Cable Defects Research Articles

Trans-DCN: A High-Efficiency and Adaptive Deep Network for Bridge Cable Surface Defect Segmentation

Cables are vital load-bearing components of cable-stayed bridges. Surface defects can lead to internal corrosion and fracturing, significantly impacting the stability of the bridge structure. The detection of surface defects from bridge cable images faces numerous challenges, including shadow disturbances due to uneven lighting and difficulties in addressing multiscale defect features. To address these challenges, this paper proposes a novel and cost-effective deep learning segmentation network, named Trans-DCN, to detect defects in the surface of the bridge cable. The network leverages an efficient Transformer-based encoder and integrates multiscale features to overcome the limitations associated with local feature inadequacy. The decoder implements an atrous Deformable Convolution (DCN) pyramid and dynamically fuses low-level feature information to perceive the complex distribution of defects. The effectiveness of Trans-DCN is evaluated by comparing it with state-of-the-art segmentation baseline models using a dataset comprising cable bridge defect images. Experimental results demonstrate that our network outperforms the state-of-the-art network SegFormer, achieving a 27.1% reduction in GFLOPs, a 1.2% increase in mean Intersection over Union, and a 1.5% increase in the F1 score. Ablation experiments confirmed the effectiveness of each module within our network, further substantiating the significant validity and advantages of Trans-DCN in the task of bridge cable defect segmentation. The network proposed in this paper provides an effective solution for downstream cable bridge image analysis.

Accurate modeling and assessment of subsea cable’s unbalanced induced current for subsea cable considering the amore wires

AC subsea cables are grounded at both ends via two metal layers, namely metallic screen (normally made by lead for high voltage subsea cable as radial water barrier) and armor, which consists of wires. This topology leads to induced current in the two grounded layers. Field test shows that occasionally unbalanced induced current is observed in grounded layers (lead and armor) between two cable ends. The difference of induced current between two cable ends can be as high as half of the load current. The cause for such unbalance is not clear and it may endanger the cable system. To analyze the phenomena and prevent potential failure, detailed analytical modeling assisted with finite-element method (FEM) is proposed in this paper to accurately analyze the unbalanced induced current for AC subsea cable. FEM is utilized to model the armor wires as an equivalent homogeneous layer. With this validated method, comprehensive analysis is performed for unbalanced induced current of AC subsea cable. It is shown that the unbalanced current is due to the inequal impedances between grounding points at two cable ends and/or the extra introduced resistor between lead sheath and armor. Based on these findings grounding status and connection status between lead and armor can be evaluated via the induced currents. An evaluation tree is then proposed to help identify the cable defects.

ViTR-Net: An unsupervised lightweight transformer network for cable surface defect detection and adaptive classification

As a crucial load-bearing component of the cable-stayed bridge, the cable requires surface defect detection to maintain its safety. The current deep-learning-based stay-cable surface defect detection still faces challenges, including insufficient actual defect samples, cumbersome labeling processes, and an effective method for further evaluation and classification of defects. To address these problems, an unsupervised vision transformer-based lightweight reconstruction network called ViTR-Net is proposed, which only uses normal stay-cable surface images to achieve end-to-end localization of defect areas in the image. ViTR-Net is a generative-based method that uses a hybrid network of convolutional neural networks and visual transformers as a feature extraction network. A feature correction fusion module is designed by integrating differential convolution and attention mechanisms to compensate for potential detail loss caused by feature extraction. Subsequently, a severity index for defects is established to assess the severity of various defects, and the detected defects are adaptively classified using the affinity propagation clustering algorithm. ViTR-Net achieves the highest defect detection accuracy and exquisite defect segmentation results on a realistic cable defect dataset through experimental validation. The proposed model can realize the surface defect assessment and adaptive classification of the stay cable, which has a good application prospect in the actual maintenance process of the stay cable.

Partial Discharge Signal Pattern Recognition of Composite Insulation Defects in Cross-Linked Polyethylene Cables.

