Pipeline Defects Research Articles

Deep Learning-Based Automatic Defect Detection Method for Sewer Pipelines

To address the issues of low automation, reliance on manual screening by professionals, and long detection cycles in current urban drainage pipeline defect detection, this study proposes an improved object detection algorithm called EFE-SSD (enhanced feature extraction SSD), based on the SSD (Single Shot MultiBox Detector) network. Firstly, the RFB_s module is added to the SSD backbone network to enhance its feature extraction capabilities. Additionally, multiple scale features are fused to improve the detection performance of small target defects to some extent. Then, the improved ECA attention mechanism is used to adjust the channel weights of the output layer, suppressing irrelevant features. Finally, the Focal Loss is employed to replace the cross-entropy loss in the SSD network, effectively addressing the issue of imbalanced positive and negative samples during training. This increases the weight of difficult-to-classify samples during network training, further improving the detection accuracy of the network. Experimental results show that EFE-SSD achieves a detection mAP of 92.2% for four types of pipeline defects: Settled deposits, Displaced joints, Deformations, and Roots. Compared to the SSD algorithm, the model’s mAP was increased by 2.26 percentage points—ensuring the accuracy of pipeline defect detection.

Analysis and prediction of pipeline corrosion defects based on data analytics of in-line inspection

In-line inspection (ILI) is important to pipeline integrity management since it can detect pipeline defects and identify potential failure locations through periodical examinations. However, effectively evaluating defects based on ILI data is challenging. Measurements of ILI are easily influenced by instrument performance and maintenance activities, leading to unmatched and imbalanced data. Poor ILI data make it difficult to establish defect growth models based on multiple inspections. This study conducted comprehensive analysis of ILI data for evaluating corrosion defects of a steel pipeline. First, statistical analysis was performed on raw data to visualize distributions of corrosion depths and number of corrosions. Second, hierarchical clustering method was used to classify corrosion severity levels based on features of corrosion depth and estimated repair factor. The interaction effect between adjacent corrosions was considered. Machine learning methods, including k-nearest neighbor, support vector machine, random forest, and light gradient boosting machine were used to explore the relationship between the location parameters of adjacent corrosions and severity levels. Then, maximum corrosion depths and corrosion density were filtered from raw ILI data of multiple inspections, which were critical for pipeline failure prediction. Finally, distribution parameters were fitted to establish stochastic growth models on maximum corrosion depth and corrosion number density. This study presents data analytics based approach to obtain valid information from ILI data in practice.

Structural Optimization and Simulation of a Magnetic Leak Detection Device for Streak-like Defects in Oil Pipes

Striped defects are a common type of defects in oil pipelines, divided into horizontal and longitudinal stripes, and it is difficult to accurately quantify the results of conventional pipeline leakage magnetic detection to correspond to the type of defects and their extent. In this paper, a new type of oil pipe non-destructive testing equipment is proposed and designed based on the principle of magnetic leakage detection using three-dimensional finite element simulation, and the magnetic field distribution inside the equipment is simulated using ANSYS finite element analysis software to provide original data reference for the development of the new equipment.

Research on magnetic inversion in alternating current magnetic flux leakage testing

Defects bring significant security risks to pipelines, which are essential carriers in oil and gas transportation. However, when alternating current magnetic flux leakage (AC-MFL) testing is applied to pipeline defect detection, the morphological reversal of the detection signal under specific parameters has adverse effects on defect identification and quantification. This paper identifies and explains the phenomenon of detection signal morphological reversal in AC-MFL testing, which is defined as magnetic inversion (MI). Based on the AC-MFL testing mechanism, the causes of MI are analysed. The influence of the excitation current frequency, excitation current intensity and defect depth on MI is numerically analysed using the finite element method. The excitation current frequency and the defect depth are important factors causing MI, but the excitation current density is not. MI only occurs when deep defects are detected under low-frequency excitation. The boundary conditions of AC-MFL testing are further clarified.

