Leakage Signal Research Articles

Adaptive fast Walsh-Hadamard transform for magnetic flux leakage signal of broken wire damage extraction under noise background

ABSTRACT Steel wire rope usually works in harsh environments, making it prone to damage during frequent use. Magnetic flux leakage testing is an important way of non-destructive testing, preventing some major accidents of hoist equipment by identifying the damage to steel wire ropes. Whereas, the harsh environment usually generates noise and results in difficulty in extracting the damage features of the magnetic flux leakage signal, which makes it hard to identify the damage. The fast Walsh-Hadamard transform is widely used in signal processing. The denoising effect depends closely on the transform coefficients. If the transformation coefficients can be adaptively retained, better denoising effects can be achieved. Therefore, we propose the adaptive fast Walsh-Hadamard transform to extract the magnetic flux leakage signal of steel wire rope under noise background. Using the cross-correlation co efficient and the similarity of the greyscale histogram as the indexes, the Fast Walsh-Hadamard transform combines the adaptive particle swarm optimisation to adaptively retain the optimal transformation coefficient and then gets the optimal denoising signal. Meanwhile, compared to wavelet denoising methods, the adaptive fast Walsh-Hadamard transform can effectively improve denoising performance in peak-to-peak reductivity and can be successfully used in steel wire rope damage extraction.

Advanced acoustic leak detection in water distribution networks using integrated generative model

Water distribution networks (WDNs) experience significant water loss due to leaks, necessitating advanced water leak detection methods. However, machine learning-based acoustic method heavily relies on signal information and is limited by data scarcity and the limited diversity of available data. To address this challenge and enhance water leak detection in WDNs, this study proposes an LSTM-GAN approach. Acoustic signals are collected from WDNs to train the LSTM-GAN model, which generates synthetic leak signals to enhance the dataset. The validity of the generative method is evaluated through t-SNE and acoustic characteristics analysis. LSTM-based water leak detection models are established and compared using the original and the generated datasets to confirm the efficacy of generated samples in improving water leak detection performances. The capability of LSTM-GAN has been evaluated through different perspectives, including sensitivity analysis and model comparison. The results validate the quality and consistency of the generated acoustic signals under leak conditions. Besides, the optimal number of generated samples should be determined according to the requirements and characteristics of the leak detection task. Furthermore, the comparison between the proposed method and other acoustic generative methods demonstrates the superiority of LSTM-GAN-generated signals in enhancing the performance of leak detection models. The proposed generative method offers an innovative approach to facilitate machine learning-based leak detection models with limited data, thereby enhancing robustness.

Research on Magnetic Memory Detection of Weld Fatigue Damage Based on Two-Dimensional Spectral Entropy

Abstract In light of the intrinsic relationship between weld fatigue damage and the characteristics of magnetic leakage signals, fatigue experiments were conducted on butt welds to analyze the evolution of magnetic leakage signal as fatigue cycles increased. The introduction of two-dimensional spectral entropy allowed for the construction of a fatigue stage division model based on the two-dimensional spectral entropy diagram. The results revealed that distinctions between magnetic leakage signal under loaded and unloaded conditions were solely evident in their magnitude, with consistent curve distribution trends observed across various fatigue cycles. Furthermore, the distribution pattern of magnetic leakage signal displayed significant fluctuations, characterized by a sharp gradient increase following the emergence of fatigue cracks. These distribution characteristics of magnetic leakage signal differed markedly from the magnetic field distribution at other fatigue stages, with a higher growth rate observed as fatigue cycles increased. The two-dimensional spectral entropy spectrum analysis of magnetic leakage signals at different fatigue stages indicated the disorder in the magnetic leakage signal distribution within the high fatigue zone, signifying the expansion of fatigue microcracks. To some extent, two-dimensional spectral entropy can serve as an early warning system for detecting fatigue cracks in welds and achieving early identification of fatigue microcracks.

Acoustic Imaging Method for Gas Leak Detection and Localization Using Virtual Ultrasonic Sensor Array.

An acoustic imaging method for detecting and locating gas leaks based on a virtual ultrasonic sensor array is proposed and experimentally demonstrated. A scanning sensor array of only two sensors is used to collect the acoustic signals generated by the leakage hole. The matrix of the leakage signal is processed by the cross-power spectrum method to achieve time consistency, afterward, the location of the leakage source can be calculated by the virtual beamforming method. The influence of the number of sensors and the distance between adjacent sensors on the effect of the proposed method are compared and discussed. To verify the effectiveness and operability of the detection and localization method, several experiments were carried out. Furthermore, a series of experiments were conducted to assess the accuracy and stability of this method. The experimental results demonstrate that the proposed method based on a virtual sensor array can achieve highly accurate localization of gas leaks and performs well regarding stability.