To investigate the pattern recognition of complex defect types in XLPE (cross-linked polyethylene) cable partial discharges and analyze the effectiveness of identifying partial discharge signal patterns, this study employs the variational mode decomposition (VMD) algorithm alongside entropy theories such as power spectrum entropy, fuzzy entropy, and permutation entropy for feature extraction from partial discharge signals of composite insulation defects. The mean power spectrum entropy (PS), mean fuzzy entropy (FU), mean permutation entropy (PE), as well as the permutation entropy values of IMF2 and IMF13 (Pe) are selected as the characteristic quantities for four categories of partial discharge signals associated with composite defects. Six hundred samples are selected from the partial discharge signals of each type of compound defect, amounting to a total of 2400 samples for the four types of compound defects combined. Each sample comprises five feature values, which are compiled into a dataset. A Snake Optimization Algorithm-optimized Support Vector Machine (SO-SVM) model is designed and trained, using the extracted features from cable partial discharge datasets as case examples for recognizing cable partial discharge signals. The identification outcomes from the SO-SVM model are then compared with those from conventional learning models. The results demonstrate that for partial discharge signals of XLPE cable composite insulation defects, the SO-SVM model yields better identification results than traditional learning models. In terms of recognition accuracy, for scratch and water ingress defects, SO-SVM improves by 14.00% over BP (Back Propagation) neural networks, by 5.66% over GA-BP (Genetic Algorithm-Back Propagation), and by 12.50% over SVM (support vector machine). For defects involving metal impurities and scratches, SO-SVM improves by 13.39% over BP, 9.34% over GA-BP, and 12.56% over SVM. For defects with metal impurities and water ingress, SO-SVM shows enhancements of 13.80% over BP, 9.47% over GA-BP, and 13.97% over SVM. Lastly, for defects combining metal impurities, water ingress, and scratches, SO-SVM registers increases of 11.90% over BP, 9.59% over GA-BP, and 12.05% over SVM.

Micro-crack localization for steel strands using nonlinear vibro-acoustic modulation based on modified signal bispectrum analysis

Under continuous environmental erosion and long-time high tension, fatigue micro-cracks of bridge cables appear frequently to challenge the reliability of cables. The vibro-acoustic modulation analysis is adopted because of its sensitivity to contact-type defects, especially fatigue cracks. In this paper, using multiple sets of low-frequency vibration and high-frequency ultrasonic excitation, the propagation of the ultrasonic wave in the steel strands is studied. Then, the modulated signal bispectrum is proposed to improve the detection reliability of nonlinear modulation components in the nonlinear vibro-acoustic modulation signal of the contact-type defect. The numerical simulations and laboratory tests of straight wire, helical wire, and multi-wire strands are carried out for micro-crack detection to verify the robustness of the proposed method. Compared with the traditional method, the modulated signal bispectrum can still produce clearer peak detection under high noise conditions. The results show that it provides a promising, dynamic and rapid cable defect detection technique.

Reinforcement Learning-Based Automation of Time-Frequency Domain Reflectometry

Advanced reflectometry, which can be used to estimate the location of defects in electrical cables with high accuracy, has undergone continuous development based on advanced signal processing techniques. However, in actual fields, non-experts find it difficult to use advanced reflectometry owing to the difficulty of the application process. Therefore, in this paper, a novel technique that can automate the signal-design process in reflectometry, enabling anyone to use advanced reflectometry in the actual field, is proposed. In this work, the signal-design process is automated by utilizing reinforcement learning (RL), and the application methodology is explained using time-frequency domain reflectometry. The agent of the proposed RL model is trained in a simulation-based environment. Finally, the trained agent is applied to a real-world cable to demonstrate its performance.

The impact of different air gap defects in polypropylene coaxial cables on electric field distortion

The internal cable will have different air gaps due to various physical influences, and partial discharge caused by air gap defects is the main cause of cable insulation aging. To avoid serious consequences caused by air gap defects, it is crucial to analyze the extent of the impact of early-stage air gaps on the electric field in the cable. In this paper, COMSOL Multiphysics software is used to build a three-dimensional model of the cable, and the insulation material is polypropylene. Different positions and sizes of air gap defects are designed in the model. The electric field distribution inside the cable is obtained through the finite element algorithm, and the degrees of distortion of the electric field under different air gap sizes, positions, and shapes are compared. The results show that the size of the air gap affects the change in the electric field. Air gaps closer to the copper core position produce greater electric field distortion. Additionally, air gaps with larger curvature also result in greater electric field distortion. Based on the conclusion of this study, the influence degree caused by different air gap defects can be determined and provide a basis for the analysis of such faults.

A machine learning-based assessment model for defect diagnosis in XLPE power cables

Cross-linked polyethylene (XLPE) power cables are commonly used in flexible DC transmission applications. The diagnosis of the defects of XLPE power cable has consistently been a focal point of research as it is an essential equipment for power delivery. Previous research works have seldom employed machine learning methods to deal with this problem. Therefore, this work presents a machine learning-based assessment model that combines the Categorical Boosting (CatBoost) algorithm and Aquila optimizer. The CatBoost model is developed to examine the stages of the cable defect. The load condition, corrosion condition, operating life, and partial discharge are the inputs into the CatBoost model. The Aquila optimizer is employed to optimize parameters in an automated manner during the training of the CatBoost model. The performance comparison is made between the proposed model and the existing models. The proposed model demonstrates a high level of accuracy, precision, recall, and F1-score, all higher than 99 %. The model exhibits at least 1 % more achievement in accuracy, precision, recall, and F1-score when compared to the next best model, XGBoost. These results suggest that the proposed model is capable of effectively assessing the stages of cable defects. In addition to this, these experimental results of the proposed model are superior to those of the existing models, which demonstrate that the proposed model is superior to the existing models in terms of its ability to assess the defect stages of cables.

