Journal of Pipeline Science and Engineering最新文献

{"title":"A multi-level classification model for corrosion defects in oil and gas pipelines using meta-learner ensemble (MLE) techniques","authors":"Adamu Abubakar Sani ,&nbsp;Mohamed Mubarak Abdul Wahab ,&nbsp;Nasir Shafiq ,&nbsp;Kamaludden Usman Danyaro ,&nbsp;Nasir Khan ,&nbsp;Adamu Tafida ,&nbsp;Arsalaan Khan Yousafzai","doi":"10.1016/j.jpse.2024.100244","DOIUrl":"10.1016/j.jpse.2024.100244","url":null,"abstract":"<div><div>Maintaining the integrity of oil and gas pipelines is necessary for the efficient and safe transport of hydrocarbons. Corrosion defects can lead to decreased operational efficiency, leaks, a reduction in operational efficiency, and even catastrophic pipeline failures. Machine learning techniques are useful in detecting corrosion defects, ensemble methods that combine multiple classifiers offer better predictive accuracy. The aim of this work is to develop multi-level classification model an efficient ensemble technique capable of predicting the level of corrosion defects and addressing class imbalances in oil and gas pipeline data. The study uses a two-level stacking ensemble learning method that enhances corrosion defect prediction called the meta-learner ensemble (MLE). The model classifies corrosion defects into three categories: high, medium, and low. Prediction accuracy was improved by using a stacking classifier that combines multiple basic classifiers with a logistic regression meta-learner. Findings show that most corrosion defects fall within the low-risk category, with a significant number falling into the medium-to-high-risk range, highlighting the necessity for targeted maintenance. Considering the challenges of dataset imbalance, the stacking classifier achieved 94% accuracy, showing balanced performance across all risk categories. The stacking model outperformed the random forest and logistic regression models in terms of F1-scores, precision, and recall. This study demonstrates the application of stacking ensemble techniques in predicting corrosion risks and optimizing pipeline maintenance strategies. It provides vital information for improving pipeline safety and optimizing predictive maintenance practices by providing an in-depth assessment of various machine learning models, especially when real-time monitoring systems are integrated.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 2","pages":"Article 100244"},"PeriodicalIF":4.8,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144491310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A burst capacity model for pipelines containing pinhole-in-corrosion defects","authors":"Y. Shen,&nbsp;W. Zhou","doi":"10.1016/j.jpse.2024.100243","DOIUrl":"10.1016/j.jpse.2024.100243","url":null,"abstract":"<div><div>This study develops a practical burst capacity model for oil and gas pipelines containing pinhole-in-corrosion (PIC) defects based on results of extensive parametric three-dimensional finite element analyses (FEA) that are validated by full-scale burst tests of corroded pipe specimens reported in the literature. The PIC defect considered in this study contains a cylindrical-shaped pinhole located inside a cuboidal-shaped general corrosion. The proposed model takes the form of the well-known PCORRC model for the burst capacity of the general corrosion plus a correction term taking into account the impact of the pinhole, whereby the correction term is evaluated as a function of the depth and length of the general corrosion as well as the depth and relative position of the pinhole using the Gaussian process regression based on the results of parametric FEA. The accuracy of the proposed PIC model is demonstrated using 16 FEA cases and shown to be higher than that of the well-known RSTRENG model and a burst capacity model for complex-shaped corrosion defects reported in the recent literature.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 2","pages":"Article 100243"},"PeriodicalIF":4.8,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144656263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Inhibition and co-condensation behaviour of 2-mercaptoethanol in top-of-line CO2 corrosion environments","authors":"Mariana C. Folena ,&nbsp;Joshua Owen ,&nbsp;Iain W. Manfield ,&nbsp;Hanan Farhat ,&nbsp;J.A.C. Ponciano ,&nbsp;Richard Barker","doi":"10.1016/j.jpse.2024.100224","DOIUrl":"10.1016/j.jpse.2024.100224","url":null,"abstract":"<div><div>Top of line corrosion (TLC) is a significant problem in oil and gas transportation pipelines, leading to both economic and production loss. Conventional organic corrosion inhibitors typically fail to provide effective protection for this particular type of corrosion. As such, the chemical inhibition of TLC relies on volatile compounds which can partition from the aqueous to the condensate formed at the top of the pipeline. Studies have shown that thiol compounds, through their high affinity for metallic surfaces, are providing effective inhibition in such environments, yet their inhibition mechanism and co-condensation characteristics are yet to be fully determined. This work studies the efficiency, adsorption mechanism and condensation behaviour of 2-mercaptoethanol (2-ME) as a volatile corrosion inhibitor in CO₂-containing TLC environments