TECHNICAL PROGRAMME | Energy Infrastructure – Future Pathways
Pipelines, Storage and SPRs
Forum 8 | Digital Poster Plaza 2
28
April
12:30
14:30
UTC+3
Effective management of pipelines, storage facilities, and Strategic Petroleum Reserves (SPRs) is paramount for ensuring energy security and market stability. As global energy demand exhibits fluctuations, the infrastructure required for oil transportation and storage must adapt to guarantee a reliable supply. This forum will examine advancements in pipeline technology, storage solutions, and the strategic significance of SPRs in mitigating supply disruptions. Key areas of discussion encompass enhancing pipeline safety, optimising storage capacity, and the role of SPRs in emergency response and market stabilisation, thereby contributing to a resilient energy system within a dynamic global context. The geopolitical relevance of this topic is undeniable, as the diversification of pipeline routes emerges as a cornerstone of energy security for entire regions.
A gas hydrate is a crystal structure formed of cage-like hydrogen bonds between water molecules and trapping guest gas molecules in the hydrate cage at low-temperature and high-pressure thermodynamic conditions. By clogging pipes, valves, and other oil and gas refining and transmission equipment, natural gas hydrate causes pressure drop and flow reduction, ultimately leading to pipeline explosion and causing financial and life risks. So far, physical and chemical methods have been used to prevent this problem. Physical methods such as pipeline insulation, depressurization, dehumidification, and heating are not technically and economically desirable. Therefore, chemical methods are considered as an alternative approach. Chemical methods refer to inhibitors, which include Thermodynamic Hydrate Inhibitors (THIs) and Low-Dosage Hydrate Inhibitors (LDHIs). Low-Dosage Hydrate Inhibitors are divided into Kinetic Hydrate Inhibitors (KHIs) and Anti-Agglomerates (AAs). Thermodynamic Inhibitors are not economically and environmentally acceptable, due to the required high-weight percentages to be effective. Anti-Agglomerates are unacceptable due to their reaction with other additives, such as corrosion inhibitors, and their effectiveness after hydrate formation. However, Kinetic Inhibitors are a suitable option due to their low dosage and delaying hydrate formation reaction. In this study, the Iron Oxide (Fe3O4) nanoparticles were functionalized with polyvinyl pyrrolidone (PVP) polymer (Fe3O4@PVP) as a Kinetic Inhibitor using the Co-precipitation method and characterized by PXRD, FESEM/EDX, and TGA analyses. Then, a PVT test in a high-pressure cell was used to investigate Fe3O4@PVP inhibitory effect. In this method, the time of hydrate formation is obtained by detecting the pressure stabilization point when temperature decreases at a constant volume. The same steps are repeated for PVP, and the Fe3O4 effect on this material's inhibition is determined by comparing the PVT graphs. The reusability of Fe3O4@PVP is determined by creating a magnetic field; the nanostructure is separated and dried at 100°C. Finally, the recycled nanostructure is added to the system, and its inhibition is measured by PVT testing and compared with previous graphs. Fe3O4@PVP with a large surface area is expected to reduce the weight percentage of the kinetic inhibitor required and increase the performance due to the increased contact surface of PVP with water molecules in the gas flow line. In addition, Fe3O4@PVP is easily separated with a strong magnet due to the magnetic nature of its core, which makes it possible to reuse as an inhibitor. This chemical inhibitor's recyclability and small quantities required make it an environmentally friendly and economical inhibitor.
Co-author/s:
Ali Safaei, Assistant Professor, University of Tehran.
Azadeh Ebrahimian Pirbazari, Associate Professor, College of Engineering, University of Tehran.
Dr. Behnam Shahsavani, Assistant Professor, Petroleum Engineering Department, School of Chemical and Petroleum Engineering, Shiraz University.
Co-author/s:
Ali Safaei, Assistant Professor, University of Tehran.
Azadeh Ebrahimian Pirbazari, Associate Professor, College of Engineering, University of Tehran.
Dr. Behnam Shahsavani, Assistant Professor, Petroleum Engineering Department, School of Chemical and Petroleum Engineering, Shiraz University.
In our work on pipeline safety, we’ve seen how girth weld defects—micro-cracks or incomplete fusion—quietly threaten strategic petroleum reserve (SPR) pipelines, particularly in remote regions like Sub-Saharan Africa. These flaws risk leaks, environmental harm, and energy disruptions, yet traditional nondestructive testing (NDT) methods, like magnetic flux leakage, often falter due to logistical delays and limited sensitivity. In our view, a smarter approach is overdue. We propose a predictive AI-IoT framework to detect these defects early, aligning with TÜV standards (DIN EN ISO 5817, TÜV H2.23) to safeguard SPR pipelines and support net-zero ambitions.
A PRISMA-guided review of studies from 2015 to 2025 across Scopus, IEEE Xplore, and ResearchGate informed our approach. From 320 studies, we selected 50 focusing on AI-IoT integration, field-validated setups, and weld defects under 1.5 mm. Our framework integrates IoT sensors (temperature, pressure, acoustic) for real-time monitoring, AI-driven defect classification using YOLOv8 with convolutional block attention modules, and a TÜV-compliant reporting system. Python simulations, leveraging SymPy for Bayesian risk modeling and PyTorch for neural network training, used API and PHMSA datasets to replicate corrosion and seismic challenges in African SPR pipelines. Cybersecurity is addressed through AES-256 encryption and edge computing for secure, low-latency data processing.
Results demonstrate 98.5% detection accuracy, surpassing magnetic flux leakage (89.5%), with 70% faster detection, 60% fewer false alarms, and 40% reduced maintenance costs. Synthesized field trials confirm enhanced resilience in Sub-Saharan pipelines, though data gaps in ultra-remote areas suggest broader validation is needed. This framework paves a transformative path for predictive, TÜV-compliant pipeline safety, advancing sustainable energy delivery in challenging regions. Expanded field tests could solidify its global impact.
Keywords: AI-IoT fusion, girth weld flaws, predictive NDT, TÜV benchmarks, SPR resilience, net-zero pathways, Sub-Saharan pipelines, pipeline safety.
A PRISMA-guided review of studies from 2015 to 2025 across Scopus, IEEE Xplore, and ResearchGate informed our approach. From 320 studies, we selected 50 focusing on AI-IoT integration, field-validated setups, and weld defects under 1.5 mm. Our framework integrates IoT sensors (temperature, pressure, acoustic) for real-time monitoring, AI-driven defect classification using YOLOv8 with convolutional block attention modules, and a TÜV-compliant reporting system. Python simulations, leveraging SymPy for Bayesian risk modeling and PyTorch for neural network training, used API and PHMSA datasets to replicate corrosion and seismic challenges in African SPR pipelines. Cybersecurity is addressed through AES-256 encryption and edge computing for secure, low-latency data processing.
Results demonstrate 98.5% detection accuracy, surpassing magnetic flux leakage (89.5%), with 70% faster detection, 60% fewer false alarms, and 40% reduced maintenance costs. Synthesized field trials confirm enhanced resilience in Sub-Saharan pipelines, though data gaps in ultra-remote areas suggest broader validation is needed. This framework paves a transformative path for predictive, TÜV-compliant pipeline safety, advancing sustainable energy delivery in challenging regions. Expanded field tests could solidify its global impact.
Keywords: AI-IoT fusion, girth weld flaws, predictive NDT, TÜV benchmarks, SPR resilience, net-zero pathways, Sub-Saharan pipelines, pipeline safety.
The escalating demand for reliable energy supply necessitates robust and efficient pipeline infrastructure. Current pipeline integrity management (PIM) methods, while effective, often face limitations in detecting subtle defects, particularly in challenging environments or at early stages of corrosion. This abstract presents the transformative potential of quantum magnetometers (QMs) as a next-generation solution for enhanced pipeline integrity assessment.