Defect Identification of XLPE Power Cable Using Harmonic Visualized Characteristics of Grounding Current

This paper proposes an online monitoring and defect identification method for XLPE power cables using harmonic visualization of grounding currents. Four typical defects, including thermal aging, water ingress and dampness, insulation scratch, and excessive bending, were experimentally conducted. The AC grounding currents of the cable specimens with different defects were measured during operation. By using the chaotic synchronization system, the harmonic distortion was transformed into a 2D scatter diagram with distinctive characteristics. The relationship between the defect type and the diagram features was obtained. A YOLOv5 (you only look once v5) target recognition model was then established based on the dynamic harmonics scatter diagrams for cable defect classification and identification. The results indicated that the overall shape, distribution range, density degree, and typical lines formed by scatter aggregation can reflect the defect type effectively. The proposed method greatly reduces the difficulty of data analysis and enables rapid defect identification of XLPE power cables, which is useful for improving the reliability of the power system.

Image and audio characterization of electromagnetic signals in cable defect detection

Power cables play a very important role in urban development. On the other hand, the integrity and the safe operation of power cables are crucial as even a minor potential mishap can result in serious loss of life and property. Hence, early diagnosis and warning of cable faults are imperative. Addressing the current lack of practical detection technologies, this study proposes a non-destructive testing method based on electromagnetic field principles. Through scanning the power-on power cables with probes, the electric field intensity around the cables can be measured, and the weak anomaly caused by structural and material defects can be detected using Superlets transformation. Additionally, to gain a better characterization of the faults, a digital post-processing approach consisting of imaging and sonification algorithms is developed to aid in pinpointing the location of the faults. Both numerical simulation and experimental test indicate that the proposed non-destructive detection method is feasible and can achieve good accuracy in locating cable faults. With image and audio characterization, the present method has great potential applications in ensuring the safety of power cables.

A defect location method for power cable based on Burg power spectral

AbstractThe frequency‐domain reflection (FDR) has been demonstrated to be a trustworthy technique in solving the defect location of power cable by field experiments. However, the location spectrum of the FDR requires manual window smoothing and can be disturbed by spurious peaks. Aiming at these shortcomings of FDR, a new method of cable defect location based on Burg power spectral (BPS) is introduced in this paper. The idea of this method is to use linear difference variance to fit the distribution of reflection coefficient spectrum and build an auto‐regressive (AR) model. The Burg algorithm is employed to estimate the coefficients model and calculate the power distribution of the AR model. Then, the cable defects will be located by BPS with high precision and resolution. In this method, the fast Fourier transform (FFT) with windowed function is replaced by an AR model without windowed function. This suppressed the impact of spurious peaks or spectrum leakage in FFT on the localization defects, and the localization resolution is higher. Finally, we validate the feasibility and effectiveness of BPS through experiments conducted on a 500 m laboratory cable and a 9.6 km submarine cable.

An efficient accuracy improvement method for cable defect location based on instantaneous filtering in time-frequency domain

Time-frequency domain reflectometry is a highly sensitive method to locate cable defect. However, locating a potential defect far from the cable head may be less accurate because of the signal amplitude attenuation and the interference parts. To solve the problem, this paper proposes an accuracy improvement method based on instantaneous filtering in time-frequency domain. The method extracts the frequency spectrum of the time-frequency signal, and then filters the spectrum and reconstructs the signal based on the difference between the signal and interference spectra, which can eliminate the interference and improve the location accuracy. In simulation, the location error of this method improves from 5.47 % to 0.57 %. In experiment, the proposed method reduces the location errors and magnifies the location peaks of the breakage defect, thermal aging defect, and ground faults. For the defects studied in this paper, the method improves the defect location accuracy and defect amplitude detectability of TFDR.