through a novel direct assessment of condensate chemistry and real-time TLC measurements. Experimental analysis of condensate partitioning is performed through the implementation of a biochemical technique which targets sulphydryl groups, coupled with a miniature electrode configuration for real time, in-situ electrochemical TLC measurements. The proposed assay results in a rapid, cost-effective screening technique that can monitor thiol-based chemistries that condense in conjunction with the water phase. The new developed biochemical methodology identified that from 20 ppm of 2-ME added to the bulk solution, only around 12 ppm was present within the condensate. Additionally, 2-ME addition into the system resulted in a corrosion inhibitor efficiency of 93.8% where the chemical act as a mixed-type corrosion inhibitor. The corrosion and condensation experiments are complemented with surface characterization via XPS and STEM-EDX techniques. The surface characterization analysis showed a compact inner layer containing sulphur which is related to adsorption of the thiol.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 1","pages":"Article 100224"},"PeriodicalIF":4.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143510316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Extended design philosophy of hydrogen transport pipelines","authors":"Dr. M. Liu","doi":"10.1016/j.jpse.2024.100228","DOIUrl":"10.1016/j.jpse.2024.100228","url":null,"abstract":"<div><div>This paper examines some specific design issues associated with hydrogen transportation via pipelines based on recent field development study of high-throughput hydrogen pipelines. A mechanical design review is undertaken, and the current design practices and challenge are examined first. An array of key parameters considered to have significant bearing on the hydrogen pipeline general mechanical design are considered and assessed, including out of roundness (OOR) imperfections, combined stress and design factors, thermal gradients, joint mismatch and fabrication, fatigue assessment, installation, specifications and material consideration. Some of these are typically ignored for the conventional pipeline design, but open to rationalization for hydrogen charged pipeline systems subject to material embrittlement risk arising from hydrogen absorption. Complementary to the current design standards and as a spur to discussion on the hydrogen pipeline design analysis, special considerations and recommendations are proposed on materials specification, additional design criteria and construction assessments, and their rationale to mitigate material embrittlement with a view to improving hydrogen pipeline design, reliability and integrity management potentially leading to some tangible cost saving.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 1","pages":"Article 100228"},"PeriodicalIF":4.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143682692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FELA Evaluation of uplift, lateral and inclined capacity of buried pipeline in layered clays","authors":"Parin Dalal,&nbsp;Jitesh T. Chavda,&nbsp;Chandresh H. Solanki","doi":"10.1016/j.jpse.2024.100226","DOIUrl":"10.1016/j.jpse.2024.100226","url":null,"abstract":"<div><div>The offshore buried pipelines are prone to upheaval and lateral buckling due to the high temperature and pressure of the materials being transported. The pipeline placed on marine soil or buried in layered soil can be subjected to drained and undrained loading conditions. An attempt has been made in the present study to evaluate the uplift and lateral capacity factor (<em>N</em>_u) of buried pipeline in layered clays using finite element limit analysis (FELA) considering the layered clay condition as soft clay over hard clay and hard clay over soft clay. The lateral and uplift capacity factors are evaluated corresponding to varying normalized <em>C</em>/<em>D</em> ratio, where <em>C</em> is the crown height and <em>D</em> is the diameter of the pipeline, <em>h</em>₁/<em>D</em> ratio, where <em>h</em>₁ is the height of upper layer of clay, and <em>S</em>_u1/<em>S</em>_u2, where <em>S</em>_u1 is undrained shear strength of upper clay layer and <em>S</em>_u2 is the undrained shear strength of bottom clay layer. The inclined capacity of buried pipeline in layered clays is also evaluated numerically and by interpolation using the vertical and lateral capacity factors. Then the assessment of the interpolated inclined capacity is also performed. The FELA results are compared with those solutions available in the literature and the present study outcomes are presented as design charts and tables. This study will be useful to the offshore foundation engineering practitioners.