify the blockage and damage conditions of siphons, and the recognition accuracy of the proposed method is higher than 94.4%. Therefore, this research has value for engineering applications.Recently, a series of methods have been developed for blockage or leakage detection in pipes, such as piezoelectric ultrasonic sensors technology [5], eddy current probes [6], closed-circuit television (CCTV) [7], sewer scanner evaluation technology (SSET) [8], and ground-penetrating radar (GPR) [9,10]. Piezoelectric ultrasonic sensors can detect minimal defects, and they have the advantages of being portable, non-polluting, and highly accurate for pipeline damage detection. However, piezoelectric ultrasonic testing is relatively difficult, tedious, and expensive, and its use is limited by the operating frequency. Eddy current probe detection has several limitations, and it can only be used to detect the surface or near-surface defects in magnetic or non-magnetic conductive siphons. In CCTV and SSET, the camera is installed on a mobile robot, which passes through the siphon to obtain the video data. The images can be used to manually or automatically evaluate the health or structure of siphons. Nevertheless, the detection is expensive and limited to relatively small portions of the sewer system.In contrast, acoustic detection is a non-destructive testing method with the advantages of simple implementation, low cost and high detection efficiency. The detection results do not depend on the subjectivity of the inspectors. Acoustic detection is suitable for inspecting pipes with different shapes (straight, curved, and siphon) and fluids of different densities (low, medium, and high). The changes in acoustic wave forms are related to the system characteristics (such as blockage and leakage) [11,12]. According to recent study results, the detection methods can detect sewer blockages and leakages based on acoustic s...

A Novel Feature Selection Based on VMD and Information Gain for Pipe Blockages

“…If the center frequency of the last IMF reaches its maximum value for the first time, it means that no insufficient decomposition occurs, and the value of K increases gradually until the maximum center frequency remains relatively stable. The parameter of decomposing mode number K was decided in advance, where it was determined according to a previous study [38]. Therefore, the K value in the paper was set as 12.…”

Investigation on Features Extraction of Defect Signals Using Support Vector Machine and Multi-feature Fusion

“…Yenus et al [11] collected sound wave data from the steel-smelting process and used FFT filtering to gain important feature information of the sound signal frequency domain. Zhu et al [12] used variable modular modal decomposition (VMD) and acoustic energy density to acquire acoustic characteristics signals in the field of civil engineering testing and categorized the blockage or damage of the subterranean water pipeline. Zhang et al [13] used independent component analysis to filter the traffic noise from the signals collected by sounding inspection methods.…”

Energy-distributable waterborne acoustic launcher for directional sensing

“…Exotic waterborne acoustic behaviors have been observed successively. [11,12] However, superdirectional underwater acoustic signal transmission remains a great challenge due to the strong fluid-solid interaction (FSI). Previous waterborne acoustic lens equipment has many defects such as large acoustic beam side lobes and poor noise immunity.…”