A Novel Time-frequency Domain Reflectometry Method Based on S-transform for Power Cable Defect Localization

Background:: The large-scale aging of cross-linked polyethylene (XPLE) leads to an increase in the frequency of power cable accidents, which poses a threat to the safe operation of the power grid. Objective:: Traditional time-frequency domain reflectometry (TFDR) techniques for fault localization in power cables are susceptible to cross-terms interference, which makes it impossible to accurately locate defects. To overcome the limitation, this paper has proposed a novel cable fault localization method based on S-transform. Method:: The method employs S-transform to perform time-frequency analysis on the collected signals of TFDR, mapping the time-domain signals into time-frequency domain signals. Then, cross-correlation of the time-frequency domain signals is estimated, allowing for accurate positioning of cable defects. Results:: The results of the field experiments conducted on a 10 kV cross-linked polyethylene cable with artificially introduced defects have demonstrated that the proposed method could effectively locate the cable defects with small absolute error. Conclusion:: Compared to existing TFDR methods, the proposed method has been found to be free from interference of cross-terms, resulting in higher reliability and smaller blind spots for detecting cable defects.

Identification of hidden defects in optical cables based on BOTDR distributed detection technology

Identification of hidden defects in optical cables based on BOTDR distributed detection technology

A Reflection Coefficient Estimation Method for Power Cable Defects Based on Three-Point Interpolated FFT

A Reflection Coefficient Estimation Method for Power Cable Defects Based on Three-Point Interpolated FFT

BiLSTM-FCN based vibration signal diagnosis of smart grid cables

Abstract Cable faults threaten the safe and stable operation of smart grids, and vibration signal diagnosis research on cables based on artificial intelligence technology can effectively enhance the reliability of smart grids. In order to improve the speed and accuracy of cable defect identification, this paper proposes a partial discharge identification method for cables based on a fully convolutional bidirectional long short-term memory neural network (BiLSTM-FCN). The time-domain characteristics of different working conditions under industrial frequency AC voltage are collected by building a vibration signal-based partial discharge test platform for cables. The Overlap strategy enhances the data set. The BiLSTM layer is introduced to process the one-dimensional time domain waveform signal, and combined with the local detail features extracted by the FCN layer, the data features are more abundant. Thus, a more accurate diagnosis of localized discharge in high voltage cables under different operating conditions. The results show that the diagnostic accuracy based on the BiLSTM-FCN model reaches 92.2%, which is 1.2% and 1.4% higher compared to the FCN model and the BiLSTM model. BiLSTM-FCN model possesses a better recognition effect and faster recognition speed in the identification of partial discharge defects type, which can effectively achieve the automatic detection of abnormal fault nodes of smart grid cables. It is significant for realizing online dynamic evaluation of small portable online monitoring equipment and provides a reference for future related research.

Исследование влияния магнитного поля на характеристики частичных разрядов

The paper is devoted to the study of the dependences of the characteristics of partial discharges on magnetic induction. The design of the experimental setup has been developed. It allows applying both high voltage and current comparable to the operating one. The setup includes a high voltage source (dielectric tester), a current flow circuit, a high voltage current transformer and a sample of XLPE insulated cable. The operation of the electrical circuit of the experimental setup is simulated using software. The modeling has shown that if the operational electrical strength of the current transformer insulation is present, the high-voltage potential cannot contact the current flow circuit. After this, modeling of the magnetic field inside the insulating layer is carried out. Based on the developed design, an experimental setup is created. To record partial discharges, an artificial defect is created in a cable sample. The results of magnetic field modeling made it possible to estimate the magnetic induction in the field of an artificial cable defect. Next, experimental studies are carried out to assess the influence of the magnetic field of the cable core current on the characteristics of partial discharges. The measurement results have showed a decrease in the average apparent charge of partial discharges and partial discharge power with increasing current. In addition, waveforms are compared, but no significant differences are found. The magnetic field of the current may influence the PD performance in the long term due to its possible influence on the direction of growth of the electrical tree structure.

A Cable Defect Localization Method Based on Multiresolution Singular Value Decomposition and Stochastic Subspace Identification

A Cable Defect Localization Method Based on Multiresolution Singular Value Decomposition and Stochastic Subspace Identification

A Novel Time–Frequency-Domain Reflectometry Location Method for Power Cable Defects Based on Synchrosqueezing Transform

A Novel Time–Frequency-Domain Reflectometry Location Method for Power Cable Defects Based on Synchrosqueezing Transform

Research on Cable Insulation Layer Defect Detection Based on Terahertz Technology

The insulation layer of a cable plays a very important role in protecting the cable. If defects such as voids and detachment occur in the insulation layer of the cable, it can lead to a short circuit in the cable and cause a fire. In this article, a new insulation layer detection method is proposed, which uses terahertz equipment to detect defects in cables and obtain terahertz images with defects. However, some defect images are relatively blurry. Morphological algorithms are used to denoise and enhance the blurry images to obtain high-quality defect images to determine the location and size of defects. Terahertz technology has become a new method for detecting defects in cable insulation layers and is increasingly widely used.