Journal of Pipeline Science and Engineering最新文献

{"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":"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":"Crack assessment in spiral-welded pipelines repaired by composite patch: A SMART and failure assessment diagram approach","authors":"Ardeshir Savari","doi":"10.1016/j.jpse.2024.100222","DOIUrl":"10.1016/j.jpse.2024.100222","url":null,"abstract":"<div><div>This study presents a methodology for assessing cracks in spiral-welded pipelines (SWPs) repaired with composite sleeves, utilizing the Separating Morphing and Adaptive Remeshing Technique (SMART) for crack growth modeling and a failure assessment diagram (FAD) approach. Stress analysis identifies critical regions for crack initiation, and Ansys™ Mechanical software is used for automated remeshing to study crack growth. Various scenarios are considered, including stationary cracks and those that grow under static or cyclic loading. A parametric analysis examines the impact of factors such as crack dimensions, internal pressure, sleeve mechanical properties, and repair thickness on both non-repaired and repaired models. Safety factors are derived using the FAD curve, accounting for both conservative and non-conservative fracture criteria. The study finds that composite repairs are more effective for deep, long cracks than for shallow, short ones. Although the evaluation of stress intensity factors (SIFs) and stresses might suggest safety, FAD assessments indicate potential failure risks, necessitating urgent repairs. The extracted safety factors demonstrate the effectiveness of composite patches in enhancing the reliability of SWPs, regardless of employing a conservative or non-conservative approach. This methodology provides valuable insights into the assessment and repair of SWPs with composite sleeves.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 1","pages":"Article 100222"},"PeriodicalIF":4.8,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143167463","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":"Quantification of methane emissions from typical natural gas stations using on-site measurement technology","authors":"Wenlong Jia ,&nbsp;Pingyang Jia ,&nbsp;Li Gu ,&nbsp;Lei Ren ,&nbsp;Yang Zhang ,&nbsp;Honghuan Chen ,&nbsp;Xia Wu ,&nbsp;Wei Feng ,&nbsp;Jiujiang Cai","doi":"10.1016/j.jpse.2024.100229","DOIUrl":"10.1016/j.jpse.2024.100229","url":null,"abstract":"<div><div>Natural gas transmission systems are the main source of methane emissions in the oil and gas industry. Methane, as the second most potent greenhouse gas, makes a strong contribution to climate change. The hydrogen flame ionization detector and Hi-Flow sampler (a large flow methane detector) technologies were used to measure fugitive methane emissions in five distinct categories of stations in natural gas transmission pipelines in China. The methane emission rate of different components was quantified, enabling a comparison of methane emission characteristics across different stations. The resulting data was used to deduce a correlation equation between the methane concentration and the emission rate of various components. The leakage probability of components in the surveyed stations ranged from 2.54% to 7.77%. Notably, the leakage probability of liquefied natural gas (LNG) terminals was considerably higher than that of the other stations. A one-way analysis of variance revealed significant differences in methane emission rates between components with different processes. The bootstrap method was used to calculate the mean methane emission rates and 95% confidence intervals for each component. The mean methane emission rates and 95% confidence intervals for valves, flanges, connectors and open-ended lines were 26.43 (15.86, 38.56), 35.84 (23.36, 50.19), 4.90 (3.43, 6.73), and 30.76 (18.62, 44.19) kg/a, respectively. In conclusion, the total fugitive methane emissions detected at the LNG terminal and underground gas storage were 5,202.1 and 1,891 kg/a, respectively. There were no significant differences in the emissions of the compressor, distribution, and meter stations on the natural gas transmission trunk pipe, with values between 1,000 and 1,200 kg/a. The bootstrap method, in conjunction with the Monte Carlo method, was used to estimate the fugitive methane emissions in the compressor area of another natural gas compressor station. The estimated result was 1,853.58 kg/a, while the measured value was 1,418.55 kg/a, therefore exhibiting a slight discrepancy.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 2","pages":"Article 100229"},"PeriodicalIF":4.8,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143487226","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":"Experimental study on the leakage identification for the buried gas pipeline via vibration signals","authors":"Xiugang Chen ,&nbsp;Cuiwei Liu ,&nbsp;Kang Xiao ,&nbsp;Wenjie Liu ,&nbsp;Tao Gu ,&nbsp;Yuxing Li","doi":"10.1016/j.jpse.2024.100230","DOIUrl":"10.1016/j.jpse.2024.100230","url":null,"abstract":"<div><div>It is difficult to detect and locate small leakages, especially for buried pipelines. Therefore, a non-intrusive leakage identification method for buried gas pipelines is proposed in this study. Accelerometers were arranged in the soil at a certain distance from the leakage orifice to capture the acceleration signals caused by leakage. A 7-layer wavelet transform was applied to extract the leakage characteristic frequency band. Meanwhile, the attenuation characteristics of vibration signals were analyzed and the signal amplitude attenuation patterns in the axial, radial, and circumferential directions were analyzed. The results show that the leakage recognition rate is nearly 100% by selecting a peak signal-to-noise ratio (P-SNR) threshold of 7.26. Thus, the non-intrusive method based on accelerometers can be successfully applied for the leakage monitoring of buried gas pipelines.