Review of Prediction of Stress Corrosion Cracking in Gas Pipelines Using Machine Learning

Machines, Год журнала: 2024, Номер 12(1), С. 42 - 42

Опубликована: Янв. 8, 2024

Pipeline integrity and safety depend on the detection prediction of stress corrosion cracking (SCC) other defects. In oil gas pipeline systems, a variety corrosion-monitoring techniques are used. The observed data exhibit characteristics nonlinearity, multidimensionality, noise. Hence, data-driven modeling have been widely utilized. To accomplish intelligent enhance control, machine learning (ML)-based approaches developed. Some published papers related to SCC discussed ML their applications, but none works has shown real ability detect or predict in energy pipelines, though fewer researchers tested models prove them under controlled environments laboratories, which is completely different from work field. Looking at current research status, authors believe that there need explore best technologies identify clear gaps; critical review is, therefore, required. objective this study assess status learning’s applications detection, gaps, indicate future directions scientific application point view. This will highlight limitations challenges employing for also discuss importance incorporating domain knowledge expert inputs accuracy reliability predictions. Finally, framework proposed demonstrate process condition assessments pipelines.

Язык: Английский

---

Insights into modern machine learning approaches for bearing fault classification: A systematic literature review

Results in Engineering, Год журнала: 2024, Номер 23, С. 102700 - 102700

Опубликована: Авг. 10, 2024

Rolling bearings are essential components in a wide range of equipment, such as aeroplanes, trains, and wind turbines. Bearing failure has the potential to result complete system failure, it accounts for approximately 45 %–50 % failures rotating machinery. Hence, is imperative establish thorough accurate predictive maintenance program that can efficiently foresee prevent mishaps or malfunctions. The literature employed variety techniques approaches, from conventional methods contemporary machine learning (ML) ML-integrated IoT-based solutions, categorise bearing faults. This article provides an overview most recent research models used classification summary highlights various significant challenges current models, issues with function, complexities neural network structure, unrealistic datasets, dynamic working conditions machines, noise dataset, limited data availability, imbalanced datasets. In order tackle problems, researchers have endeavored improve apply different methods, convolutional networks, deep belief LiNet, among others. Researchers primarily developed these approaches using datasets publicly accessible sources. study also identified gaps deficiencies, including imbalance, difficulties integration. nascent technologies field problem diagnosis acknowledged Internet Things-based ML vision-based techniques, which currently their initial phases advancement. Ultimately, puts forth several prospective suggestions recommendations.

Язык: Английский

---

Prediction of oil and gas pipeline failures through machine learning approaches: A systematic review

Energy Reports, Год журнала: 2023, Номер 10, С. 1313 - 1338

Опубликована: Авг. 16, 2023

Pipelines are vital for transporting oil and gas, but leaks can have serious consequences such as fires, injuries, pollution, property damage. Therefore, preserving pipeline integrity is crucial a safe sustainable energy supply. The rapid progress of machine learning (ML) technologies provides an advantageous opportunity to develop predictive models that effectively tackle these challenges. This review article mainly focuses on the novelty using deep techniques, specifically artificial neural networks (ANNs), support vector machines (SVMs) hybrid (HML) algorithms, predicting different failures in gas industry. In contrast existing noncomprehensive reviews defects, this explicitly addresses application ML parameters, data reliability purpose. surveys research specific area, offering coherent discussion identifying motivations challenges associated with types defects pipelines. also includes bibliometric analysis literature, highlighting common investigated failures, experimental tests. It in-depth details, summarized tables, failure types, commonly used resources, critical discussions. Based comprehensive aforementioned, it was found approaches, ANNs SVMs, accurately predict compared conventional methods. However, highly recommended combine multiple algorithms enhance accuracy prediction time further. Comparing based field, experimental, simulation various establish reliable cost-effective monitoring systems entire network. systematic expected aid understanding gaps provide options other researchers interested failures.

Язык: Английский

---

Reliability-based maintenance optimization of long-distance oil and gas transmission pipeline networks

Reliability Engineering & System Safety, Год журнала: 2024, Номер 249, С. 110236 - 110236

Опубликована: Май 22, 2024

Язык: Английский

---

Consequence assessment of gas pipeline failure caused by external pitting corrosion using an integrated Bayesian belief network and GIS model: Application with Alberta pipeline

Reliability Engineering & System Safety, Год журнала: 2023, Номер 240, С. 109573 - 109573

Опубликована: Авг. 17, 2023

Язык: Английский

---

Dynamic risk investigation of urban natural gas pipeline accidents using Stochastic Petri net approach

Process Safety and Environmental Protection, Год журнала: 2023, Номер 178, С. 933 - 946

Опубликована: Сен. 3, 2023

Язык: Английский

---

A stochastic model for RUL prediction of subsea pipeline subject to corrosion-fatigue degradation

Process Safety and Environmental Protection, Год журнала: 2023, Номер 178, С. 739 - 747

Опубликована: Авг. 18, 2023

Язык: Английский

---

Analysis of machine learning models and data sources to forecast burst pressure of petroleum corroded pipelines: A comprehensive review

Engineering Failure Analysis, Год журнала: 2023, Номер 155, С. 107747 - 107747

Опубликована: Ноя. 3, 2023

Язык: Английский

---

Research on risk assessment of coal and gas outburst during continuous excavation cycle of coal mine with dynamic probabilistic inference

Process Safety and Environmental Protection, Год журнала: 2024, Номер 190, С. 405 - 419

Опубликована: Авг. 15, 2024

Язык: Английский

---

Finite-Element Modeling of the Dynamic Behavior of a Crack-like Defect in an Internally Pressurized Thin-Walled Steel Cylinder

Applied Sciences, Год журнала: 2024, Номер 14(5), С. 1790 - 1790

Опубликована: Фев. 22, 2024

This article presents one part of a study on the dynamic deformation and fracture sections steel gas pipelines with an external crack-like defect under action internal pressure. work was performed basis finite-element simulations using cylindrical shell model executed by ANSYS-19.2 example section pipeline “Beineu–Bozoy–Shymkent” in Republic Kazakhstan. The propagation incipient along resulting its tip area were investigated. options loading working critical pressure both considered. It found that, within time 1.0 ms, formed crack expanded circumferential direction up to maximum value, which depended value A further growth cracks occurred longitudinal direction. At operating pressure, initial length increased factor 5.6, while equivalent stresses 1.53 3.5 ms. Within 3.75 stopped growing due decompression. Specifically, there stop Vice versa, at did not change qualitatively, process, it decreased results stress–strain state showed distance between walls reached 23 mm free edge. Conversely, periods 2.25 two three times, respectively. elongation 5.8 times time. Together, twice, after Moreover, studies that additional considerations edges led increment 3.6% length. this can be used for development measurements field structural reinforcement.

Язык: Английский

---