Traditional magnetic flux leakage (MFL) and ultrasonic testing (UT) methods can be challenged by sensitivity thresholds, operational speeds, and environmental factors. Quantum magnetometers, leveraging the ultra-high sensitivity of atomic spin precession, offer unparalleled precision in detecting minute magnetic field anomalies caused by pipe corrosion, stress, and defects. This novel approach allows for the identification of smaller, nascent integrity issues that might otherwise go unnoticed by conventional techniques.
Deployment of advanced QM systems may involve in-line or external survey platforms (e.g., drone-mounted), to generate high-resolution, precise magnetic field maps of pipeline segments. Through sophisticated data processing and inversion algorithms, these magnetic anomalies are translated into detailed 3D representations of pipeline health, accurately pinpointing the location and characterizing the extent of structural anomalies.
The implementation of quantum magnetometry promises significant advantages for the oil and gas industry, including: greatly improved defect detection rates, enhanced proactive maintenance capabilities, reduced false positive indications, increased operational efficiency through faster survey speeds, and ultimately, a significant reduction in environmental risks and costly failures. This technology represents a crucial step towards achieving a new standard of predictive and reliable pipeline integrity, contributing directly to global energy security and sustainability.
Traditional magnetic flux leakage (MFL) and ultrasonic testing (UT) methods can be challenged by sensitivity thresholds, operational speeds, and environmental factors. Quantum magnetometers, leveraging the ultra-high sensitivity of atomic spin precession, offer unparalleled precision in detecting minute magnetic field anomalies caused by pipe corrosion, stress, and defects. This novel approach allows for the identification of smaller, nascent integrity issues that might otherwise go unnoticed by conventional techniques.
Deployment of advanced QM systems may involve in-line or external survey platforms (e.g., drone-mounted), to generate high-resolution, precise magnetic field maps of pipeline segments. Through sophisticated data processing and inversion algorithms, these magnetic anomalies are translated into detailed 3D representations of pipeline health, accurately pinpointing the location and characterizing the extent of structural anomalies.
The implementation of quantum magnetometry promises significant advantages for the oil and gas industry, including: greatly improved defect detection rates, enhanced proactive maintenance capabilities, reduced false positive indications, increased operational efficiency through faster survey speeds, and ultimately, a significant reduction in environmental risks and costly failures. This technology represents a crucial step towards achieving a new standard of predictive and reliable pipeline integrity, contributing directly to global energy security and sustainability.
Underground gas storage (UGS), a critical facility for natural gas peak shaving and supply security, often suffers severe sand production and reservoir property deterioration during high-intensity cyclic injection–production operations, posing risks to both safety and economic efficiency. However, the mechanisms and dynamic evolution of reservoir properties under such cyclic conditions remain poorly understood. In this study, a custom-designed large-scale physical simulation system for weakly cemented sandstone cores was used to conduct systematic experiments under multiple operating conditions. The effects of key parameters—including injection/production flow rate and cycle number—on sand production behavior and permeability evolution were analyzed. Results show that during gas injection, reduced flow velocity drives fine particles deeper into the reservoir, causing deposition, blockage, and significant permeability reduction. Conversely, during production, increased near-wellbore flow velocity induces a partial unblocking effect, leading to partial permeability recovery. Overall permeability variation ranges from 5% to 25%, with diminishing amplitude as cycles progress. Complementary triaxial cyclic loading tests were performed to elucidate rock damage accumulation mechanisms under alternating loads. Damage evolution was quantitatively characterized in terms of Young’s modulus degradation and residual strain accumulation, considering loading stress level, and cycle count. Based on experimental findings and theoretical analysis, an integrated porosity–permeability prediction and rock strength damage model was developed, incorporating both deformation and particle migration processes. A case study on an actual UGS well validated the model, revealing that with increasing injection–production cycles, near-wellbore damage intensifies, the critical sand production pressure drop decreases significantly (by ~26.3% after 10 cycles and ~32.4% after 20 cycles), and the damage zone becomes highly heterogeneous, with azimuthal differences up to 30%. This research clarifies the dynamic response mechanisms of sand production and reservoir property evolution during multi-cycle injection–production in UGS. It establishes a comprehensive workflow from experimental simulation to predictive modeling, offering theoretical and technical guidance for safe operation and optimized sand control in gas storage facilities.
Structural Health Monitoring (SHM) is recognized as an effective tool for enhancing safety and ensuring the integrity of structures, thereby reducing maintenance and repair costs. Among various techniques, the electro-mechanical impedance (EMI) method, which employs piezoelectric materials, has emerged in recent decades as a powerful, non-destructive, real-time approach for early damage detection in critical equipment and structures.
This research focuses on monitoring the health of buried pipelines subjected to transverse loading, using the electro-mechanical impedance method. This technique relies on the interaction between the structure (the pipe) and the piezoelectric material, which acts as both a sensor and an actuator. To address this problem, both finite element modeling and experimental testing have been employed. In particular, transverse loading on fuel transfer pipes is primarily caused by ground subsidence phenomena.
In the adopted method, any defect that affects the structure results in a change in its natural frequency, which in turn alters the structure’s frequency response. This leads to variations in the impedance of the structure. In this study, transverse loading and its effects—including stress, plastic deformation, and work hardening—are considered as potential damages to the pipe. The pipes tested are made of carbon steel X60, similar to those used in gas and oil transmission pipelines.
Initially, based on the actual model and existing standards, a small-scale laboratory model was designed in COMSOL Multiphysics software. For this model, considering laboratory capabilities, three-point bending and four-point bending experimental setups were modeled, and the impedance method was applied under both healthy and loaded conditions. Subsequently, experiments were conducted on specimens similar to these models. Piezoelectric patches were attached to the pipes, and by applying voltage to them, electro-mechanical impedance monitoring was performed during loading.
Finally, the results obtained from implementing the impedance method in COMSOL were compared with experimental data to validate the approach.
The results indicate that as stress increases, the impedance output shifts slightly to the right, and the resonance peaks of the impedance significantly increase. Moreover, due to plastic deformation and work hardening, the impedance signals exhibit behavior opposite to that in the elastic range; that is, before plasticity and within the elastic region, increasing load and tension lead to an increase in impedance amplitude with slight rightward shifts. However, after surpassing the elastic limit and entering the plastic zone, the impedance amplitude decreases and shifts leftward. Similar behavior is observed due to work hardening, with notable differences in amplitude variation compared to the elastic state. The behavior in this case is highly dependent on the magnitude of the applied load, especially in the plastic region.
Co-author/s:
Iman Jalilvand, Postdoctoral Research Fellow, University of British Columbia.
This research focuses on monitoring the health of buried pipelines subjected to transverse loading, using the electro-mechanical impedance method. This technique relies on the interaction between the structure (the pipe) and the piezoelectric material, which acts as both a sensor and an actuator. To address this problem, both finite element modeling and experimental testing have been employed. In particular, transverse loading on fuel transfer pipes is primarily caused by ground subsidence phenomena.
In the adopted method, any defect that affects the structure results in a change in its natural frequency, which in turn alters the structure’s frequency response. This leads to variations in the impedance of the structure. In this study, transverse loading and its effects—including stress, plastic deformation, and work hardening—are considered as potential damages to the pipe. The pipes tested are made of carbon steel X60, similar to those used in gas and oil transmission pipelines.
Initially, based on the actual model and existing standards, a small-scale laboratory model was designed in COMSOL Multiphysics software. For this model, considering laboratory capabilities, three-point bending and four-point bending experimental setups were modeled, and the impedance method was applied under both healthy and loaded conditions. Subsequently, experiments were conducted on specimens similar to these models. Piezoelectric patches were attached to the pipes, and by applying voltage to them, electro-mechanical impedance monitoring was performed during loading.