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 2","pages":"Article 100230"},"PeriodicalIF":4.8,"publicationDate":"2024-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479037","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":"A novel approach integrating the method of characteristics with large time-step scheme (MOC-LTS) for efficient transient flow simulation in liquid pipelines","authors":"Shengyuan Wei,&nbsp;Shangfei Song,&nbsp;Bohui Shi,&nbsp;Jing Gong","doi":"10.1016/j.jpse.2024.100227","DOIUrl":"10.1016/j.jpse.2024.100227","url":null,"abstract":"<div><div>Water hammer incidents pose a significant risk to the safety and stability of pipeline operations. Therefore, rapid and precise transient flow simulation is essential for efficiently developing scientific water hammer control strategies. Nevertheless, the prevailing transient flow simulation methods for liquid pipelines predominantly employ explicit schemes to solve transient flow control equations, necessitating adherence to the stability criterion of Courant-Friedrichs-Lewy (CFL) ≤ 1. This results in limited time step size, which in turn constrains computational efficiency, particularly when simulating hydraulic behavior in large-scale pipeline networks. In this paper, a novel approach integrating the method of characteristics (MOC) with a large time-step scheme (LTS) is proposed to enable rapid and accurate simulation of transient flow in liquid pipelines. The proposed approach discretizes the computational domain into contiguous control volumes, ategorizing them as either boundary or internal control volumes depending on whether they are affected by boundary conditions within a large time step. For internal control volumes, an LTS scheme based on the first-order Godunov format is employed to improve computational efficiency. For boundary control volumes, MOC is applied iteratively to accurately capture boundary dynamics until the simulated time matches that of the internal control volumes. Quantitative analysis is conducted to verify the performance of the proposed approach. The results confirm that the proposed approach outperforms the MOC in computational efficiency while maintaining minimal accuracy loss.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 1","pages":"Article 100227"},"PeriodicalIF":4.8,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143478540","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":"Mechanical properties of the liner for strengthening steel pipe under the action of normal fault","authors":"Kejie Zhai ,&nbsp;Deqiang Hu ,&nbsp;Kaidong Wang ,&nbsp;Hongyuan Fang ,&nbsp;Niannian Wang ,&nbsp;Bin Li ,&nbsp;Xueming Du ,&nbsp;Yuquan Hu ,&nbsp;Xiangqian Fan","doi":"10.1016/j.jpse.2024.100225","DOIUrl":"10.1016/j.jpse.2024.100225","url":null,"abstract":"<div><div>Using liner pipe to rehabilitate pressure pipe can effectively improve the mechanical performance of the pipe. To explore the mechanical properties of the liner for repairing pressure pipes under the action of a normal fault, a refined three-dimensional (3D) finite element (FE) model is established and assessed by experiments and FE results. Then, the stress distribution of the liner is analyzed, and the effects of fault slip distance, slip angle, pipe diameter, host thickness, internal pressure, liner elastic modulus, and friction factor on the liner stress and vertical displacement are studied. Finally, the bearing capacity of the pipeline against normal faults is analyzed. The study shows that the distribution morphology of the crown and shoulder is similar and opposite to the distribution morphology of the invert and haunch. The crown and invert stress of the pipe is the highest, while the stress on the springline is the lowest. When the host pipe thicknesses are 3.0 mm, 3.5 mm, 4.0 mm, and 5.0 mm, the slip distance reaches 309 mm, 342 mm, 370 mm, and 449 mm, respectively, and the liner will damage at the crown.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 1","pages":"Article 100225"},"PeriodicalIF":4.8,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143167464","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":"Data-driven multi-fault detection in pipelines utilizing frequency response function and artificial neural networks","authors":"Hussein A. M. Hussein ,&nbsp;Sharafiz B. Abdul Rahim ,&nbsp;Faizal B. Mustapha ,&nbsp;Prajindra S. Krishnan ,&nbsp;Nawal Aswan B. Abdul Jalil","doi":"10.1016/j.jpse.2024.100223","DOIUrl":"10.1016/j.jpse.2024.100223","url":null,"abstract":"<div><div>This research presents a data-driven structural health monitoring (SHM) approach for pipeline systems that leverages frequency response function (FRF) signals and artificial neural network (ANN) algorithms to accurately identify and classify diverse pipeline fault conditions. The study focuses on three specific faults: bolt looseness, scale deposits, and crack occurrence at pipeline supports, which were replicated on a pipeline segment located at the Sound and Vibration Research Group (SVRG) at University Putra Malaysia (UPM). The FRF signals were captured using accelerometers to monitor the structural health of the pipeline. The data acquisition stage involved collecting FRF signals from the accelerometers to capture vibrations and responses related to the identified faults using a Siemens LMS SCADAS data acquisition unit. The data underwent preprocessing, including the application of principal component analysis (PCA) for feature selection. The subsequent data processing stage involved the application of an ANN algorithm for pattern recognition to analyze and classify the acquired data, identifying patterns associated with the replicated fault conditions. The proposed methodology demonstrated exceptional performance, with the ANN model achieving consistently high overall accuracy (above 99.7%) and remarkably low mean squared error (in the range of 0.0088 × 10⁻³ to 0.3062 × 10⁻³) across multiple iterations and sensor datasets. The detailed class-specific metrics, including accuracy, precision, sensitivity, and F1-score, further substantiated the model’s effectiveness in identifying the individual fault types with near-perfect or perfect results for the majority of the fault scenarios. The location-invariant performance of the ANN model across different sensor placements demonstrates the robustness of the proposed data-driven SHM methodology. This research highlights the transformative potential of integrating state-of-the-art data-driven techniques to revolutionize the monitoring and assessment of critical pipeline infrastructure, ultimately enhancing the safety, reliability, and longevity of these vital systems.