Quantization of magnetic flux leakage internal detection signals for composite defects of gas and oil pipelines

This study aimed to solve the quantitative problem of the magnetic flux leakage (MFL) internal detection signals of long-distance oil and gas pipelines. Based on the magnetic charge theory, the numerical–analytical model for MFL internal detection of pipeline complex defects was constructed by introducing stress factor in this work. This model was used to investigate the changes of magnetic signals caused by different division sizes of the defective end-face. The distribution pattern of MFL signal under different geometric sizes and stresses of defective end-face was analyzed, and its influence on the characteristics of magnetic signals was assessed. The effectiveness of the model was verified through experiments. The results indicated that the overall accuracy of magnetic signal analysis by determining the optimal division size on the end face defects was improved by 35% compared with the conventional magnetic charge model, in which the calculation accuracy for defects with depth less than 25% of wall thickness was 41%. The axial signal component had extreme values. The radial component showed sinusoidal fluctuations, accompanied by peaks and troughs. The magnetic signal component increased non-linearly with the increase of the depth and width of the defect, and the incremental change increased first and then decreased. The magnetic signal components exponentially decreased with the increase of defect stress under magnetic saturation, and the decay rate gradually decreased with the increase of stress.

Design and Implementation of Three-Channel Drainage Pipeline Ground Penetrating Radar Device.

In order to solve the current problems that conventional video inspection can only detect, as an internal pipeline defect and drainage pipeline radar inspection device detects in a single direction and at radar frequency in water pipeline defect detection, a three-channel drainage pipeline ground penetrating radar (GPR) inspection device was designed and developed, the assembly and commissioning of the device prototype were completed, and an actual engineering test application was carried out. Focusing on the problem that the detection direction and depth of the single-channel detection device are limited, a three-channel drainage pipeline GPR inspection device is designed to realize the synchronous detection of the inside of the pipeline, the pipeline body, and the external environment of the pipeline, improving the detection depth and efficiency. According to the design scheme of the three-channel drainage pipeline GPR inspection device, the assembly of the device prototype was completed. The device contains three radar channels, the top of the main frequency of the antenna is 1.4 GHz, the two sides are 750 MHz, the video camera has a pixel count of 4 million, and the positioning accuracy is less than 1 mm, the waterproof grade is IP68, the detection accuracy of pipe deformation (slope) is 0.1°, the detection depth outside the pipe is 1.2 m, and the detection accuracy of corrosion thickness is 15 mm. In a practical application of the device, the Jianguomenqiao sewage pipeline in Beijing, China, was tested, resulting in the discovery of 87 defects, including 39 loose soil areas at the bottom of the pipe exterior, 40 void areas, and 8 cavities.

Quantitative study on the propagation characteristics of MFL signals of outer surface defects in long-distance oil and gas pipelines

The magnetic flux leakage (MFL) internal detection is one of the most effective methods for assessment of long-distance oil and gas pipelines. To quantify the outer surface defect through MFL signals, which are affected by pipe wall and its shielding effect, propagation compensation factor (PCF) was proposed to apply to a classical magnetic charge model. Using the established model for outer surface defects in long-distance oil and gas pipelines, characteristics of MFL signals with different wall thicknesses and defect sizes along with their propagation patterns were analyzed. To verify the analytical model, X70 pipes with different wall thicknesses were used for systematic experiments. The results showed that the pipe wall thickness had a significant attenuation effect on the MFL signals of external defects. As the wall thickness increased from 7 to 17 mm, the MFL signals exhibited a first-order exponential decay, with a maximum error of 25.8% and a minimum error of 2.5%. When the defect depth increased from 0.6 to 7.2 mm, the MFL signals showed a first-order exponential upward trend, with a maximum error of 18.8% and a minimum error of 2.0%. This study effectively described the propagation characteristics of MFL signals of outer surface defects, and facilitated identification and quantitative evaluation of outer surface defects.

