Pipeline Defects Research Articles

Pipeline inspection using a low-cost Wi-Fi based intelligent pigging solution

This study presents a low-cost smart pipeline inspection gauge (PIG) designed for pipeline defect (leakage) detection, and for quick data access and recovery for the purpose of analysis, utilizing locally sourced materials and off-the-shelf sensors and electronics. The PIG’s electronic circuit is designed to house the sensors and allow for easy reception and transfer of pressure measurements to the pipeline manager’s laptop via a WiFi module. A pressure sensor, a motion sensor, a wireless communicator, and an Arduino Microcontroller are utilized in the development of this PIG. The PIG was tested experimentally by being put through stationary, no load-no defect, and no load-defect tests respectively. The PIG was kept still during the stationary tests but was conveyed within a 160 mm diameter Polyvinyl Chloride (PVC) conduit with a length of 6.7 m for both the no load-no defect and no load-defect tests, using a 0.125 Hp direct current (DC) motor, with a gearbox attachment to pull from one end to the other. Using a WiFi module and the PuTTY program, the pressure values were retrieved. The test results revealed that P1 (front pressure) values were higher than P2 (rear pressure) values for the no load tests. P1 readings ranged from 1213 to 1214 Pa, with an average of 1213.86 Pa for the no load-no defect tests. The average P2 value was 1094.24 Pa, with a range of 1094.24 Pa to 1094.75 Pa. The pressure values for the no load-defect cases began at 1226.8 Pa and steadily decreased for the first 1.5 minutes, then remained at an average of 1214.2 Pa for the next 20 seconds until they arrived at the first defected point, where a value of 1216.1 Pa was recorded. The PIG traversed the pipeline until it had caught all of the pressure pulses at the defective sites. The higher pressure pulses (spikes) observed at the points of defects created along the pipeline in the experimental results from the no load-defect tests indicates that the Smart PIG was capable of detecting the created defects and demonstrated that the low-cost Smart PIG can be used to detect leakages on a pipe and can also be deployed in real life situations.

Automated Classification of Pipeline Defects from Ultrasonic Phased Array Total Focusing Method Imaging

The defects in the welds of energy pipelines have significantly influenced their safe operation. The inefficient and inaccurate detection of the defects may give rise to catastrophic accidents. Ultrasonic phased array inspection is an important means of ensuring pipeline safety. The total focusing method (TFM), using ultrasonic phased arrays, has become widely used in recent years in non-destructive evaluation (NDE). However, manual defect recognition of TFM images is seen to lack accuracy and robustness, arising from deficiency of practical experience. In this paper, the automated classification of different defects from TFM images is studied with a view to facilitate inspection efficacy. By experimentally implementing the TFM approach on a bespoke specimen, the images corresponding to crack-like defects and pore-like defects were employed to investigate the effectiveness of four different machine learning models (known as Support Vector Machine, CART Decision tree, K Nearest Neighbors, Naive Bayes) containing data augmentation, feature extraction and defect classification. The results suggested that the accuracy of defect classification using the HOG-Poly-SVM algorithm was 93%, which outperformed the results from other algorithms. The advantage of the HOG-Poly-SVM algorithm used in defect classification of ultrasonic phased array TFM data is discussed by conducting ten-fold cross validation and other evaluation metrics. In this paper, in order to improve the efficiency of detecting pipeline defects in the future, and for testing test blocks simulating buried pipelines containing defects, we proposed, for the first time, that ultrasonic phased-array TFM imaging results in small object detection images, and found that the SVM algorithm was applicable to ultrasonic phased array TFM imaging, providing a research method and ideas for the use of artificial intelligence in industrial non-destructive testing.