Finally, the results obtained from implementing the impedance method in COMSOL were compared with experimental data to validate the approach.
The results indicate that as stress increases, the impedance output shifts slightly to the right, and the resonance peaks of the impedance significantly increase. Moreover, due to plastic deformation and work hardening, the impedance signals exhibit behavior opposite to that in the elastic range; that is, before plasticity and within the elastic region, increasing load and tension lead to an increase in impedance amplitude with slight rightward shifts. However, after surpassing the elastic limit and entering the plastic zone, the impedance amplitude decreases and shifts leftward. Similar behavior is observed due to work hardening, with notable differences in amplitude variation compared to the elastic state. The behavior in this case is highly dependent on the magnitude of the applied load, especially in the plastic region.
Co-author/s:
Iman Jalilvand, Postdoctoral Research Fellow, University of British Columbia.
The integration of drag-reducing polymers (DRPs) in oil-water pipelines has emerged as a promising strategy for optimizing flow efficiency and enhancing separation processes. This study consolidates findings from multiple investigations on the effects of DRPs on oil-water flow dynamics within horizontal pipelines, emphasizing their significant role in reducing drag, altering flow patterns, and improving emulsion stability.
In experiments conducted in a 0.0254 m diameter pipe, the injection of water-soluble polymer solutions, specifically at concentrations of 10–15 ppm, led to drag reductions of approximately 65%. This reduction was particularly pronounced at higher mixture velocities, resulting in a noticeable decrease in pressure gradient and a shift in flow patterns. Notably, the phase inversion in dispersed flow regimes was identified within a 0.33–0.35 water fraction range, which could be effectively managed with the introduction of as little as 5 ppm of DRP.
Further investigations into water holdup conducted in a 2.54 cm pipe revealed that DRP injection significantly influenced water holdup at various superficial water velocities. The presence of DRP consistently increased water holdup in oil-water mixtures at lower velocities, demonstrating their potential to enhance separation efficiency. The results underscore the capability of DRPs to modify the distribution of oil-water droplets, thereby optimizing flow characteristics.
Additionally, the impact of DRPs on surfactant-stabilized water-oil emulsions was explored. The application of both oil-soluble and water-soluble polymers was examined for their effect on emulsion stability and pressure drop across varying temperatures and concentrations. The findings indicated that the appropriate selection of DRP could markedly improve emulsion stability, particularly with higher molecular weight polymers. Conversely, elevated temperatures tended to diminish the stability benefits provided by DRPs.
The results highlight the intricate interplay between drag reduction, flow dynamics, and emulsion characteristics, paving the way for enhanced design and operation of oil-water pipeline systems. By employing targeted DRP formulations, the energy efficiency of pipeline transport can be significantly improved, contributing to more sustainable oil and gas operations. This research not only elucidates the mechanisms behind DRP efficacy but also sets the foundation for future innovations in pipeline technology aimed at optimizing drag reduction and flow management.
In experiments conducted in a 0.0254 m diameter pipe, the injection of water-soluble polymer solutions, specifically at concentrations of 10–15 ppm, led to drag reductions of approximately 65%. This reduction was particularly pronounced at higher mixture velocities, resulting in a noticeable decrease in pressure gradient and a shift in flow patterns. Notably, the phase inversion in dispersed flow regimes was identified within a 0.33–0.35 water fraction range, which could be effectively managed with the introduction of as little as 5 ppm of DRP.
Further investigations into water holdup conducted in a 2.54 cm pipe revealed that DRP injection significantly influenced water holdup at various superficial water velocities. The presence of DRP consistently increased water holdup in oil-water mixtures at lower velocities, demonstrating their potential to enhance separation efficiency. The results underscore the capability of DRPs to modify the distribution of oil-water droplets, thereby optimizing flow characteristics.
Additionally, the impact of DRPs on surfactant-stabilized water-oil emulsions was explored. The application of both oil-soluble and water-soluble polymers was examined for their effect on emulsion stability and pressure drop across varying temperatures and concentrations. The findings indicated that the appropriate selection of DRP could markedly improve emulsion stability, particularly with higher molecular weight polymers. Conversely, elevated temperatures tended to diminish the stability benefits provided by DRPs.
The results highlight the intricate interplay between drag reduction, flow dynamics, and emulsion characteristics, paving the way for enhanced design and operation of oil-water pipeline systems. By employing targeted DRP formulations, the energy efficiency of pipeline transport can be significantly improved, contributing to more sustainable oil and gas operations. This research not only elucidates the mechanisms behind DRP efficacy but also sets the foundation for future innovations in pipeline technology aimed at optimizing drag reduction and flow management.
Among various options, subsurface storage in salt caverns has emerged as a commercially viable and technically robust solution for large-scale hydrogen storage due to their low permeability, self-healing properties and high operational flexibility. However, the relatively small volumetric capacity of individual caverns compared to other subsurface porous media limits their overall storage efficiency and economic viability.
Traditionally, hydrogen is stored in salt caverns by injecting compressed gas into the void space. Here we introduce a novel approach to enhance hydrogen storage capacity by filling caverns with microporous sorbent materials prior to gas injection. A range of microporous sorbents—including activated carbons and metal-organic frameworks—were evaluated under representative pressure-temperature conditions. Among them, activated carbon may be the most scalable and cost-effective option for field deployment. The use of commercially available sorbents with favorable cost-performance ratios makes this approach applicable to both existing caverns and new constructions.
Our experimental results show that microporous materials can significantly increase volumetric hydrogen storage, especially under shallow cavern conditions where gas compression is less effective. When filled with microporous activated carbon, for example, hydrogen storage capacity can be increased by up to 15% when compared to empty caverns. This enhancement offers both economic and operational benefits by maximizing the working gas volume per cavern and reducing capital and operational costs. Additionally, sorbents may provide extra mechanical support, potentially lowering the minimum operational pressure and improving cavern stability during cyclic injection and withdrawal.
This approach represents the first known application of microporous sorbents for enhancing hydrogen storage in engineered salt caverns. It bridges the gap between surface-based hydrogen storage technologies and subsurface geological storage systems. Future research will focus on searching more cost-effective sorbent materials, optimizing the performance of existing sorbents under specific geological settings, evaluating long-term performance under cyclic loading, and conducting field-scale demonstrations to validate the concept.
Co-author/s:
Rajesh Goteti, Geological resources Team Lead, Aramco Americas.
Ahmet Atilgan, Research Scientist, Aramco Americas.
Dr. Yaser Zayer, Lead Geologist, Saudi Aramco.
Traditionally, hydrogen is stored in salt caverns by injecting compressed gas into the void space. Here we introduce a novel approach to enhance hydrogen storage capacity by filling caverns with microporous sorbent materials prior to gas injection. A range of microporous sorbents—including activated carbons and metal-organic frameworks—were evaluated under representative pressure-temperature conditions. Among them, activated carbon may be the most scalable and cost-effective option for field deployment. The use of commercially available sorbents with favorable cost-performance ratios makes this approach applicable to both existing caverns and new constructions.
Our experimental results show that microporous materials can significantly increase volumetric hydrogen storage, especially under shallow cavern conditions where gas compression is less effective. When filled with microporous activated carbon, for example, hydrogen storage capacity can be increased by up to 15% when compared to empty caverns. This enhancement offers both economic and operational benefits by maximizing the working gas volume per cavern and reducing capital and operational costs. Additionally, sorbents may provide extra mechanical support, potentially lowering the minimum operational pressure and improving cavern stability during cyclic injection and withdrawal.