Machine-Learning-Based Classification for Pipeline Corrosion with Monte Carlo Probabilistic Analysis

Pipeline corrosion is one of the leading causes of failures in the transmission of gas and hazardous liquids in the oil and gas industry. In-line inspection is a non-destructive inspection for detecting corrosion defects in pipelines. Defects are measured in terms of their width, length and depth. Consecutive in-line inspection data are used to determine the pipeline’s corrosion growth rate and its remnant life, which set the operational and maintenance activities of the pipeline. The traditional approach of manually processing in-line inspection data has various weaknesses, including being time consuming due to huge data volume and complexity, prone to error, subject to biased judgement by experts and challenging for matching of in-line inspection datasets. This paper aimed to contribute to the adoption of machine learning approaches in classifying pipeline defects as per Pipeline Operator Forum requirements and matching in-line inspection data for determining the corrosion growth rate and remnant life of pipelines. Machine learning techniques, namely, decision tree, random forest, support vector machines and logistic regression, were applied in the classification of pipeline defects using Phyton programming. The performance of each technique in terms of the accuracy of results was compared. The results showed that the decision tree classifier model was the most accurate (99.9%) compared with the other classifiers.

A Multi-Sensor Detection Method Based on WGAN-GP and Attention-Bi-GRU for Well Control Pipeline Defects

A Multi-Sensor Detection Method Based on WGAN-GP and Attention-Bi-GRU for Well Control Pipeline Defects

A new evaluation method of dented natural gas pipeline based on ductile damage

Dent is the most common defect on natural gas pipelines, leading to pipe leakage or rupture. Since the dent depth-based failure criterion is unreasonable, this work proposed a new ductile damage-based evaluation method for dented natural gas pipelines. The new method was proposed by finite element analysis combined with Oyane ductile damage criterion. Specifically, a finite element-based model was developed to model the formation process of an unconstrained dent, and its accuracy was verified by comparison with test data. A new parameter called the pipeline defect parameter was defined as the ratio of the dent depth to the pipeline diameter to illustrate the dimensionless of dent depth. Then, two safety indicators based on pipeline defect parameter, i.e., monitoring and repairing thresholds, of dented pipelines were determined considering the dent springback. The parameter effects, i.e., indenter geometries and size, as well as internal pressure, were determined. Finally, the proposed method's adaptability and reasonable were demonstrated by case studies. It is expected to provide a useful method for operating dented natural gas pipelines safely.

Finite element study of remote field eddy current methods for inner diameter and outer diameter pipeline defect classification

Remote field eddy current (RFEC) methods are widely applied for detecting pipeline defects. However, current RFEC methods cannot distinguish inner diameter (ID) defects from outer diameter (OD) defects. In addition, existing RFEC probes are usually driven by an extremely low-frequency signal, which reduces the detection efficiency. To address these issues, a novel external RFEC probe is designed to improve the detection performance. First, the probe structure is designed using a simulation tool. Second, the excitation and structural parameters are optimally selected. Finally, the relationships between the signal features and the defect dimensions are analysed. The results show that the probe can realise the RFEC effect without shield cages, the exciting frequency is significantly improved and the phase angle can be used to classify ID and OD defects.

EXPERIENCE IN THE APPLICATION OF NON-DESTRUCTIVE TESTING METHODS CONTROL IN THE OPERATION OF PRODUCTS

The article summarizes the practical experience accumulated by the author in the application of non-destructive testing methods in the operation of aviation equipment, main gas pipelines, railway rolling stock. The main criteria for the selection of non-destructive testing methods, their applicability depending on the depth of the defect location and the maximum achievable sensitivity of the method are considered. The main advantages and disadvantages of non-destructive testing methods are indicated specific examples are given: –the influence of manufacturing defects in the material of products (main gas pipelines, railway rolling stock) on the detection of operational cracks; –an erroneous approach to ultrasonic inspection of zones of “tight” connection of two smoothly processed parts of the product and ways to eliminate such errors; –incorrect testing of the control technology, without taking into account: statistics on rejection of parts during their repair, the causes of the destruction of the part, the influence of the operating conditions of the product; the influence of ambient temperature. Recommendations are given on the search zones for operational defects of technological gas pipelines. Recommendations have been worked out to eliminate the identified shortcomings. The author gives examples of the application of non-destructive testing methods for 30 years of his practical activity.