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 1","pages":"Article 100223"},"PeriodicalIF":4.8,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143167467","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":"Experimental study of the full-scale burst failure behavior of carbon dioxide steel pipeline","authors":"Duihong Zhang ,&nbsp;Ruoxi Wang ,&nbsp;Xin Ouyang ,&nbsp;Yaru Fu ,&nbsp;Hao Wang ,&nbsp;Feng Yan ,&nbsp;Xiaoben Liu","doi":"10.1016/j.jpse.2024.100221","DOIUrl":"10.1016/j.jpse.2024.100221","url":null,"abstract":"<div><div>Carbon Capture, Utilization and Storage (CCUS) is an important strategic reserve technology to reduce CO₂ emissions. Accelerating the application and development of CCUS technology is a realistic need and an important path for the energy industry to achieve the goal of carbon peak and carbon neutrality. It is the most economical method to transport CO₂ from carbon source to carbon sink in supercritical state through pipeline. The key issue of supercritical/dense phase CO₂ pipeline design is whether the pipeline steel has an adequate toughness to arrest running ductile fracture. For the study of toughness requirements of pipeline, full-scale burst test is the most direct and effective method at present. In order to research the toughness requirements of the supercritical CO₂ pipeline, the first full-scale burst test of CO₂ pipeline in China was carried out. The X65 steel pipeline with an outer diameter of 323.9 mm and a wall thickness of 7.2–7.6 mm was used as the test pipe. The test gas was 95% CO₂ + 4% N₂ + 1% H₂, the test pressure was 11.85 MPa, and the temperature was 12.6 °C. The test results show that the axial prefabricated crack of the crack initiation pipe was successfully detonated and the crack propagated along the axial direction. On the west side, the crack was arrested at the girth weld of the two pipelines, and on the east side the crack was arrested ductilely because the base metal of the pipeline had sufficient toughness. The test steel pipe showed typical ductile shear fracture characteristics. The data of crack propagation velocity, pressure and temperature were collected, and the test results were accurate. After the burst of the pipe, the high-pressure gas in the pipe was sprayed upward and out in the opposite direction of the wind direction, and then diffused along the wind direction to the external field under the action of the wind velocity. This test provides data support for China to master the development, pipeline design and construction technology of million-ton CO₂ pipeline. The test results will significantly improve the prediction accuracy of crack arrest toughness of CO₂ pipeline of China, and provide important technical support for the safe construction and operation of global CO₂ pipeline.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 1","pages":"Article 100221"},"PeriodicalIF":4.8,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143167462","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":"Natural gas consumption forecasting using a novel two-stage model based on improved sparrow search algorithm","authors":"Weibiao Qiao ,&nbsp;Qianli Ma ,&nbsp;Yulou Yang ,&nbsp;Haihong Xi ,&nbsp;Nan Huang ,&nbsp;Xinjun Yang ,&nbsp;Liang Zhang","doi":"10.1016/j.jpse.2024.100220","DOIUrl":"10.1016/j.jpse.2024.100220","url":null,"abstract":"<div><div>The foundation of natural gas intelligent scheduling is the accurate prediction of natural gas consumption (NGC). However, its volatility, brings difficulties and challenges in accurately predicting NGC. To address this problem, an improved model is developed combining improved sparrow search algorithm (ISSA), long short-term memory (LSTM), and wavelet transform (WT). First, the performance of ISSA is tested. Second, the NGC is divided into several high- and low-frequency components applying different layers of Coilfets’, Fejer-Korovkins’, Symletss’, Haars’, and Discretes’ orders. In addition, the LSTM is applied to forecast the decomposed components in view of the one- and multi-step, and its hyper-parameters are optimized by ISSA. At last, the final prediction results are reconstructed. The research results indicate that: 1) Comparing to other machine algorithms (e.g., fuzzy neural network), the convergence speed and stability of ISSA are stronger in view of standard deviation and mean; 2) The prediction performance of the developed model is better than that of other forecasting models; 3) The forecasting performance of the single-step forecasting is superior to that of the two-, three-, and four- step; 4) The computational load of the proposed prediction model is the highest compared to other models, and the prediction accuracy is still excellent on the extended time series.</div></div>","PeriodicalId":100824,"journal":{"name":"Journal of Pipeline Science and Engineering","volume":"5 1","pages":"Article 100220"},"PeriodicalIF":4.8,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143168567","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}