Bimorph sensor based in-line inspection method for corrosion defect detection in natural gas pipelines

Recently, bimorph sensors based on the in-line inspection (ILI) method have shown considerable promise for detecting surface defects (e.g., corrosions) in gas pipelines. However, the effect of physical parameters such as bimorph position and scanning speed on the performance of the bimorph sensor has not yet been investigated. As a result, the capability of the bimorph sensor for defect detection in pipelines is not clear. This study aims to optimize the physical parameters and investigate the influence of physical parameters on the performance of the bimorph sensor. For this purpose, first various corrosion defect sizes were considered and analyzed using piezoelectric theory. Next, an analytical relationship between the vibration response of the bimorph sensor and defect is derived using the Euler-Bernoulli beam theory. Finally, a real-time field test was conducted based on the installation of the proposed method on a developed smart PIG to demonstrate the detection efficiency of the bimorph sensor. The novel contributions of this study are as follows: (1) The proposed analytical method uses cantilever beam vibrational mode shapes together with the piezoelectric effect to detect and quantify the corrosion defects. (2) The current study proposed a bimorph sensor method capable of performing high scanning speed (0.5 m/s) in real-time pipeline inspection. (3) The performance of the proposed method on the various position of bimorph on the cantilever probe and scanning speed is studied analytically and experimentally. (4) Multiple corrosion defects and pipeline joints were detected and localized successfully in complex pipeline networks. • Proposed a bimorph sensor method to detect corrosion defects in gas pipelines. • Performance of the proposed method is investigated analytically and experimentally. • Bimorph sensor is designed and tested in a laboratory testbed. • Effectiveness of the proposed method on various physical parameters is presented. • Field test is conducted with the designed bimorph sensor array.

Time domain numerical modelling of guided wave excitation in fluid-filled pipes

Acoustic waves have been widely used to inspect pipeline defects, including leakage, blockage and corrosion etc. The time-domain excitation of guided waves in the fluid/solid coupled pipeline system has rarely been studied theoretically. This requires the incorporation of a source term in the coupled system. This article introduces a finite element based numerical model to study the excitation of guided waves in the coupled system with a sound source either in the fluid or on the pipe wall. A compatible pair of time-domain Perfectly Matched Layers (PMLs) have been proposed to absorb pipe end reflections in the elastic wall and in the fluid respectively. These fluid/solid PML numerical formulations are coupled and the implementation of the coupling is introduced. The numerical model is validated against an enlarged model without PML, and excellent agreement has been achieved. The numerical model shows that the dominant excited wave mode is a fluid type wave mode when the sound source is a fluid source or a radial elastic line source. However, the dominant excited wave mode is a structure type wave mode when the sound source is an axial elastic line source. • A compatible pair of fluid and elastic PML formulations have been proposed. • A mixed displacement-strain un-split formulation is proposed in the elastic domain. • A mixed velocity potential-velocity un-split formulation is proposed in the fluid domain. • Fluid or radial elastic line source excites a fluid dominant wave mode in the low frequency range. • Axial elastic line source excites a structure dominant wave mode in the low frequency range.

축대칭 반사모드 특성 규명 및 배관 결함검출

The converted modes generated by mode conversion in guided waves-based inspection can provide plenty of defect information, and the reasonable usage of multiple wave modes can improve the results of defect inspection and evaluation. This paper focuses on the inter-conversion process of axisymmetric modes for incident longitudinal modes when interacting with the defects in pipeline whilst ignoring the converted non-axisymmetric modes through suppressing them in reception. This process is defined as symmetric mode conversion in this research. The pattern of axisymmetric mode sequence during symmetric conversion is identified and the method is proposed to extract the converted axisymmetric mode components for analysis. The relationships between the defect features and the modes generated in symmetric mode conversion under the excitation of longitudinal mode waves are investigated. The results show that longitudinal modes in symmetric mode conversion provide the potential for establishing an effective defect inspection.

