Explore the vast range of titles available.

Gas pipeline systems are one of the largest energy infrastructures in the world and are known to be very efficient and reliable. However, this does not mean they are prone to no risk. Corrosion is a significant problem in gas pipelines that imposes large risks such as ruptures and leakage to the environment and the pipeline system. Therefore, various maintenance actions are performed routinely to ensure the integrity of the pipelines. The costs of the corrosion-related maintenance actions are a significant portion of the pipeline’s operation and maintenance costs, and minimizing this large cost is a highly compelling subject that has been addressed by many studies. In this paper, we investigate the benefits of applying reinforcement learning (RL) techniques to the corrosion-related maintenance management of dry gas pipelines. We first address the rising need for a simulated testbed by proposing a test bench that models corrosion degradation while interacting with the maintenance decision-maker within the RL environment. Second, we propose a condition-based maintenance management approach that leverages a data-driven RL decision-making methodology. An RL maintenance scheduler is applied to the proposed test bench, and the results show that applying the proposed condition-based maintenance management technique can reduce up to 58% of the maintenance costs compared to a periodic maintenance policy while securing pipeline reliability.

Dry gas seals are widely used in the petrochemical industry for shaft end sealing of compressors, pumps and other equipment involving flammable, explosive, toxic and harmful media. To address the challenge of accurately identifying the fault states of dry gas seals under strong noise interference, this paper proposes a Multi-scale Attention 1D Residual Network (MA1D-ResNet) model based on sample augmentation. First, a dry gas seal acoustic emission (AE) test rig was built to collect non-stationary AE signals. The training dataset was expanded to five times its original size through data segmentation and Gaussian noise injection, significantly enhancing the model’s generalization capability in the data-input domain and training process. Then, the proposed model incorporates a Multi-scale Dual Attention Module (MDAM) into the ResNet18 architecture: it employs 1D convolutions to process temporal signals directly, avoiding feature loss, and integrates MDAM after the first convolutional layer and the Stage1 layer to strengthen fault feature extraction. Finally, experimental results demonstrate that the proposed model achieves an average accuracy of 99.8571% in classifying seven fault states (significantly outperforming five comparative models including CNN, ResNet, and ResNet-CBAM), with 100% recognition rate for five of the fault categories. The proposed model exhibits outstanding noise robustness, maintaining an accuracy of 92.43% under strong noise conditions of −6 dB. This study provides a highly robust solution for the intelligent fault diagnosis of dry gas seals in complex noise environments.

Dry gas reservoirs play a pivotal transitional role in meeting the net-zero target worldwide. Accurate modelling and simulation of this energy source require fast and reliable prediction of the gas compressibility factor (Z-factor). The experimental measurements of Z-factor are the most reliable source; however, they are expensive and time-consuming. This makes developing accurate predictive models essential. Traditional methods, such as empirical correlations and Equations of States (EoSs), often lack accuracy and computational efficiency. This study aims to address these limitations by leveraging the predictive power of machine learning (ML) techniques. Hence in this study three ML models of Artificial Neural Network (ANN), Group Method of Data Handling (GMDH), and Genetic Programming (GP) were developed. These models were trained on a comprehensive dataset comprising 1079 samples where pseudo-reduced pressure (Ppr) and pseudo-reduced temperature (Tpr) served as input and experimentally measured Z-factors as output. The performance of the developed ML models was benchmarked against two cubic EoSs of Peng–Robinson (PR) and van der Waals (vdW), and two semi-empirical correlations of Dranchuk-Abou-Kassem (DAK) and Hall and Yarborough (HY), and recent developed ML based models, using statistical metrics of Mean Squared Error (MSE), coefficient of determination (R2), and Average Absolute Relative Deviation Percentage (AARD%). The proposed ANN model reduces average prediction error by approximately 70% relative to the PR equation of state and by over 35% compared with the DAK correlation, while maintaining robust performance across the full Ppr and Tpr of dry gas systems. Additionally paired t-tests and Wilcoxon signed-rank tests performed on the ML results confirmed that the ANN model achieved statistically significant improvements over the other models. Moreover, two physical equations using the white-box models of GMDH and GP were proposed as a function of Ppr and Tpr for prediction of the dry gas Z-factor. The sensitivity analysis of the data shows that the Ppr has the highest positive effect of 88% on Z-factor while Tpr has a moderate effect of 12%. This study presents the first unified, statistically validated comparison of ANN, GMDH, and GP models for accurate and interpretable Z-factor prediction. The developed models can be used as an alternative tool to bridge the limitation of cubic EoSs and limited accuracy and applicability of empirical models.