Experimental study on strain and failure location of interacting defects in pipeline

The interaction between adjacent defects significantly influences the internal pressure loading capacity of corroded pipelines, and the failure pressure of the interacting defects is lower than that the defects would attain when they were isolated. Therefore, it is necessary to study the interaction mechanism between different defects. The experimental program described in the paper involves seamless steel tubes with D/t = 31 and different sizes of interacting defects. The fluid is passed inside the sealed pipeline and the failure pressure of such locally corroded pipeline was obtained experimentally. The strains within and between the defects were measured using strain gauges and the measured data were analyzed. The results of full-scale corroded pipeline tests showed that the strain of failure defect will rise first and then decrease, and the interaction between this defect and adjacent defects is the most obvious. Through the analysis of the failure location of interacting defects with internal pressure, it can be seen that the failure location was the defect with the lowest internal pressure bearing capacity for adjacent defects with significantly different failure pressures. In contrast, the failure location was the defect in the middle of the corrosion region for adjacent defects with no significant difference in failure pressure.

Semi-supervised pipeline anomaly detection algorithm based on memory items and metric learning

ABSTRACT Traditional detection algorithms of pipeline non-destructive testing extract information from a large number of defect samples to ensure the detection performance, but even if an adequate of defect samples are collected, it is difficult to enumerate the possible defect morphology in nature. In this paper, we proposed a new semi-supervised anomaly detection algorithm to solve the existing problems. We consider using the most representative feature vectors generated by feature extractor as memory items to represent background information. In addition, this paper also imports a few defect samples to form a semi-supervised structure in the training stage and introduces a metric learning module to make the memory items have the ability to fully represent the background and enhance robustness. To prove the effectiveness of our algorithm, this paper has verified its performance in micro-size pipeline defects. In the experiment, the high-definition industrial camera was used to scan and record the image sequence from the inner surface of the pipeline sample. The latest anomaly detection algorithms have been used as a platform for objective performance evaluation. The result shows our algorithm is more effective in pipeline defect detection and has strong robustness for anti-interference.

Analysis and application of weak guided wave signal detection based on double Duffing oscillators

In this study, a double chaotic detection system was proposed to identify the weak defect echo signal caused by small defects during ultrasonic guided wave (UGW) nondestructive testing of pipelines. By identifying the amplitude and time of flight (ToF) of defect echoes, minor defects in early damage identification of pipelines were quantitatively detected. First, the Duffing oscillator detection system parameters were determined using the displacement bifurcation diagram and a Poincare map. Thereafter, the UGW signal was added to the driving force of the Duffing system. The influence characteristics of UGWs on Duffing systems were deduced in detail, and the identification method of the UGW amplitude was obtained. Two Duffing chaotic systems with specific frequencies were constructed, and the ToF of the UGW was determined from the compensation phase. Simulation and experimental results showed that this method could identify the size and ToF of UGWs simultaneously. Even when the signal-to-noise ratio (SNR) was −20 dB, the identification error of the amplitude was only 8 %, which indicated that the detection result was acceptable. Pipeline defects identified using this method, in which the identification error of the defect size was below 7 %, and the defect location identification error was below 6 %, indicated that the method could effectively improve the sensitivity of UGWs in the detection of small defects in a pipeline. This provided a guarantee for early damage identification of a pipeline.

Deep Learning for Magnetic Flux Leakage Detection and Evaluation of Oil & Gas Pipelines: A Review

Magnetic flux leakage testing (MFL) is the most widely used nondestructive testing technology in the safety inspection of oil and gas pipelines. The analysis of MFL test data is essential for pipeline safety assessments. In recent years, deep-learning technologies have been applied gradually to the data analysis of pipeline MFL testing, and remarkable results have been achieved. To the best of our knowledge, this review is a pioneering effort on comprehensively summarizing deep learning for MFL detection and evaluation of oil and gas pipelines. The majority of the publications surveyed are from the last five years. In this work, the applications of deep learning for pipeline MFL inspection are reviewed in detail from three aspects: pipeline anomaly recognition, defect quantification, and MFL data augmentation. The traditional analysis method is compared with the deep-learning method. Moreover, several open research challenges and future directions are discussed. To better apply deep learning to MFL testing and data analysis of oil and gas pipelines, it is noted that suitable interpretable deep-learning models and data-augmentation methods are important directions for future research.