Experimental evaluation of multi-jointed soft detection arm of geometry inspection gauges for detecting internal convex defects in natural gas pipelines

Regular deformation inspection of in-service natural gas pipelines can reduce accidents caused by pipeline failure. In this study, a novel contact-testing geometry inspection gauge is proposed, and its multi-jointed soft detection arm is the focus of our study. 3D printing technology and mold casting were used to fabricate a newly designed detection arm. A finite element method was used to analyze the process of the detection arm passing through the convex defect and optimize its joint number. Then, a series of comparison experiments were conducted with various convex defects to evaluate the superiority of the measuring performance of the multi-jointed soft detection arm. The experimental results show that compared to the no-jointed detection arm, the multi-jointed detection arm has a more accurate experimental value, especially for defects with closer heights (8 and 10 mm) and is relatively more stable in repeated experiments. This study provides options for the design of a flexible caliper pipeline inspection gauge for deformation inspection in pipelines.

Three-dimensional finite element analysis and research of leakage magnetic field of flake, pit, through-hole defect in petroleum pipelines

Abstract Flake, pit and through-hole defects are the three common types of defects in oil pipelines. In practical testing applications, it is necessary to clarify the magnetic leakage characteristics of different defects and set reasonable detection points to distinguish different types of defects accurately and quantify the degree of each defect precisely. In this paper, the leakage magnetic field of flaky, pitted and through-hole tube wall defect is analyzed. Using three-dimensional finite element simulation, the spatial stereo model of leakage magnetic field is inverted by extracting the data of characteristic nodes. The distribution of the leakage magnetic field in space, for the radial and circumferential components is obtained. On this basis, the effect on the main components of magnetic leakage field at different locations in space is determined, and the best of placing a potential sensor for detecting three kinds of defects in space are derived. This provides a basis for determining sensor locations in magnetic leakage detection devices, inverting defect models from multi-sensor data and accurately quantifying the degree of defects.

Cross-domain feature selection and diagnosis of oil and gas pipeline defects based on transfer learning

Developing intelligent pipeline defect diagnosis technology is of great significance to ensure the efficiency and safety of pipeline transportation. However, a challenge in real-world tasks is the inadaptability and instability of these technologies for processing data from different distributions. Therefore, this paper proposes an intelligent transfer defect diagnosis framework that combines a hybrid feature selection method and transfer learning (TL) technology. The hybrid feature selection method consists of two cross-domain filtering feature selection methods and feature subset evaluation. A Monte Carlo simulation wrapper is used to obtain the best transfer feature subset. The obtained optimal feature subset is fed to the feature adaptation-based classification method for defect diagnosis. We used two different datasets as the target domain and source domain and simulated two transfer scenarios to verify the framework. Experimental results demonstrate that the proposed diagnosis framework achieves high accuracy and effectiveness in pipeline defect diagnosis cross-domain transfer tasks. This will facilitate pipeline maintenance engineers in solving the problem of pipeline defect diagnosis and reasonably arranging pipeline maintenance.

A novel unbalanced weighted KNN based on SVM method for pipeline defect detection using eddy current measurements

Pipeline safety inspections are particularly important because they are the most common means of energy transportation. In order to avoid pipe leakage, eddy current inspection is often used in metal pipe defect detection. However, in practice, due to problems such as noise and interference, a small number of labeled pipeline defect samples, and unbalanced sample distribution, the detection task cannot be completed. To address the above problems, this study proposes an unbalanced weighted k-nearest neighbor (KNN) based on support vector machine (SVM) defect detection algorithm. The multi-segment hybrid adaptive filtering algorithm is adopted to improve the identification of strong interference and large noise eddy current signals in this paper while retaining useful information such as defects. At the same time, the unbalanced weighted KNN based on the SVM defect detection algorithm is used to solve the problems of low accuracy and large limitations of the algorithm. The experimental results show that, compared with the KNN and SVM algorithms, the detection rate, false detection rate, and missed detection rate of defects are significantly improved.

An Automatic Defect Detection System for Petrochemical Pipeline Based on Cycle-GAN and YOLO v5.