Spiral-groove dry gas seals are widely used in turbomachinery. However, high-fidelity numerical simulations remain challenging because the gas film is micron-scale and features high shear and pronounced boundary-layer effects, while experimental studies are often expensive due to the large design space and tight machining tolerances. To address these issues, this study integrates a Kriging surrogate model with surrogate-based optimization (SBO) to systematically identify the key structural and operating parameters governing seal performance. The results quantify the individual effects of key geometric parameters, providing practical guidance for spiral-groove seal design and optimization. The Kriging model captures the nonlinear relationships between performance and design variables and shows good generalization, with a maximum residual standard deviation of 2.78 and all others below 1.0. Sobol analysis reveals that structural parameters dominate performance: groove depth and width exhibit total-effect indices of approximately 0.74 and 0.56, respectively, while rotational speed is the most influential operating parameter (≈0.75). Among eight structural variables, groove depth is the most critical, increasing leakage by more than 200% as it rises from 5 to 8 μm, followed by spiral angle and groove number; all remaining parameters each contribute less than 10%.

With the improvement of dry gas seal efficiency in high-parameter fields, the flow pattern of gas film lubrication is complicated. Based on gas lubrication theory, the Reynolds equation of compressible gas was established with a bidirectional T-groove dry gas seal as the research object. The Reynolds equation was solved to obtain a modified turbulent film pressure distribution law that affects gas lubrication. The effectiveness of the calculation program was verified by experimental tests. The results show that with an increase in operating parameters, the turbulence effect caused the gas film pressure fluctuation in the T-groove region to intensify, resulting in gas film flow instability. In addition, the inertia effect improved, which slowed down the leakage and affected the change law of stiffness and the rigid leakage ratio. When the fluid speed and gas pressure were low, the inertia effect could be ignored. When the groove depth was increased to 8 μm, the height difference between the trough and non-T-groove region became larger due to the combination of the turbulence and inertia effects. Further, when the gas film thickness was 3 μm, the opening force and gas film stiffness were high due to the dynamic pressure effect in the small film thickness groove. An increase in the gas film thickness weakened the turbulence effect and reduced the gas film pressure fluctuation.

The gas film of the carbon dioxide (CO2) spiral groove dry gas seal (S-DGS) is less than 3 μm during the startup process, and its opening stability is directly related to the operating performance of S-DGS. The finite difference method is employed to solve numerically the pressure distribution of S-DGS considering the slip flow and the real gas effect. The influence of both effects on the startup characteristics of S-DGS is discussed at different structural parameters. The results show that the slip flow effect inhibits the opening ability of CO2 S-DGS, whereas the real gas effect enhances its opening ability. Within the range of working conditions investigated, the seal processes a lowest startup rotational speed when the spiral angle is 7.5°, and the highest gas film stiffness occurs at small spiral angle when the film thickness is 0.6 μm. However, the relationship between groove number and gas film stiffness is complex which relates to the balance film thickness of the startup process. A higher opening ability can also be achieved by reasonably increasing the balance coefficient.