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

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 (MSRNs) 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 sizable 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.

Optimized variational mode decomposition denoising method based on weighted mean of vectors algorithm

Aiming at the noise interference in oil and gas pipeline leakage detection, a signal denoising method based on improved variational mode decomposition (VMD) algorithm is proposed. First, the weighted mean of vectors algorithm (INFO) is used to select the parameters of the VMD algorithm adaptively to obtain the best decomposition level K value and penalty factor α value, which effectively solves the problem that the parameters are difficult to select in VMD. Then, according to the Hausdorff distance between the original signal and the probability density of each IMF, the effective modal components are selected for reconstruction and denoising signal is obtained. In oil and gas pipeline leakage signal processing, compared with whale optimization algorithm, grey wolf optimization algorithm, and particle swarm optimization algorithm, the reconstructed signal obtained by the proposed INFO algorithm optimized VMD parameters has higher signal-to-noise ratio and lower mean square error and mean absolute error. It shows that the proposed algorithm has better denoising effect.

QoT-aware tree selection, routing, modulation, and spectrum assignment for filterless EONs over the C + L-band

Filterless optical networks (FONs) as an economical solution use passive couplers/splitters rather than expensive active filter devices. In this way, after intermediate and destination nodes, lightpaths are dropped and continued, which generates leakage signals in other links and wastes spectrum. Thus, designing efficient resource allocation in FONs by considering the leakage signals and their interfering effects is of utmost importance. On the other hand, a gradual transition from wavelength division multiplexing optical networks to elastic optical networks (EONs) is occurring due to their efficient utilization of spectrum. Furthermore, utilizing the L-band beside the conventional C-band for spectrum assignment offers a wide range of frequency resources. Therefore, in this paper, we propose an integer linear program (ILP) to solve quality of transmission (QoT)-aware tree selection, routing, modulation, and spectrum assignment problems in filterless EONs over the C+L-band. Furthermore, we provide heuristic algorithms to deal with complex large-scale networks. The performance gap of the proposed ILP and heuristic algorithms is evaluated over a small-scale (5-node) network. The results show that the ILP and heuristic algorithms have almost the same performance in terms of spectrum usage and assigned modulation format, and ILP has a slightly higher generalized signal-to-noise-ratio (GSNR) (0.23 dB or 0.8% at optimum launch power). Furthermore, the heuristic algorithms are also examined over a large-scale network (TID region A topology). The results reveal that the GSNR estimation method severely affects the performance in terms of spectrum usage, blocking, and outage. Furthermore, by using the proposed MX5 method, as long as there is a fill margin of approximately 2 dB, there is no outage or blocking over the C+L-band, up to a network throughput of 110 Tbps and conventional C-band transmission with lower throughput (i.e., 40 Tbps). Finally, our extensive numerical results provide a rule of thumb for balancing blocking, outage, spectrum usage, and the number of expensive L-band transponders by selecting the appropriate modulation assignment method.

Application of dynamic event-triggered hybrid gravitational search algorithm in pipeline leakage detection

In this paper, a hybrid gravitational search algorithm (GSA) based on the dynamic event-triggered mechanism, which is called DHGSA, is proposed to alleviate the slow exploitation problem of the GSA that may result in premature convergence and falling into local optimization. First, the DHGSA is divided into the exploration stage and the exploitation stage through the introduction of the population diversity. Then, the memory and social information exchange abilities of the particle swarm optimization algorithm are added in the DHGSA’s exploration stage, which can accelerate the convergence speed of the GSA. Next, the dynamic event-triggered mechanism (DETM) is added in the exploitation stage of the DHGSA, and a “celestial banishment strategy” is proposed, which improves the exploitation ability of the GSA and makes it have the ability to avoid falling into local optimal value. The derived results indicate that, compared with several other well-known search algorithms, the DHGSA has better performance on convergence speed, optimization accuracy and stability. Finally, the DHGSA is employed to optimize the parameters of the variational mode decomposition (VMD) algorithm for the oil and gas pipeline signal decomposition. The signal-to-noise ratio (SNR) of the three types of pipeline signals after denoising reaches 8.8406 dB, 9.0869 dB and 5.6880 dB, respectively. It is proved that the leakage signals can be denoised effectively in the research of the oil and gas pipeline signal processing.