Defect detection of petrochemical pipelines is an important task for industrial production safety. At present, pipeline defect detection mainly relies on closed circuit television method (CCTV) to take video of the pipeline inner wall and then detect the defective area manually, so the detection is very time-consuming and has a high rate of false and missed detections. To solve the above issues, we proposed an automatic defect detection system for petrochemical pipeline based on Cycle-GAN and improved YOLO v5. Firstly, in order to create the pipeline defect dataset, the original pipeline videos need pre-processing, which includes frame extraction, unfolding, illumination balancing, and image stitching to create coherent and tiled pipeline inner wall images. Secondly, aiming at the problems of small amount of samples and the imbalance of defect and non-defect classes, a sample enhancement strategy based on Cycle-GAN is proposed to generate defect images and expand the data set. Finally, in order to detect defective areas on the pipeline and improve the detection accuracy, a robust defect detection model based on improved YOLO v5 and Transformer attention mechanism is proposed, with the average precision and recall as 93.10% and 90.96%, and the F1-score as 0.920 on the test set. The proposed system can provide reference for operators in pipeline health inspection, improving the efficiency and accuracy of detection.

A Feature Selection–Based Intelligent Framework for Predicting Maximum Depth of Corroded Pipeline Defects

A Feature Selection–Based Intelligent Framework for Predicting Maximum Depth of Corroded Pipeline Defects

Electromagnetic Pigging System Based on Sandwich Differential Planar Coil

In-pipeline inspection is an important precontrol method to ensure the safety of oil and gas pipeline transportation. This article proposes an electromagnetic in-pipe detector based on passive resonance-enhanced differential planar coils to detect defects on the inner surface of pipes. Both qualitative and quantitative analyses of pipeline defects and damage are developed. The introduction of passive resonant coils is shown to significantly improve the detection capability of the sensor. This is coupled with the establishment of a theoretical derivation model of the proposed structure. The hardware platform of the laboratory system has been built, and an eddy current internal detector suitable for 8-in-diameter pipes is developed and integrated into the system. Numerical simulations and experimental verifications on flat defects and pipe defects have been undertaken. The obtained results have shown that the real defects have been correctly detected, and the system is effective, reliable, and efficient.

Automatic defogging, deblurring, and real-time segmentation system for sewer pipeline defects

Conventional deep-learning-based inspection methods for sewer pipeline defects neglect the complex inner environment of pipelines (e.g., fog and motion blur) and real-time segmentation despite their high accuracy for clear images. To solve the problem of low accuracy and slow speed of fuzzy image inspection, a novel defogging, deblurring, and real-time segmentation system for sewer pipeline defects is proposed. First, an attention-based algorithm for defogging and a generative adversarial network (GAN) for deblurring are created to improve the sharpness of pipeline images. Second, a real-time segmentation network called Pipe-Yolact-Edge is proposed to detect the defects in pipeline images at a pixel level, which achieves the highest mean average precision (mAP) of 92.65% and the fastest speed of 41.23 frames per second (fps) among the state-of-the-art segmentation networks. Comparison experiments show that the mAP of the proposed segmentation model is improved by 7.93% and 15.43% after defogging and deblurring of pipeline images, respectively, thus revealing the impact of Pipe-Defog-Net and Pipe-Deblur-GAN. In particular, the proposed defogging and deblurring methods for pipeline images can reduce the effects of contrast reduction, boundary enlargement, and missing inspection of small defects caused by fog and motion blur. Finally, the trained model is transferred into a small development device to segment the images of pipeline defects on site.

Image Classification Method Based on Improved Deep Convolutional Neural Networks for the Magnetic Flux Leakage (MFL) Signal of Girth Welds in Long-Distance Pipelines

Girth weld defects in long-distance oil and gas pipelines are one of the main causes of pipeline leakage failure and serious accidents. Magnetic flux leakage (MFL) is one of the most widely used inline inspection methods for long-distance pipelines. However, it is impossible to determine the type of girth weld defect via traditional manual analysis due to the complexity of the MFL signal. Therefore, an automatic image classification method based on deep convolutional neural networks was proposed to effectively classify girth weld defects via MFL signals. Firstly, the image data set of girth welds MFL signal was established with the radiographic testing results as labels. Then, the deep convolutional generative adversarial network (DCGAN) data enhancement algorithm was proposed to enhance the data set, and the residual network (ResNet-50) was proposed to address the challenge presented by the automatic classification of the image sets. The data set after data enhancement was randomly selected to train and test the improved residual network (ResNet-50), with the ten validation results exhibiting an accuracy of over 80%. The results indicated that the improved network model displayed a strong generalization ability and robustness and could achieve a more accurate MFL image classification of the pipeline girth welds.