This approach represents the first known application of microporous sorbents for enhancing hydrogen storage in engineered salt caverns. It bridges the gap between surface-based hydrogen storage technologies and subsurface geological storage systems. Future research will focus on searching more cost-effective sorbent materials, optimizing the performance of existing sorbents under specific geological settings, evaluating long-term performance under cyclic loading, and conducting field-scale demonstrations to validate the concept.
Co-author/s:
Rajesh Goteti, Geological resources Team Lead, Aramco Americas.
Ahmet Atilgan, Research Scientist, Aramco Americas.
Dr. Yaser Zayer, Lead Geologist, Saudi Aramco.
Driven by escalating energy demands and technological progress, the use of high-grade steel in oil and gas pipelines has grown steadily. In the past 15 years, X70 and X80 steel pipelines, spanning over 60,000 kilometers, have enabled the development of a new pipeline system featuring large diameters, high strength, and high pressure. However, their extensive adoption has been marred by persistent challenges, especially the girth weld fracture failures. For example, PHMSA data shows that 10+ leakage incidents occurred in newly built high-grade steel pipelines from 2009–2010. Malaysia reported X70 pipeline weld fractures in 2014 and 2018; China recorded three consecutive X80 pipeline weld failures from 2017–2019; and Canada issued a 2020 advisory on this critical issue.
Through a decade of in-depth analyses and rigorous material testing, the authors have elucidated the root causes of cracks in semi-automatic and manual welds, clarified the softening/embrittlement mechanisms in automatic welds' heat-affected zones, and determined the combined effects of low matching, pre-strain, and geometric discontinuities. This research established a theoretical framework for predicting brittle fracture failures in high-grade pipeline welds. The framework offers practical guidance for improving new pipeline construction quality, managing in-service weld risks, and supports the future application of X90 and higher-grade pipeline steels.
Through a decade of in-depth analyses and rigorous material testing, the authors have elucidated the root causes of cracks in semi-automatic and manual welds, clarified the softening/embrittlement mechanisms in automatic welds' heat-affected zones, and determined the combined effects of low matching, pre-strain, and geometric discontinuities. This research established a theoretical framework for predicting brittle fracture failures in high-grade pipeline welds. The framework offers practical guidance for improving new pipeline construction quality, managing in-service weld risks, and supports the future application of X90 and higher-grade pipeline steels.
Pipeline safety serves as a foundational element in ensuring the operational integrity and security of energy infrastructure. Due to the factors, such as geological instability, material fatigue, and unauthorized third-party encroachment, persistent challenges continue to impede real-time risk detection and coordinated emergency response in pipeline systems. Operators now leverage advanced monitoring technologies such as distributed fiber optic sensing (DFOS), unmanned aerial systems (UAS), and computer vision-enabled cameras (CVCs) to achieve holistic perimeter threat assessment. These solutions have driven a 94.4% decrease in pipeline failure rates, with incident frequency dropping from 1.78 (2015) to 0.1 (2024) per 1,000 km-year.
Despite these technological improvements, significant issues persist. Interoperability constraints between monitoring systems have resulted in disparate data ecosystems that hinder unified risk management. Specifically, alarms generated through DFOS lack automated correlation with UAS and CVC data streams, requiring human operators to manually reconcile multi-system verification. Furthermore, post-detection processes dependent on manual data aggregation and decision-making introduces substantial response delays during emergency operations, potentially unsatisfying the requirement of 5-minute emergency action prescribed in API RP 1174:2020 for pipeline leak containment.
The past decade has seen unprecedented advances in artificial intelligence, marked by developments in large language models (LLMs) such as ChatGPT and DeepSeek. These innovations have fundamentally redefined operational paradigms in big data analysis. To address issues mentioned above, a DeepSeek-based intelligent agent was developed for pipeline risk management, enabling intelligent multi-system coordination and decision support across pipeline safety operations. This pioneering architecture positions the AI agent as a cognitive command hub, achieving seamless external system interoperability through industry-standard API protocols while enabling bidirectional data/control flows.
The system architecture further incorporates a AI-powered alarm risk verification engine, which integrates multi-source alert feeds with rule sets and historical incident repositories. This risk verification module autonomously executes various system tasks, such as drone takeoff or camera rotation, and generates priority rankings.
The framework also culminates in an intelligent emergency response knowledge base that synthesizes real-time risk analysis with operational metadata, including pipeline specifications and High-Consequence Area (HCA) geospatial parameters. This cognitive agent autonomously executes: risk stratification through machine learning classifiers, resource allocation optimization via constraint-based algorithms, activation of emergency plans, and automated notification workflows—delivering decision support throughout the emergency management lifecycle.
This technological innovation introduces pipeline risk management into a framework that comprehensively addresses the full operational lifecycle from risk control to emergency response. By implementing intelligent cross-system data integration and leveraging DeepSeek's advanced analytical capabilities, the solution achieves significant operational efficiencies - reducing manual intervention while accelerating risk verification and response times. Operational data demonstrates the system's proven effectiveness, currently delivering annualized cost savings exceeding RMB 3.6 million through optimized resource allocation and incident prevention measures.
Co-author/s:
Zixiao Chen, Senior Engineer, PetroChina.
Liwen Tan, Senior Engineer, PetroChina.
Jingdong Chen, Senior Engineer, PetroChina.
Despite these technological improvements, significant issues persist. Interoperability constraints between monitoring systems have resulted in disparate data ecosystems that hinder unified risk management. Specifically, alarms generated through DFOS lack automated correlation with UAS and CVC data streams, requiring human operators to manually reconcile multi-system verification. Furthermore, post-detection processes dependent on manual data aggregation and decision-making introduces substantial response delays during emergency operations, potentially unsatisfying the requirement of 5-minute emergency action prescribed in API RP 1174:2020 for pipeline leak containment.
The past decade has seen unprecedented advances in artificial intelligence, marked by developments in large language models (LLMs) such as ChatGPT and DeepSeek. These innovations have fundamentally redefined operational paradigms in big data analysis. To address issues mentioned above, a DeepSeek-based intelligent agent was developed for pipeline risk management, enabling intelligent multi-system coordination and decision support across pipeline safety operations. This pioneering architecture positions the AI agent as a cognitive command hub, achieving seamless external system interoperability through industry-standard API protocols while enabling bidirectional data/control flows.
The system architecture further incorporates a AI-powered alarm risk verification engine, which integrates multi-source alert feeds with rule sets and historical incident repositories. This risk verification module autonomously executes various system tasks, such as drone takeoff or camera rotation, and generates priority rankings.
The framework also culminates in an intelligent emergency response knowledge base that synthesizes real-time risk analysis with operational metadata, including pipeline specifications and High-Consequence Area (HCA) geospatial parameters. This cognitive agent autonomously executes: risk stratification through machine learning classifiers, resource allocation optimization via constraint-based algorithms, activation of emergency plans, and automated notification workflows—delivering decision support throughout the emergency management lifecycle.
This technological innovation introduces pipeline risk management into a framework that comprehensively addresses the full operational lifecycle from risk control to emergency response. By implementing intelligent cross-system data integration and leveraging DeepSeek's advanced analytical capabilities, the solution achieves significant operational efficiencies - reducing manual intervention while accelerating risk verification and response times. Operational data demonstrates the system's proven effectiveness, currently delivering annualized cost savings exceeding RMB 3.6 million through optimized resource allocation and incident prevention measures.
Co-author/s:
Zixiao Chen, Senior Engineer, PetroChina.
Liwen Tan, Senior Engineer, PetroChina.
Jingdong Chen, Senior Engineer, PetroChina.