Research on self-leakage flux magnetic identification method of the most dangerous section of parallel wire cable under multi-point broken wire condition

The self-leakage magnetic signal of 37 parallel steel wires was detected by using magnetic signal detection technology and equipment. Based on the theoretical and experimental data, the relationship between the magnetic signal characteristics and the influencing factors was analyzed. The magnetic signal characteristics of multi-point interleaved broken wires are explored. The results show that the characteristics of the self-magnetic flux leakage signal of parallel wires broken are related to the defect parameters of the broken wires. The influence of lifting height on the magnetic signal is less than 3.8 %. The influence rate of the detection angle path is under 8.3 %. By analyzing the measured magnetic signals, a method for identifying the most dangerous cross section is proposed, and this is modified and improved. The maximum identification error of the recognition error is only 5.6 %.

Numerical and experimental research on vibration signal characteristics of water pipeline leakage

In the leak detection of water pipelines, interference and environmental noise directly affect the effectiveness of leak detection and the accuracy of leak point location, so it is necessary to study the real signal. Previous studies mostly rely on a single test to improve the positioning accuracy by collecting vibration signals for denoising, but denoising will also affect the real signal, and the actual detection situation is complex, so it is difficult to deal with all working conditions only through the test. With the rapid development of computer technology, the combination of numerical simulation and experiment is expected to solve this problem. Therefore, this paper takes the acceleration signal as the research object, collects and simulates the leakage signals under different pressure strengths by combining experiments with numerical simulation, and verifies the feasibility and accuracy of a numerical simulation model. The generation of leakage vibration acceleration under different pressure and different leakage hole radius is simulated. Research findings: a. the leakage signal energy has a power function relationship with the pressure and an exponential function relationship with the leakage radius; b. the characteristic frequency is the variable of the characteristics of pipeline and leakage hole, which is independent of the pressure; c. the power of each peak frequency has a step-by-step change trend with the energy of the signal; d. the power of acceleration signal concentrates to a higher frequency with the increase of pressure and the decrease of leakage radius. This study provides a basis for identifying, detecting, and extracting leakage signals in a real noise environment, helps to improve the accuracy of acoustic emission signal detection, and can provide a theoretical basis for pipeline leakage detection research.

Improved Reconstruction of Magnetic Flux Leakage Signal From Wire Rope Damage Using Novel Smooth Function and Feature Peak Compensation

Improved Reconstruction of Magnetic Flux Leakage Signal From Wire Rope Damage Using Novel Smooth Function and Feature Peak Compensation

Research on Noise Reduction Method for Leakage Signal of Water Supply Pipeline

Research on Noise Reduction Method for Leakage Signal of Water Supply Pipeline

A Masked Multi-View Bidirectional Network for Class Extremely Imbalanced Object Detection Under Magnetic Flux Leakage Signals

A Masked Multi-View Bidirectional Network for Class Extremely Imbalanced Object Detection Under Magnetic Flux Leakage Signals

Development of a convolutional neural network model to predict the size and location of corrosion defects on pipelines based on magnetic flux leakage signals

This study employs the convolutional neural network (CNN) to predict the dimensions and locations of corrosion defects on steel pipelines based on magnetic flux leakage (MFL) signals. Extensive three-dimensional parametric finite element analyses are carried out to generate MFL signals corresponding to semi-ellipsoidal-shaped corrosion defects with different sizes and locations on a pipe model. The white noises characterized by different signal-to-noise ratios are considered in the analysis to represent the measurement errors in the real MFL inspection tool. The numerically generated MFL signals are used to train and validate the CNN model to predict the dimensions and locations of the corrosion defects. The results indicate that the developed CNN model achieves a high predictive accuracy. The study demonstrates the application of CNN model to improve the pipeline integrity management practice.

A Novel Defect Detection Method for Overhead Ground Wire.

Overhead ground wires typically have strong axial tension and are prone to structural defects caused by corrosion and lightning strikes, which could lead to serious safety hazards. Therefore, it is important to detect defects accurately and quickly to avoid those problems. Existing defect detection methods for overhead ground wires are mainly traditional metal defect detection methods, including eddy current detection, ultrasonic detection, and manual visual inspection. However, those methods have problems of low detection efficiency, high environmental requirements, and insufficient reliability. To solve the above problems, this paper studies a novel type of defect detection technology for overhead ground wire. Firstly, the magnetic leakage characteristics around the defects of overhead ground wires are analyzed, and the defect detection device is designed. Then, the influence of air gap, lift-off distance, defect width, and cross-sectional loss rate on the magnetic flux leakage signal is studied, a novel defect detection method for overhead ground wire is proposed, and experimental verification is carried out. The results show that the proposed method can accurately locate and quantify the defect, which has the advantages of good reliability and high efficiency and lays the foundation for preventing accidents caused by defective overhead ground wires.