A coupling model of multi-feature fusion and multi-machine learning model integration for defect recognition

As Oil and gas pipelines are vulnerable to physical defects such as dents, cracks and corrosion leading to the risk of pipeline leakage. In this context, the recognition of these pipeline defects by using magnetic flux leakage (MFL) signal can provide a reliable reference and a good evaluation standard for predicting the remaining life of in-service pipelines. Nevertheless, the complexity of the MFL signal brings severe challenges to the recognition accuracy. This study, therefore, proposes a new coupling model for defect recognition based on multi-feature fusion and multi-machine learning model integration. This model is divided into three analysis phase, namely feature extraction phase, feature fusion phase and defect recognition phase. In the first phase, three kinds of features are extracted to obtain as much defect MFL signal information as possible. In the second phase, a multi-feature fusion method based on Dempster-Shafer (DS) evidence theory and Apriori algorithm is proposed, eliminating redundant features and realizing information complementation between different feature sets. In the third phase, we introduce a multi-machine learning model integration network (Stacking) to improve the defect recognition accuracy, which is inputted by the feature subset obtained from multi-feature fusion. By combining multi-feature fusion method with the Stacking mechanism, this coupling defect recognition model realizes the recognition of defect MFL signals. Experimental work shows that the proposed model improves the recognition accuracy and has the advantages of strong anti-jamming ability.

Transformer‐optimized generation, detection, and tracking network for images with drainage pipeline defects

AbstractRegular detection of defects in drainage pipelines is crucial. However, some problems associated with pipeline defect detection, such as data scarcity and defect counting difficulty, need to be addressed. Therefore, a Transformer‐optimized generation, detection, and counting method for drainage‐pipeline defects was established in this paper. First, a generation network called Trans‐GAN‐Cla was developed for data augmentation. A classification network was trained to improve the quality of the generated images. Second, a detection and tracking model called Trans‐Det‐Tra was developed to track and count the number of defects. Third, the feature extraction capability of the proposed method was improved by leveraging Transformers. Compared with some well‐known convolutional neural network‐based methods, the proposed network achieved the best classification and detection accuracies of 87.2% and 87.57%, respectively. Furthermore, the F1 scores were 87.7% and 91.9%. Finally, two pieces of onsite videos were detected and tracked, and the numbers of misalignments and obstacles were accurately counted. The results indicate that the established Transformer‐optimized method can generate high‐quality images and realize the high‐accuracy detection and counting of drainage pipeline defects.

Ultrasonic Testing of Defects in Pipeline Based on Image Characteristics of TOFD Circumferential Scan

Ultrasonic Testing of Defects in Pipeline Based on Image Characteristics of TOFD Circumferential Scan

A Novel Cascaded Deep Learning Model for the Detection and Quantification of Defects in Pipelines via Magnetic Flux Leakage Signals

In this paper, we present a machine learning based quantitative method for the interpretation of signals gathered from non-destructive-testing (NDT) of steel pipelines via a semi-autonomous in-line-inspection (ILI) robot. The robot has a magnetic-flux-leakage (MFL) sensor that produces three axis data for each point of pipeline with specific intervals. Both the robot and the MFL sensor have been developed in-house. The signals collected via MFL sensor are converted into images to be used as input for the proposed defect detection model. We propose a combination of a defect detection model based on SwinYv5 object detection algorithm and a quantification model based on Cross-Residual Convolutional Neural Network (CR-CNN). The detected defect locations are used to extract the Region of Interest (ROI) images of defects that are used as input for the quantification model. In data collection phase, numerous tests have been conducted via a special test mechanism and a custom data augmentation technique has been deployed in order to increase the amount and variety of training data. According to test results, the proposed method is capable of detecting defects with a precision of 98.9% and quantifying them with maximum errors of 1.30, 1.65 and 0.47 mm for length, width and depth respectively.