Julian von Gramatzki
Chair
Executive Vice President Process Technology
TÜV NORD Systems GmbH & Co. KG
Brima M Baluwa Koroma
Vice Chair
Director General
National Petroleum Regulatory Authority
Qingshan Feng
Vice Chair
General Manager, Production Department
China Oil & Gas Pipeline Network Corporation
The integration of drag-reducing polymers (DRPs) in oil-water pipelines has emerged as a promising strategy for optimizing flow efficiency and enhancing separation processes. This study consolidates findings from multiple investigations on the effects of DRPs on oil-water flow dynamics within horizontal pipelines, emphasizing their significant role in reducing drag, altering flow patterns, and improving emulsion stability.
In experiments conducted in a 0.0254 m diameter pipe, the injection of water-soluble polymer solutions, specifically at concentrations of 10–15 ppm, led to drag reductions of approximately 65%. This reduction was particularly pronounced at higher mixture velocities, resulting in a noticeable decrease in pressure gradient and a shift in flow patterns. Notably, the phase inversion in dispersed flow regimes was identified within a 0.33–0.35 water fraction range, which could be effectively managed with the introduction of as little as 5 ppm of DRP.
Further investigations into water holdup conducted in a 2.54 cm pipe revealed that DRP injection significantly influenced water holdup at various superficial water velocities. The presence of DRP consistently increased water holdup in oil-water mixtures at lower velocities, demonstrating their potential to enhance separation efficiency. The results underscore the capability of DRPs to modify the distribution of oil-water droplets, thereby optimizing flow characteristics.
Additionally, the impact of DRPs on surfactant-stabilized water-oil emulsions was explored. The application of both oil-soluble and water-soluble polymers was examined for their effect on emulsion stability and pressure drop across varying temperatures and concentrations. The findings indicated that the appropriate selection of DRP could markedly improve emulsion stability, particularly with higher molecular weight polymers. Conversely, elevated temperatures tended to diminish the stability benefits provided by DRPs.
The results highlight the intricate interplay between drag reduction, flow dynamics, and emulsion characteristics, paving the way for enhanced design and operation of oil-water pipeline systems. By employing targeted DRP formulations, the energy efficiency of pipeline transport can be significantly improved, contributing to more sustainable oil and gas operations. This research not only elucidates the mechanisms behind DRP efficacy but also sets the foundation for future innovations in pipeline technology aimed at optimizing drag reduction and flow management.
In experiments conducted in a 0.0254 m diameter pipe, the injection of water-soluble polymer solutions, specifically at concentrations of 10–15 ppm, led to drag reductions of approximately 65%. This reduction was particularly pronounced at higher mixture velocities, resulting in a noticeable decrease in pressure gradient and a shift in flow patterns. Notably, the phase inversion in dispersed flow regimes was identified within a 0.33–0.35 water fraction range, which could be effectively managed with the introduction of as little as 5 ppm of DRP.
Further investigations into water holdup conducted in a 2.54 cm pipe revealed that DRP injection significantly influenced water holdup at various superficial water velocities. The presence of DRP consistently increased water holdup in oil-water mixtures at lower velocities, demonstrating their potential to enhance separation efficiency. The results underscore the capability of DRPs to modify the distribution of oil-water droplets, thereby optimizing flow characteristics.
Additionally, the impact of DRPs on surfactant-stabilized water-oil emulsions was explored. The application of both oil-soluble and water-soluble polymers was examined for their effect on emulsion stability and pressure drop across varying temperatures and concentrations. The findings indicated that the appropriate selection of DRP could markedly improve emulsion stability, particularly with higher molecular weight polymers. Conversely, elevated temperatures tended to diminish the stability benefits provided by DRPs.
The results highlight the intricate interplay between drag reduction, flow dynamics, and emulsion characteristics, paving the way for enhanced design and operation of oil-water pipeline systems. By employing targeted DRP formulations, the energy efficiency of pipeline transport can be significantly improved, contributing to more sustainable oil and gas operations. This research not only elucidates the mechanisms behind DRP efficacy but also sets the foundation for future innovations in pipeline technology aimed at optimizing drag reduction and flow management.
Lianshuang Dai
Speaker
Deputy Director of Production Department
China Oil & Gas Pipeline Network Corporation
Driven by escalating energy demands and technological progress, the use of high-grade steel in oil and gas pipelines has grown steadily. In the past 15 years, X70 and X80 steel pipelines, spanning over 60,000 kilometers, have enabled the development of a new pipeline system featuring large diameters, high strength, and high pressure. However, their extensive adoption has been marred by persistent challenges, especially the girth weld fracture failures. For example, PHMSA data shows that 10+ leakage incidents occurred in newly built high-grade steel pipelines from 2009–2010. Malaysia reported X70 pipeline weld fractures in 2014 and 2018; China recorded three consecutive X80 pipeline weld failures from 2017–2019; and Canada issued a 2020 advisory on this critical issue.
Through a decade of in-depth analyses and rigorous material testing, the authors have elucidated the root causes of cracks in semi-automatic and manual welds, clarified the softening/embrittlement mechanisms in automatic welds' heat-affected zones, and determined the combined effects of low matching, pre-strain, and geometric discontinuities. This research established a theoretical framework for predicting brittle fracture failures in high-grade pipeline welds. The framework offers practical guidance for improving new pipeline construction quality, managing in-service weld risks, and supports the future application of X90 and higher-grade pipeline steels.
Through a decade of in-depth analyses and rigorous material testing, the authors have elucidated the root causes of cracks in semi-automatic and manual welds, clarified the softening/embrittlement mechanisms in automatic welds' heat-affected zones, and determined the combined effects of low matching, pre-strain, and geometric discontinuities. This research established a theoretical framework for predicting brittle fracture failures in high-grade pipeline welds. The framework offers practical guidance for improving new pipeline construction quality, managing in-service weld risks, and supports the future application of X90 and higher-grade pipeline steels.
Anupam Das
Speaker
Deputy Chief Engineer (Telecom & Instrumentation)
Oil India Limited
The escalating demand for reliable energy supply necessitates robust and efficient pipeline infrastructure. Current pipeline integrity management (PIM) methods, while effective, often face limitations in detecting subtle defects, particularly in challenging environments or at early stages of corrosion. This abstract presents the transformative potential of quantum magnetometers (QMs) as a next-generation solution for enhanced pipeline integrity assessment.
Traditional magnetic flux leakage (MFL) and ultrasonic testing (UT) methods can be challenged by sensitivity thresholds, operational speeds, and environmental factors. Quantum magnetometers, leveraging the ultra-high sensitivity of atomic spin precession, offer unparalleled precision in detecting minute magnetic field anomalies caused by pipe corrosion, stress, and defects. This novel approach allows for the identification of smaller, nascent integrity issues that might otherwise go unnoticed by conventional techniques.
Deployment of advanced QM systems may involve in-line or external survey platforms (e.g., drone-mounted), to generate high-resolution, precise magnetic field maps of pipeline segments. Through sophisticated data processing and inversion algorithms, these magnetic anomalies are translated into detailed 3D representations of pipeline health, accurately pinpointing the location and characterizing the extent of structural anomalies.
The implementation of quantum magnetometry promises significant advantages for the oil and gas industry, including: greatly improved defect detection rates, enhanced proactive maintenance capabilities, reduced false positive indications, increased operational efficiency through faster survey speeds, and ultimately, a significant reduction in environmental risks and costly failures. This technology represents a crucial step towards achieving a new standard of predictive and reliable pipeline integrity, contributing directly to global energy security and sustainability.
Traditional magnetic flux leakage (MFL) and ultrasonic testing (UT) methods can be challenged by sensitivity thresholds, operational speeds, and environmental factors. Quantum magnetometers, leveraging the ultra-high sensitivity of atomic spin precession, offer unparalleled precision in detecting minute magnetic field anomalies caused by pipe corrosion, stress, and defects. This novel approach allows for the identification of smaller, nascent integrity issues that might otherwise go unnoticed by conventional techniques.