Semi-supervised learning for steel surface inspection using magnetic flux leakage signal

Semi-supervised learning for steel surface inspection using magnetic flux leakage signal

ASYMPTOTICALLY OPTIMAL ALGORITHM FOR PROCESSING SIDE RADIATION SIGNALS FROM MONITOR SCREENS ON LIQUID CRYSTAL STRUCTURES

An asymptotically optimal compatible algorithm for detecting side radiation signals from the monitor screen on liquid crystal structures and estimating the duration of image immutability on the monitor screen is found, which will better intercept information from monitor screens. The structure of a special technical intelligence tool is justified as a maximum likelihood algorithm for a finite number of unknown quadrature amplitudes of the information leakage signal from the monitor screen on liquid crystal structures.

On the mixed acoustic and vibration sensors for the cross-correlation analysis of pipe leakage signals

Pipe leak detection can be carried out by various acoustic/vibration sensors, such as acoustic pressure, velocity and acceleration sensors. The purpose of this study is to investigate the effectiveness of the mixed acoustic/vibration sensors for the determination of pipe leakage. Firstly, a propagation and attenuation model of leakage signal in the liquid-filled pipeline is established based on frequency response functions. Further, the expressions of the cross-correlation function of different sensor types are derived with respect to the differential properties of Fourier transform. Then, the influence of signal-to-noise ratio (SNR) on the cross-correlation function is analyzed. Numerical simulation is employed to generate pressure, velocity and acceleration signals by differentiating the leakage source signals. Simulation results indicate that the use of pressure sensor acts as low-pass filtering operation, whereas the velocity and acceleration sensors act as band-pass filtering. Finally, experimental work is carried out on a medium density polyethylene (MDPE) pipe. Leakage signals are collected synchronously by hydrophones and accelerometers. Experimental results show that the cross-correlation function of hydrophones fluctuates slowly with peak value being less obvious, while the cross-correlation function of accelerometers fluctuates rapidly and has a sharper peak. In comparison, there is a compromise in the fluctuation for the sake of peak sharpness in the cross-correlation function of the mixed sensors, indicating that the corresponding cross-correlation result are less affected by background noise.

Research on pipeline leakage signal denoising using variational mode decomposition and energy value

In order to separate the effective components and the noise components after variational mode decomposition (VMD) and improve the denoising effect of VMD, a denoising approach combining VMD with energy value (EV) and VMD (VMD-EV-VMD) is proposed. First, VMD decomposes the original signal into K intrinsic mode functions (IMF) and then calculates the EV of the probability density function of each IMF component. According to the changing trend of energy value, the effective components and the noise components are distinguished. Subsequently, each noise component is decomposed by VMD again, the effective components are selected by calculating the correlation coefficient (CC) between the input component of the second VMD and the IMF obtained from the second VMD. The effective components selected by VMD twice are used for signal reconstruction. Simulation experiments and pipeline leakage signal processing show that the method of VMD-EV-VMD achieves a greater SNR than the methods of EEMD, VMD-EV, and VMD-WT. and it has a smaller MSE and MAE, A better denoising effect is achieved and the pipeline leakage characteristics are more accurately preserved. In addition, the accuracy of the SVM classifier is used to verify the effectiveness of the proposed method.

Application of pipeline leakage detection based on distributed optical fiber acoustic sensor system and convolutional neural network

Underwater pipelines are exposed to harsh environments, including high salinity, multi-modal vortex corrosion, and severe wave interference. Their safety is essential for the development and transportation of marine energy. Therefore, real-time safety monitoring of long-distance energy pipelines is of great strategic importance for ensuring the safety of life and property and energy security. With the rapid development of energy development, the corrosion and leakage mechanisms of natural gas pipelines, as well as their identification and early warning, have become the focus of attention. Optical fiber sensing technology has been applied to various energy safety monitoring fields. However, the mechanism of sound source fluctuations in pipeline leakage and the mutual coupling mechanism between distributed optical fiber sensing technology and leakage sound waves are not yet clear. This paper establishes a model based on sound wave propagation and leakage noise response, derives a quadratic fitting relationship between pipeline pressure fluctuations and leakage orifices and a relationship between leakage noise source standard deviation and orifices, and proposes a complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) permutation entropy underwater natural gas pipeline leakage signal recognition method based on distributed optical fiber acoustic sensing technology. The results of theoretical analysis are verified by experiments. It shows that the signal processing method of CEEMDAN permutation entropy is superior to traditional noise reduction methods, which can better preserve the features of the original signal; the radial basis function (RBF) neural network model can accurately identify four different leakage features with an accuracy of 88.15%, and its recognition stability and generalization ability are superior to convolutional neural network, backpropagation, and random forest. Therefore, the research results of this paper provide a new method for safety monitoring in the application of energy pipeline transportation engineering, and expand the potential application scenarios of distributed acoustic sensing sensor systems and RBF neural networks.