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 1","pages":"Article 100226"},"PeriodicalIF":4.8,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143644450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research progress on dynamic crack propagation and crack arrest models of supercritical and dense-phase CO2 pipelines","authors":"Yifei Wang ,&nbsp;Qihui Hu ,&nbsp;Buze Yin ,&nbsp;Xuefeng Zhao ,&nbsp;Lan Meng ,&nbsp;Jianlu Zhu ,&nbsp;Xin Ouyang ,&nbsp;Yuxing Li","doi":"10.1016/j.jpse.2025.100255","DOIUrl":"10.1016/j.jpse.2025.100255","url":null,"abstract":"<div><div>In the past decade, research on the propagation and arrest of CO₂ pipeline fractures has achieved some results. This paper comprehensively reviews and evaluates the full-scale burst test, arrest control theory model, and numerical simulation, and systematically analyzes the remaining problems. Among them, the brittle-ductile transition process during the fracture process of the pipeline is still unclear, and the relationship between the crack tip pressure and the saturation pressure is still debatable. Both of these points need to be further studied through experiments. Furthermore, the scarcity of existing experimental data has limited the applicability of current arrest models. The prediction of low toughness or saturation pressure is overly conservative, and the experimental-based arrest theory model requires further refinement and optimization. In terms of numerical models, finite element simulation’s accuracy in predicting the fracture process requires improvement, while the fluid-solid coupling model improves calculation accuracy. However, due to the limitations of existing commercial software for calculating the FSI problem, there is a need to develop a commercial FSI strategy for CO₂ pipeline crack propagation. In addition, the majority of existing models describe fluid behavior using homogeneous flow models, and there have been few studies on decompression models that account for delayed phase changes, limiting the model’s prediction accuracy. The three-dimensional pipe-fluid-soil coupling is the most complete model for calculating fracture processes, and it should be the primary focus and challenge of numerical simulation.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 3","pages":"Article 100255"},"PeriodicalIF":4.8,"publicationDate":"2025-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144680798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lightweight visible damage detection algorithm for embedded systems applied to pipeline automation equipment","authors":"Jiale Xiao,&nbsp;Lei Xu,&nbsp;Changyun Li,&nbsp;Ling Tang,&nbsp;Guogang Gao","doi":"10.1016/j.jpse.2025.100254","DOIUrl":"10.1016/j.jpse.2025.100254","url":null,"abstract":"<div><div>This research is designed for low-power, cost-effective and high-performance pipeline defect inspection in embedded systems. The backbone of the algorithm, CSPHet, employs efficient combinatorial convolution and heterogeneous kernel convolution, incorporates a lightweight convolutional structure SL in the neck of the network, enhances the nonlinear representation and feature processing capability through channel shuffling, utilizes the lightweight self-attention mechanism Detect_SA for prediction, and employs a multilayered GhostConv to improve the computational efficiency. In addition, the performance of the model is optimized by knowledge refinement. When tested on a customized pipeline defect dataset, CGYOLO used 25 % less memory, ran 39.5 % fewer gigaprocessors per second, had 28.5 % fewer parameters, and improved average accuracy by 4 % to 94.3 % compared to the smallest known state-of-the-art model. In addition, the algorithm demonstrates excellent lightweight performance and utility on the Kaggle concrete crack dataset and the Norbase dataset. Finally, the model has been successfully deployed in a real-time embedded system consisting of a Raspberry Pi 4B and low-cost embedded image sensors, as well as in a simulated pipeline interior environment, meeting the real-time requirements for inspecting visible pipeline damage.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 2","pages":"Article 100254"},"PeriodicalIF":4.8,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144115147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A new model for predicting characteristics of the near-field leakage in high-pressure CO2 pipelines","authors":"Yan Shang ,&nbsp;Xiaoling Chen ,&nbsp;Peilu Wu ,&nbsp;Zhanjie Li ,&nbsp;Ming Yang ,&nbsp;Xiaokai Xing ,&nbsp;Jian Jiao ,&nbsp;Xinze Li","doi":"10.1016/j.jpse.2024.100249","DOIUrl":"10.1016/j.jpse.2024.100249","url":null,"abstract":"<div><div>The safe transportation of carbon dioxide (CO₂) is crucial to the successful implementation of Carbon Capture, Utilization, and Storage (CCUS) projects. Accidental leaks in pipelines can pose significant risks to this process. Understanding the characteristics of near-field leakage is essential for accurately predicting CO₂ diffusion patterns and conducting effective risk assessments. This paper presents a compressible multiphase flow model based on non-equilibrium phase transitions. Utilizing this model, the characteristics of under-expanded jets resulting from high-pressure CO₂ pipeline leakage are investigated in this study. The shock wave structures of the Mach disk and jet boundary layer are examined. Furthermore, the effects of various initial pressures, initial temperatures and leakage sizes on the pressure, fluid velocity, temperature, and Mach number in the near field are analyzed. Lastly, the paper proposes predictive formulas for the position, diameter, and boundary layer thickness of the Mach disk based on simulation results. A comparison of the predicted values with experimental data shows that these formulas can accurately predict the characteristic dimensions of the normal shock wave, with a maximum error rate of 5.5%.