Guided Wave Focusing Imaging Detection of Pipelines by Piezoelectric Sensor Array

The sensor array-based guided wave focusing detection method can effectively improve the detection sensitivity of defects and realize the visual imaging. In this research, the three-dimensional finite element simulation model of stainless steel pipeline for guided wave focusing detection was established, and the L(0, 2) mode of guided wave was excited by applying a load on the end surface of the pipeline. And in the experiment, the excitation and reception of L(0, 2) mode guided waves on the outer surface of the stainless steel pipeline were realized by the piezoelectric transducer array. A 16-channel guided wave focusing experimental system was integrated to conduct the defect detection experiments on a stainless steel pipe with diameter of 140 mm and wall thickness of 5 mm. The total matrix data acquisition was performed, and then the amplitude total focusing (TFM) imaging and sign coherence factor (SCF) imaging of the pipe were realized. In this way, the experimental results showed that the pipeline defect detection method and the system proposed in this research can achieve the longitudinal and circumferential positioning and imaging of defects, like holes and scratches.

Novel intelligent diagnosis method of oil and gas pipeline defects with transfer deep learning and feature fusion

The destruction of oil and gas pipelines may result in enormous financial loss and significantly affect public safety. Hence, early defect diagnosis of oil and gas pipelines is of immense significance. In order to improve the accuracy and reliability of oil and gas pipeline defect detection and diagnosis with limitation of small and poor data sets, this paper proposes intelligent diagnosis and recognition method based on Transfer deep learning, Continuous Wavelet and Short-time Fourier Time-Frequency feature fusion, and Strengthen Convolutional Neural Network (TWSC). Oil and gas pipeline defects are converted into identifiable defect signals by the three-coil bidirectional excitation detector. Feature fusion, focusing on different feature distribution composed of Short-Term Fourier Transform (STFT) and Continuous Wavelet Transform (CWT), is introduced as the input of the TWSC model. It effectively extracts the time-frequency features of the defect signal on different feature distribution, and complements each other. A deep convolutional neural network with strengthen convolution kernel is constructed as a diagnostic model, expanding receptive field of diagnosis. For most practical engineering problems that only have a small data set with partial poor samples, transfer learning is introduced in the model to optimize the diagnostic performance. Parameter transfer from transfer network is operated to initialize the diagnostic model parameters. The limitation of insufficient training with a small data set and interference of poor samples during model initial training progress are both greatly improved. Under the conditions of oil and gas stations and laboratories, the typical oil and gas pipeline defects are collected to analyze. For simulating complex working conditions, the diagnosis performance of add-noise signal is verified. The final results show that TWSC intelligent diagnosis method proposed in this paper has a good performance on diagnosis accuracy and stability in defect diagnosis of oil and gas pipelines.

Simulation Analysis of External Damage and Repair of the Gas Transmission Pipeline

External damage and repair of a gas transmission pipeline were often encountered in industrial production. The damage of the gas transmission pipeline and the evaluation after repair could be solved by the finite element simulation method. Damage assessment and postrepair assessment were carried out for an external damage example of a gas transmission pipeline in an oil field based on finite element software ABAQUS. Ideally, the finite element simulation results were modified by using the theoretical calculation results of the gas transmission pipeline. Then, the simulation analysis of the defective gas transmission pipeline was carried out, and the corresponding maintenance suggestions were put forward. Finally, the B-type sleeve repair and carbon fiber composite repair were simulated and analyzed, respectively, and the bearing and stress of two kinds of repair were compared and analyzed. It was concluded that the repair effect of the carbon fiber composite was better than that of B-type sleeve. The research results could provide a new evaluation mechanism for pipeline defects and pipeline defects after repair and laid a foundation for quantitative risk assessment and repair of gas transmission pipelines.