Deployment of advanced QM systems may involve in-line or external survey platforms (e.g., drone-mounted), to generate high-resolution, precise magnetic field maps of pipeline segments. Through sophisticated data processing and inversion algorithms, these magnetic anomalies are translated into detailed 3D representations of pipeline health, accurately pinpointing the location and characterizing the extent of structural anomalies.
The implementation of quantum magnetometry promises significant advantages for the oil and gas industry, including: greatly improved defect detection rates, enhanced proactive maintenance capabilities, reduced false positive indications, increased operational efficiency through faster survey speeds, and ultimately, a significant reduction in environmental risks and costly failures. This technology represents a crucial step towards achieving a new standard of predictive and reliable pipeline integrity, contributing directly to global energy security and sustainability.
Ali Masoumi
Speaker
BSc Graduate in Safety & Technical Inspection Engineering
Independent Researcher, Preparing for MSc in HSE Engineering, 2025
In our work on pipeline safety, we’ve seen how girth weld defects—micro-cracks or incomplete fusion—quietly threaten strategic petroleum reserve (SPR) pipelines, particularly in remote regions like Sub-Saharan Africa. These flaws risk leaks, environmental harm, and energy disruptions, yet traditional nondestructive testing (NDT) methods, like magnetic flux leakage, often falter due to logistical delays and limited sensitivity. In our view, a smarter approach is overdue. We propose a predictive AI-IoT framework to detect these defects early, aligning with TÜV standards (DIN EN ISO 5817, TÜV H2.23) to safeguard SPR pipelines and support net-zero ambitions.
A PRISMA-guided review of studies from 2015 to 2025 across Scopus, IEEE Xplore, and ResearchGate informed our approach. From 320 studies, we selected 50 focusing on AI-IoT integration, field-validated setups, and weld defects under 1.5 mm. Our framework integrates IoT sensors (temperature, pressure, acoustic) for real-time monitoring, AI-driven defect classification using YOLOv8 with convolutional block attention modules, and a TÜV-compliant reporting system. Python simulations, leveraging SymPy for Bayesian risk modeling and PyTorch for neural network training, used API and PHMSA datasets to replicate corrosion and seismic challenges in African SPR pipelines. Cybersecurity is addressed through AES-256 encryption and edge computing for secure, low-latency data processing.
Results demonstrate 98.5% detection accuracy, surpassing magnetic flux leakage (89.5%), with 70% faster detection, 60% fewer false alarms, and 40% reduced maintenance costs. Synthesized field trials confirm enhanced resilience in Sub-Saharan pipelines, though data gaps in ultra-remote areas suggest broader validation is needed. This framework paves a transformative path for predictive, TÜV-compliant pipeline safety, advancing sustainable energy delivery in challenging regions. Expanded field tests could solidify its global impact.
Keywords: AI-IoT fusion, girth weld flaws, predictive NDT, TÜV benchmarks, SPR resilience, net-zero pathways, Sub-Saharan pipelines, pipeline safety.
A PRISMA-guided review of studies from 2015 to 2025 across Scopus, IEEE Xplore, and ResearchGate informed our approach. From 320 studies, we selected 50 focusing on AI-IoT integration, field-validated setups, and weld defects under 1.5 mm. Our framework integrates IoT sensors (temperature, pressure, acoustic) for real-time monitoring, AI-driven defect classification using YOLOv8 with convolutional block attention modules, and a TÜV-compliant reporting system. Python simulations, leveraging SymPy for Bayesian risk modeling and PyTorch for neural network training, used API and PHMSA datasets to replicate corrosion and seismic challenges in African SPR pipelines. Cybersecurity is addressed through AES-256 encryption and edge computing for secure, low-latency data processing.
Results demonstrate 98.5% detection accuracy, surpassing magnetic flux leakage (89.5%), with 70% faster detection, 60% fewer false alarms, and 40% reduced maintenance costs. Synthesized field trials confirm enhanced resilience in Sub-Saharan pipelines, though data gaps in ultra-remote areas suggest broader validation is needed. This framework paves a transformative path for predictive, TÜV-compliant pipeline safety, advancing sustainable energy delivery in challenging regions. Expanded field tests could solidify its global impact.
Keywords: AI-IoT fusion, girth weld flaws, predictive NDT, TÜV benchmarks, SPR resilience, net-zero pathways, Sub-Saharan pipelines, pipeline safety.
Reyhaneh Pouryousef
Speaker
Master Student
College of Engineering, University of Tehran, Tehran, Iran
A gas hydrate is a crystal structure formed of cage-like hydrogen bonds between water molecules and trapping guest gas molecules in the hydrate cage at low-temperature and high-pressure thermodynamic conditions. By clogging pipes, valves, and other oil and gas refining and transmission equipment, natural gas hydrate causes pressure drop and flow reduction, ultimately leading to pipeline explosion and causing financial and life risks. So far, physical and chemical methods have been used to prevent this problem. Physical methods such as pipeline insulation, depressurization, dehumidification, and heating are not technically and economically desirable. Therefore, chemical methods are considered as an alternative approach. Chemical methods refer to inhibitors, which include Thermodynamic Hydrate Inhibitors (THIs) and Low-Dosage Hydrate Inhibitors (LDHIs). Low-Dosage Hydrate Inhibitors are divided into Kinetic Hydrate Inhibitors (KHIs) and Anti-Agglomerates (AAs). Thermodynamic Inhibitors are not economically and environmentally acceptable, due to the required high-weight percentages to be effective. Anti-Agglomerates are unacceptable due to their reaction with other additives, such as corrosion inhibitors, and their effectiveness after hydrate formation. However, Kinetic Inhibitors are a suitable option due to their low dosage and delaying hydrate formation reaction. In this study, the Iron Oxide (Fe3O4) nanoparticles were functionalized with polyvinyl pyrrolidone (PVP) polymer (Fe3O4@PVP) as a Kinetic Inhibitor using the Co-precipitation method and characterized by PXRD, FESEM/EDX, and TGA analyses. Then, a PVT test in a high-pressure cell was used to investigate Fe3O4@PVP inhibitory effect. In this method, the time of hydrate formation is obtained by detecting the pressure stabilization point when temperature decreases at a constant volume. The same steps are repeated for PVP, and the Fe3O4 effect on this material's inhibition is determined by comparing the PVT graphs. The reusability of Fe3O4@PVP is determined by creating a magnetic field; the nanostructure is separated and dried at 100°C. Finally, the recycled nanostructure is added to the system, and its inhibition is measured by PVT testing and compared with previous graphs. Fe3O4@PVP with a large surface area is expected to reduce the weight percentage of the kinetic inhibitor required and increase the performance due to the increased contact surface of PVP with water molecules in the gas flow line. In addition, Fe3O4@PVP is easily separated with a strong magnet due to the magnetic nature of its core, which makes it possible to reuse as an inhibitor. This chemical inhibitor's recyclability and small quantities required make it an environmentally friendly and economical inhibitor.
Co-author/s:
Ali Safaei, Assistant Professor, University of Tehran.
Azadeh Ebrahimian Pirbazari, Associate Professor, College of Engineering, University of Tehran.
Dr. Behnam Shahsavani, Assistant Professor, Petroleum Engineering Department, School of Chemical and Petroleum Engineering, Shiraz University.
Co-author/s:
Ali Safaei, Assistant Professor, University of Tehran.
Azadeh Ebrahimian Pirbazari, Associate Professor, College of Engineering, University of Tehran.