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 2","pages":"Article 100249"},"PeriodicalIF":4.8,"publicationDate":"2024-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144147051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Supercritical/dense-phase CO2 pipeline leakage diffusion experiment and hazard distance prediction method","authors":"Yifei Wang ,&nbsp;Qihui Hu ,&nbsp;Xuefeng Zhao ,&nbsp;Buze Yin ,&nbsp;Lan Meng ,&nbsp;Xin Ouyang ,&nbsp;Siqi Cong ,&nbsp;Chaofei Nie ,&nbsp;Yaqi Guo ,&nbsp;Yuxing Li","doi":"10.1016/j.jpse.2024.100248","DOIUrl":"10.1016/j.jpse.2024.100248","url":null,"abstract":"<div><div>The study of the diffusion characteristics of CO₂ leakage in pipelines and the determination of the hazardous distance resulting from such leakage under various working conditions are crucial for identifying the high-consequence zone of industrial CO₂ pipelines and analyzing the consequences of accidents. Currently, there is yet to be a unified conclusion on the delineation and calculation method of hazard distance. This paper has formulated hazard distance calculation and forecasting methods by combining test verification and model calculation. First, a full-scale pipe burst leakage experiment was carried out based on a self-designed and built CO₂ pipe leakage device, the CO₂ concentration data was measured, and the CO₂ diffusion characteristics were analyzed. Then, the experimental measurement values were compared with the calculation results of the CO₂ concentration calculation model to verify the reliability of the model. Furthermore, a hazard distance calculation model was introduced, which utilized bilinear interpolation and took into account time-weighted allowable concentrations. This model accurately determined the hazard distances caused by leaks at 11 specific locations along the pipeline. It was found that the location of the leak point can lead to significant differences in the classification of the hazard distance, so the development of a hazard distance prediction model is necessary. Eventually, a hazard distance prediction model was established based on the PSO-BP neural network. Six variables were selected as input parameters: CO₂ temperature, pressure, density, position, and distance from the distance valve chamber. The hazard distance caused by a leak at 125 locations along the pipeline was predicted. The results showed that an increase in the transport distance or a location away from the valve chamber would lead to an increase in the hazard distance. At the same time, a CO₂ leak in the supercritical state will not generate a hazard distance.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 2","pages":"Article 100248"},"PeriodicalIF":4.8,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143508929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reliability analysis of slow crack growth in HDPE pipes: Impact of buried pipeline design and soil characteristics","authors":"Theylor Andres Amaya Villabon,&nbsp;Juan Sebastián Valderrama,&nbsp;Paula Juliana Garzon,&nbsp;Carlos Eduardo Rodríguez,&nbsp;Guillermo Eduardo Ávila Álvarez","doi":"10.1016/j.jpse.2024.100247","DOIUrl":"10.1016/j.jpse.2024.100247","url":null,"abstract":"<div><div>This study delves into one of the most common fracture mechanisms in polyethylene pipes and the primary cause of their long-term failure, the slow crack growth (SCG) phenomenon. This failure mode in high-density polyethylene (HDPE) pipelines can potentially lead to brittle-like fractures without any localized yielding or plastic deformation. Leveraging the ISO 9080:2012 standard for estimating pipe service life under SCG, we employ a reliability-based assessment incorporating Monte Carlo simulations to explore the impact of geometric burial design and soil characteristics on pipeline integrity.</div><div>Variables including pipe diameter, depth of cover, bedding angle, trench width, soil type, and compaction level were analyzed to determine their impact on the progression toward medium and high SCG-mediated probability of failure levels. In addition to a thorough examination of these variables, a machine learning analysis was employed as a supplementary tool to contrast and quantify their significance in influencing the time of entry into medium and high probability of failure states. This layered approach, combining detailed variable analysis with machine learning insights, underscores the complex interplay of design and environmental factors in mitigating SCG probability of failure.</div><div>Our research underscores that bedding angles under 90° substantially increase the likelihood of SCG-induced failures in HDPE pipelines. Although additional factors studied also affect failure probabilities, their impact is less critical in comparison to that of the bedding angle. By optimizing these lesser factors, minimal failure probabilities can be sustained across the standard 50-year service life of HDPE pipelines, thus bolstering their durability and reliability across diverse operating environments.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 2","pages":"Article 100247"},"PeriodicalIF":4.8,"publicationDate":"2024-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}