STRESS ANALYSIS OF INTERLAYER DEFECTS IN THIN-WALLED LINING RECYCLED COMPOSITE PIPE

The aim of this paper is to study the stress distribution law of corrosion defects in pipelines before and after repair of thin-walled lining and the effect of repair. The calculation model for corrosion defects in pipelines was established by the equilibrium differential equation of elastic–plastic mechanics. Based on ABAQUS finite element software, the pipeline model with a single corrosion defect was established. The material of the pipeline was API 5L X52N with an outer diameter of 324[Formula: see text]mm and a thickness of 10[Formula: see text]mm. The material constitutive relation was an ideal elastic–plastic model. We changed the depth-to-thickness ratio of corrosion defects ([Formula: see text], 0.1, 0.5, 0.8) and used the different lining repair materials (stainless steel and FRP). At the same time, ignoring the thickness of bonding layer and its influence on the filling of corrosion pit, the interface interaction analysis model was established by the bonding behavior between layers. We compared the stress at the corrosion defect before and after repair. It is found that with the increase of the depth-to-thickness ratio of corrosion defects, the radial stress, circumferential stress, and Mises stress at the corrosion defect all tend to increase. The circumferential stress at the defect before the repair is the largest, and its value is similar to the Mises stress. After the repair of stainless steel lining, the circumferential stress at the defect is reduced by 11.01%, and the Mises stress is reduced by 14.18%; after the repair of FRP lining, the circumferential stress at the defect is reduced by 7.01%, and the Mises stress is reduced by 3.54%. The depth-to-thickness ratio of corrosion defects has a significant impact on the stress distribution of pipelines. Therefore, the influence of corrosion depth should be paid attention to in the pipeline safety assessment. Before and after repair, the control stress at the corrosion defect of the pipeline is always the circumferential stress. The failure can be judged according to the circumferential stress; after the repair of thin-walled lining, the stress at the original defect is redistributed, and the circumferential stress and Mises stress are reduced, and the repair effect is obvious.

Investigating the micro-turbulent corrosion mechanism of pipeline defects based on a combined experimental and simulation approach

The existence of pipeline defects in oil and gas gathering pipelines predisposed the pipeline to rupture under the synergistic effects of local micro–turbulence and electrochemical corrosion. Here, a combination of experimental and simulation methods was proposed to facilitate the investigation of CO2 corrosion and the mass transfer process in pipeline defects. The corrosion kinetic characteristics of the defect region were clarified by coupling wire beam microelectrode (WBE) and electrochemical impedance spectroscopy (EIS). Additionally, the effect of flow mass transfer on the corrosion of pipeline defects was investigated by using the existing mass transfer models and COMSOL Multiphysics simulations. The results showed that different locations of the pipeline defects exhibited different mass transfer behavior and corrosion variations. The mass transfer process at the bottom of the defect was lower than that in the upper and lower edge of the defect. Furthermore, the bottom of the defect behaved as an anode and corrodes more severely at low flow velocities. The enhanced mass transfer process led to more severe corrosion at the upper and lower edges of the defect at high flow velocities.

A novel adaptive noise reduction method for field natural gas pipeline defect detection signals

To suppress noise interference and improve defect identification accuracy, we propose a transfer learning-based adaptive wavelet neural network (AWNN) method for pipeline defect detection signal denoising. Simulated noisy signals and field detection signals are used to determine the network's initial structure and fine-tune its parameters. The Meyer wavelet basis function is chosen as an excitation function based on the defect signal waveform. The pretrained structure is determined by a search algorithm. The network parameters are adaptively fine-tuned according to the sample entropy of the noise. The new genetic beetle antennae search strategy (GBA) optimization algorithm is proposed to improve the AWNN to avoid local optima. Compared with traditional noise reduction methods, the AWNN has excellent ability to recovery the pure denoised signal with a higher SNR and smaller RMSE. The AWNN can realize adaptive noise reduction of different field signals, providing reliable input for subsequent defect diagnosis.