Dr. Behnam Shahsavani, Assistant Professor, Petroleum Engineering Department, School of Chemical and Petroleum Engineering, Shiraz University.
Mahnaz Shamshirsaz
Speaker
Professor
Amirkabir University of Technology (Tehran Polytechnic)
Structural Health Monitoring (SHM) is recognized as an effective tool for enhancing safety and ensuring the integrity of structures, thereby reducing maintenance and repair costs. Among various techniques, the electro-mechanical impedance (EMI) method, which employs piezoelectric materials, has emerged in recent decades as a powerful, non-destructive, real-time approach for early damage detection in critical equipment and structures.
This research focuses on monitoring the health of buried pipelines subjected to transverse loading, using the electro-mechanical impedance method. This technique relies on the interaction between the structure (the pipe) and the piezoelectric material, which acts as both a sensor and an actuator. To address this problem, both finite element modeling and experimental testing have been employed. In particular, transverse loading on fuel transfer pipes is primarily caused by ground subsidence phenomena.
In the adopted method, any defect that affects the structure results in a change in its natural frequency, which in turn alters the structure’s frequency response. This leads to variations in the impedance of the structure. In this study, transverse loading and its effects—including stress, plastic deformation, and work hardening—are considered as potential damages to the pipe. The pipes tested are made of carbon steel X60, similar to those used in gas and oil transmission pipelines.
Initially, based on the actual model and existing standards, a small-scale laboratory model was designed in COMSOL Multiphysics software. For this model, considering laboratory capabilities, three-point bending and four-point bending experimental setups were modeled, and the impedance method was applied under both healthy and loaded conditions. Subsequently, experiments were conducted on specimens similar to these models. Piezoelectric patches were attached to the pipes, and by applying voltage to them, electro-mechanical impedance monitoring was performed during loading.
Finally, the results obtained from implementing the impedance method in COMSOL were compared with experimental data to validate the approach.
The results indicate that as stress increases, the impedance output shifts slightly to the right, and the resonance peaks of the impedance significantly increase. Moreover, due to plastic deformation and work hardening, the impedance signals exhibit behavior opposite to that in the elastic range; that is, before plasticity and within the elastic region, increasing load and tension lead to an increase in impedance amplitude with slight rightward shifts. However, after surpassing the elastic limit and entering the plastic zone, the impedance amplitude decreases and shifts leftward. Similar behavior is observed due to work hardening, with notable differences in amplitude variation compared to the elastic state. The behavior in this case is highly dependent on the magnitude of the applied load, especially in the plastic region.
Co-author/s:
Iman Jalilvand, Postdoctoral Research Fellow, University of British Columbia.
This research focuses on monitoring the health of buried pipelines subjected to transverse loading, using the electro-mechanical impedance method. This technique relies on the interaction between the structure (the pipe) and the piezoelectric material, which acts as both a sensor and an actuator. To address this problem, both finite element modeling and experimental testing have been employed. In particular, transverse loading on fuel transfer pipes is primarily caused by ground subsidence phenomena.
In the adopted method, any defect that affects the structure results in a change in its natural frequency, which in turn alters the structure’s frequency response. This leads to variations in the impedance of the structure. In this study, transverse loading and its effects—including stress, plastic deformation, and work hardening—are considered as potential damages to the pipe. The pipes tested are made of carbon steel X60, similar to those used in gas and oil transmission pipelines.
Initially, based on the actual model and existing standards, a small-scale laboratory model was designed in COMSOL Multiphysics software. For this model, considering laboratory capabilities, three-point bending and four-point bending experimental setups were modeled, and the impedance method was applied under both healthy and loaded conditions. Subsequently, experiments were conducted on specimens similar to these models. Piezoelectric patches were attached to the pipes, and by applying voltage to them, electro-mechanical impedance monitoring was performed during loading.
Finally, the results obtained from implementing the impedance method in COMSOL were compared with experimental data to validate the approach.
The results indicate that as stress increases, the impedance output shifts slightly to the right, and the resonance peaks of the impedance significantly increase. Moreover, due to plastic deformation and work hardening, the impedance signals exhibit behavior opposite to that in the elastic range; that is, before plasticity and within the elastic region, increasing load and tension lead to an increase in impedance amplitude with slight rightward shifts. However, after surpassing the elastic limit and entering the plastic zone, the impedance amplitude decreases and shifts leftward. Similar behavior is observed due to work hardening, with notable differences in amplitude variation compared to the elastic state. The behavior in this case is highly dependent on the magnitude of the applied load, especially in the plastic region.
Co-author/s:
Iman Jalilvand, Postdoctoral Research Fellow, University of British Columbia.
Yajun Song
Speaker
Ph.D. Candidate
Production and Sand Control Completion Lab, Shcool of Petroleum Engineering, China University of Petroleum, Qingdao, China
Underground gas storage (UGS), a critical facility for natural gas peak shaving and supply security, often suffers severe sand production and reservoir property deterioration during high-intensity cyclic injection–production operations, posing risks to both safety and economic efficiency. However, the mechanisms and dynamic evolution of reservoir properties under such cyclic conditions remain poorly understood. In this study, a custom-designed large-scale physical simulation system for weakly cemented sandstone cores was used to conduct systematic experiments under multiple operating conditions. The effects of key parameters—including injection/production flow rate and cycle number—on sand production behavior and permeability evolution were analyzed. Results show that during gas injection, reduced flow velocity drives fine particles deeper into the reservoir, causing deposition, blockage, and significant permeability reduction. Conversely, during production, increased near-wellbore flow velocity induces a partial unblocking effect, leading to partial permeability recovery. Overall permeability variation ranges from 5% to 25%, with diminishing amplitude as cycles progress. Complementary triaxial cyclic loading tests were performed to elucidate rock damage accumulation mechanisms under alternating loads. Damage evolution was quantitatively characterized in terms of Young’s modulus degradation and residual strain accumulation, considering loading stress level, and cycle count. Based on experimental findings and theoretical analysis, an integrated porosity–permeability prediction and rock strength damage model was developed, incorporating both deformation and particle migration processes. A case study on an actual UGS well validated the model, revealing that with increasing injection–production cycles, near-wellbore damage intensifies, the critical sand production pressure drop decreases significantly (by ~26.3% after 10 cycles and ~32.4% after 20 cycles), and the damage zone becomes highly heterogeneous, with azimuthal differences up to 30%. This research clarifies the dynamic response mechanisms of sand production and reservoir property evolution during multi-cycle injection–production in UGS. It establishes a comprehensive workflow from experimental simulation to predictive modeling, offering theoretical and technical guidance for safe operation and optimized sand control in gas storage facilities.
Pipeline safety serves as a foundational element in ensuring the operational integrity and security of energy infrastructure. Due to the factors, such as geological instability, material fatigue, and unauthorized third-party encroachment, persistent challenges continue to impede real-time risk detection and coordinated emergency response in pipeline systems. Operators now leverage advanced monitoring technologies such as distributed fiber optic sensing (DFOS), unmanned aerial systems (UAS), and computer vision-enabled cameras (CVCs) to achieve holistic perimeter threat assessment. These solutions have driven a 94.4% decrease in pipeline failure rates, with incident frequency dropping from 1.78 (2015) to 0.1 (2024) per 1,000 km-year.
Despite these technological improvements, significant issues persist. Interoperability constraints between monitoring systems have resulted in disparate data ecosystems that hinder unified risk management. Specifically, alarms generated through DFOS lack automated correlation with UAS and CVC data streams, requiring human operators to manually reconcile multi-system verification. Furthermore, post-detection processes dependent on manual data aggregation and decision-making introduces substantial response delays during emergency operations, potentially unsatisfying the requirement of 5-minute emergency action prescribed in API RP 1174:2020 for pipeline leak containment.