Purpose The purpose of this paper is to improve the film stiffness of a dry gas seal (DGS) through the proper design of 3D macroscopic surface structures based on numerical study. Design/methodology/approach A novel generalized three-dimensional (3D) geometric model is proposed to characterize macroscopic surface structures of a DGS, including grooves, waviness, radial taper and step. The mathematical model is established to simulate film pressure distribution. The effect of the surface profile and groove bottom profile on the steady-state performance of DGSs at different working conditions is investigated. Findings The unidirectional groove surface has the largest film stiffness at different speed conditions and the largest opening force at medium and high speed, whereas the annular groove has the largest opening force at static pressure. For obtaining the maximum film stiffness, unidirectional combined variable depth groove surface when ns = 0.4 and k = 0.5 outperforms the other unidirectional groove surfaces, whereas circumferential waviness when ns = 1 and k = 1 is the best choice among annular groove surfaces. Originality/value This study proposes a novel generalized 3D geometric model to characterize macroscopic surface structures of a DGS. The optimal groove bottom profile for different surface profiles of DGS is presented.

Purpose This study aims to investigate the influence mechanism of thermal-mechanical deformations on the CO2 mixture gases dry gas seal (DGS) flow field and compare the deformation characteristics and sealing performance between two-way and one-way thermal-fluid-solid coupling models. Design/methodology/approach The authors established a two-way thermal-fluid-solid coupling model by using gas film thickness as the transfer parameter between the fluid and solid domain, and the model was solved using the finite difference method and finite element method. The thermal-mechanical deformations of the sealing rings, the influence of face deformation on the flow field and sealing performance were obtained. Findings Thermal-mechanical deformations cause a convergent gap between the two sealing end faces, resulting in an increase in the gas film thickness, but a decrease in the gas film temperature and sealing ring temperature. The axial relative deformations of rotating and stationary ring end faces caused by mechanical and thermal loads in the two-way coupling model are less than those in the one-way coupling (OWC) model, and the gas film thickness and leakage rate are larger than those in the OWC model, whereas the gas film stiffness is the opposite. Originality/value This paper provides a theoretical support and reference for the operational stability and structural optimization design of CO2 mixture gases DGS under high-pressure and high-speed operation conditions.

The study examines the application of dry gas injection technology (cycling process) in different depletion stages (25%, 50%, 75%, 100% of the initial reservoir pressure, and the dew point pressure) at a gas condensate field. The injection took place with varying numbers of injection wells relative to production wells (4:1, 3:1, 2:1, 1:1, and 1:2). The study assessed the impact of dry gas injection periods, ranging from 1 to 3 years, on increasing the condensate recovery factor in a real gas condensate reservoir named X. A hydrodynamic model was used and calibrated with historical data, resulting in a comprehensive approach. Compared to the traditional depletion development method, this approach led to a significant 9% rise in the condensate recovery factor. The results indicate that injection has a positive effect on enhancing the recovery factor of condensate and gas when compared to primary development methods based on depletion. As a result, these findings facilitate a rapid evaluation of the possibility of introducing similar measures in gas-condensate reservoirs in the future for reservoir systems that have a low and moderate potential for liquid hydrocarbons C5+. The optimised multidimensional hydrodynamic calculations, utilising geological and technological models, are crucial in determining the parameters for the technological production and injection wells.

Purpose The purpose of this paper is to obtain the matching relationship between spiral groove, equalizing groove and operation parameters through the biparametric analysis for the bidirectional pumping hydrodynamic-static hybrid dry gas seal (BP-HHDGS). Design/methodology/approach The large eddy simulation (LES) model in Fluent is used to simulate the flow field of BP-HHDGS, and the biparameter variables method is chosen to analyze the effects of different parameters on the performance of BP-HHDGS. Findings BP-HHDGS has a greater opening force than hydrostatic dry gas seal (HDGS); the vortex is formed after lubricating gas is exhausted from the throttle. Increasing the depth of the equalizing groove and spiral groove has a synergistic enhancement effect on the opening force and leakage of BP-HHDGS. There is a matching relationship between spiral angle and rotational speed. The preferred parameter ranges in current conditions are found as follows: spiral angle αa = 15°–24°; groove-dam ratio λ = 0.4–0.7; equalizing groove depth hj > 35 µm; spiral groove depth hg = 5-10 µm. Originality/value The high starting capacity of HDGS is given to the hydrodynamic type seal, and thus the application promotion of HDGS in high-speed working condition is realized at the same time. This work also provides precise and quick theoretical guidance for the selection and design of hydrodynamic-static dry gas seal and further promotion.