The past decade has seen unprecedented advances in artificial intelligence, marked by developments in large language models (LLMs) such as ChatGPT and DeepSeek. These innovations have fundamentally redefined operational paradigms in big data analysis. To address issues mentioned above, a DeepSeek-based intelligent agent was developed for pipeline risk management, enabling intelligent multi-system coordination and decision support across pipeline safety operations. This pioneering architecture positions the AI agent as a cognitive command hub, achieving seamless external system interoperability through industry-standard API protocols while enabling bidirectional data/control flows.
The system architecture further incorporates a AI-powered alarm risk verification engine, which integrates multi-source alert feeds with rule sets and historical incident repositories. This risk verification module autonomously executes various system tasks, such as drone takeoff or camera rotation, and generates priority rankings.
The framework also culminates in an intelligent emergency response knowledge base that synthesizes real-time risk analysis with operational metadata, including pipeline specifications and High-Consequence Area (HCA) geospatial parameters. This cognitive agent autonomously executes: risk stratification through machine learning classifiers, resource allocation optimization via constraint-based algorithms, activation of emergency plans, and automated notification workflows—delivering decision support throughout the emergency management lifecycle.
This technological innovation introduces pipeline risk management into a framework that comprehensively addresses the full operational lifecycle from risk control to emergency response. By implementing intelligent cross-system data integration and leveraging DeepSeek's advanced analytical capabilities, the solution achieves significant operational efficiencies - reducing manual intervention while accelerating risk verification and response times. Operational data demonstrates the system's proven effectiveness, currently delivering annualized cost savings exceeding RMB 3.6 million through optimized resource allocation and incident prevention measures.
Co-author/s:
Zixiao Chen, Senior Engineer, PetroChina.
Liwen Tan, Senior Engineer, PetroChina.
Jingdong Chen, Senior Engineer, PetroChina.
Despite these technological improvements, significant issues persist. Interoperability constraints between monitoring systems have resulted in disparate data ecosystems that hinder unified risk management. Specifically, alarms generated through DFOS lack automated correlation with UAS and CVC data streams, requiring human operators to manually reconcile multi-system verification. Furthermore, post-detection processes dependent on manual data aggregation and decision-making introduces substantial response delays during emergency operations, potentially unsatisfying the requirement of 5-minute emergency action prescribed in API RP 1174:2020 for pipeline leak containment.
The past decade has seen unprecedented advances in artificial intelligence, marked by developments in large language models (LLMs) such as ChatGPT and DeepSeek. These innovations have fundamentally redefined operational paradigms in big data analysis. To address issues mentioned above, a DeepSeek-based intelligent agent was developed for pipeline risk management, enabling intelligent multi-system coordination and decision support across pipeline safety operations. This pioneering architecture positions the AI agent as a cognitive command hub, achieving seamless external system interoperability through industry-standard API protocols while enabling bidirectional data/control flows.
The system architecture further incorporates a AI-powered alarm risk verification engine, which integrates multi-source alert feeds with rule sets and historical incident repositories. This risk verification module autonomously executes various system tasks, such as drone takeoff or camera rotation, and generates priority rankings.
The framework also culminates in an intelligent emergency response knowledge base that synthesizes real-time risk analysis with operational metadata, including pipeline specifications and High-Consequence Area (HCA) geospatial parameters. This cognitive agent autonomously executes: risk stratification through machine learning classifiers, resource allocation optimization via constraint-based algorithms, activation of emergency plans, and automated notification workflows—delivering decision support throughout the emergency management lifecycle.
This technological innovation introduces pipeline risk management into a framework that comprehensively addresses the full operational lifecycle from risk control to emergency response. By implementing intelligent cross-system data integration and leveraging DeepSeek's advanced analytical capabilities, the solution achieves significant operational efficiencies - reducing manual intervention while accelerating risk verification and response times. Operational data demonstrates the system's proven effectiveness, currently delivering annualized cost savings exceeding RMB 3.6 million through optimized resource allocation and incident prevention measures.
Co-author/s:
Zixiao Chen, Senior Engineer, PetroChina.
Liwen Tan, Senior Engineer, PetroChina.
Jingdong Chen, Senior Engineer, PetroChina.
Among various options, subsurface storage in salt caverns has emerged as a commercially viable and technically robust solution for large-scale hydrogen storage due to their low permeability, self-healing properties and high operational flexibility. However, the relatively small volumetric capacity of individual caverns compared to other subsurface porous media limits their overall storage efficiency and economic viability.
Traditionally, hydrogen is stored in salt caverns by injecting compressed gas into the void space. Here we introduce a novel approach to enhance hydrogen storage capacity by filling caverns with microporous sorbent materials prior to gas injection. A range of microporous sorbents—including activated carbons and metal-organic frameworks—were evaluated under representative pressure-temperature conditions. Among them, activated carbon may be the most scalable and cost-effective option for field deployment. The use of commercially available sorbents with favorable cost-performance ratios makes this approach applicable to both existing caverns and new constructions.
Our experimental results show that microporous materials can significantly increase volumetric hydrogen storage, especially under shallow cavern conditions where gas compression is less effective. When filled with microporous activated carbon, for example, hydrogen storage capacity can be increased by up to 15% when compared to empty caverns. This enhancement offers both economic and operational benefits by maximizing the working gas volume per cavern and reducing capital and operational costs. Additionally, sorbents may provide extra mechanical support, potentially lowering the minimum operational pressure and improving cavern stability during cyclic injection and withdrawal.
This approach represents the first known application of microporous sorbents for enhancing hydrogen storage in engineered salt caverns. It bridges the gap between surface-based hydrogen storage technologies and subsurface geological storage systems. Future research will focus on searching more cost-effective sorbent materials, optimizing the performance of existing sorbents under specific geological settings, evaluating long-term performance under cyclic loading, and conducting field-scale demonstrations to validate the concept.
Co-author/s:
Rajesh Goteti, Geological resources Team Lead, Aramco Americas.
Ahmet Atilgan, Research Scientist, Aramco Americas.
Dr. Yaser Zayer, Lead Geologist, Saudi Aramco.
Traditionally, hydrogen is stored in salt caverns by injecting compressed gas into the void space. Here we introduce a novel approach to enhance hydrogen storage capacity by filling caverns with microporous sorbent materials prior to gas injection. A range of microporous sorbents—including activated carbons and metal-organic frameworks—were evaluated under representative pressure-temperature conditions. Among them, activated carbon may be the most scalable and cost-effective option for field deployment. The use of commercially available sorbents with favorable cost-performance ratios makes this approach applicable to both existing caverns and new constructions.
Our experimental results show that microporous materials can significantly increase volumetric hydrogen storage, especially under shallow cavern conditions where gas compression is less effective. When filled with microporous activated carbon, for example, hydrogen storage capacity can be increased by up to 15% when compared to empty caverns. This enhancement offers both economic and operational benefits by maximizing the working gas volume per cavern and reducing capital and operational costs. Additionally, sorbents may provide extra mechanical support, potentially lowering the minimum operational pressure and improving cavern stability during cyclic injection and withdrawal.
This approach represents the first known application of microporous sorbents for enhancing hydrogen storage in engineered salt caverns. It bridges the gap between surface-based hydrogen storage technologies and subsurface geological storage systems. Future research will focus on searching more cost-effective sorbent materials, optimizing the performance of existing sorbents under specific geological settings, evaluating long-term performance under cyclic loading, and conducting field-scale demonstrations to validate the concept.
Co-author/s:
Rajesh Goteti, Geological resources Team Lead, Aramco Americas.
Ahmet Atilgan, Research Scientist, Aramco Americas.
Dr. Yaser Zayer, Lead Geologist, Saudi Aramco.
