Research
Real-Time Gas Flow Leakage Detection: A Machine Learning Approach to Sensitivity and Uncertainty Analysis
Leakage monitoring in flow lines and pipelines is highly important in gas plants due to the relevance of such a system to safety and efficiency. This work will, therefore, attempt to resolve the uncertainties in flow monitoring by integrating machine learning techniques in conducting sensitivity tests on real-time detection mechanisms. In this paper, the effectiveness of pressure-based indicators compared with volume changes has been considered with variations in flow rate and lifting processes. The findings obtained showed that the conventional assumption of the leakage being represented by the difference between initial and final gas volumes is unsatisfactory, especially during the initial pumping phase where inflow rates may appear to be less than outflow rates because of the purging of residual gases. In addition, the ramp-up and plateau stages exhibited a fair amount of variation in inflow and outflow pressure readings, further adding to the leak detection uncertainties. It has, therefore, been deduced that a variable tolerance window will be effective for leak detection based on the differential pressure data analysis between the inlet and outlet gauges. According to the result of the data analysis, the population variance is 5.38; the sample variance varies across different stages of operation, while the maximum tolerance and pressure are 0.166 and 7.9 bars, respectively. The work automates leak detection and simulates the range of variations, showing the potentiality of AI-ML modeling in enhancing real-world applications. In this work, we are pointing out how machine learning integration may enable a completely new way to define the variable tolerance windows that dramatically improve conventional leak detection.
Automation of Gas Leak Detection: AI and Machine Learning Approaches for Gas Plant Safety
Safety and protection of the environment involve real-time gas leak detection. The paper discusses the improvement in the accuracy and speed of gas leak detection using AI based on pressure-based monitoring. The model will be performing a flow consistency check using machine learning techniques for instantaneous detection at distinct stages in flows. Extensive exploratory data analysis was performed to assess the data and to choose the right machine learning models. The findings showed a significant evolution of pressure differences over time; hence, refining the tolerance level for leakage detection down to a fractional ±0.166 window was necessary. The gas flow data was divided into training and testing datasets, which consisted of 80% and 20%, respectively. Several AI models were tested, such as linear regression, logistic regression, SVM, and Random Forest-all had a test accuracy of over 99%. This AI-powered monitoring system could trigger an alarm or immediate notification in the case of a pressure drop beyond the defined tolerance window, improving upon the traditional methods of inspection. All of these contribute to improved safety, operational efficiency, and even cost savings. Furthermore, the scalability of the model holds great promise for other industrial scenarios. The animated simulation of the proposed solution was demonstrated.
Modeling the Constant Composition Expansion Test of Black Oil Using Pressure, Volume, and Temperature (PVT) Calculations
The black oil pressure, volume, and temperature (PVT) properties of well X were measured in the laboratory in a PT cell with subsurface and surface recombination samples. Four sets of black oil samples were collected for the analysis. The black oil standard test is a constant composition expansion test (CCE) separator flash test for volatile oils and rich oil gas condensate and a constant volume depletion test (CVD). The PVT analysis was carried out at Reservoir Fluid Laboratory, Port Harcourt. Oil samples were collected from the Q oil field. The PVT analysis results were correlated to validate the bubble point pressure (Pb), oil isothermal combustibility, (Co), oil formation volume factor (Bo), and the oil viscosity (ïo). The PVT report gives Po = 2000 psi while the standing correlation gives Pb = 1934.271 psi a difference of 65.7 psi, i.e. 3.3% and solution gas/oil ratio 647.3 SCF/STB while the standing correlation gives 671.03 SCF/STB a difference of 3.5%, oil formation volume factor (Bo) of 1.456 res. Bbl/STB while standing correlations give (Bo) of 1.0675 res bbl/STB a difference of 3.6%. The isothermal compressibility of the oil ranges from 10.12 x 10-6 psi-1 at P < Pb (at 4500 psi) to 4.1309 x 1018 cp at 15 psi. The conclusion is that Gas began evolving at 2000 psig and increased as the pressure decreased. Also, it was noticed that at high pressure of 4500 psig the black oil viscosity was as low as 0.54 cp while at a lower pressure of 15 psiag the viscosity recorded was 1.38 cp. The crude is of high viscosity, with an average absolute error = 3.5% (0.035). The reservoir contains heavy crude oil with an API rating of 30.
Validating Subsurface Samples of Volatile Black Oil through PVT Calculations of Surface Separator Samples for Enhanced Reservoir Characterization
This study investigates black oil's pressure, volume, and temperature (PVT) properties from well X, analyzed using subsurface and surface recombination samples. Black oil samples were collected from the Q oil field and subjected to PVT analysis at the Reservoir Fluid Laboratory in Port Harcourt. Key findings include bubble point pressure (Pb) of 2000 psi, with a standing correlation value of 1934.3 psi, resulting in a 3.3% difference. The solution gas/oil ratio was measured at 647.3 SCF/STB, compared to 671.0 SCF/STB from correlations, a difference of 3.5%. The oil formation volume factor (Bo) was 1.456 res Bbl/STB, while standing correlations indicated 1.0675 res Bbl/STB, showing a 3.6% difference. The isothermal compressibility ranged from 10.12 x 10<sup>-6</sup> psi<sup>-1</sup> at 4500 psi to 4.1309 x 10<sup>18</sup> cp at 15 psi. Gas evolution began at 2000 psig and increased with decreasing pressure. Viscosity varied significantly, recorded at 0.54 cp at 4500 psig and 1.38 cp at 15 psig. The reservoir contains heavy crude oil with an API rating of 30 and an average absolute error of 3.5% (0.035). These results enhance reservoir characterization and validate the use of PVT calculations in analyzing volatile black oil samples.
Optimizing Methane Recovery from Natural Gas Streams: Insights from Aspens Hysis Simulation
This study utilized the Aspen HYSYS Simulator Version 8.6 to simulate plant operations and optimize natural gas recovery using Technip’s feed gas composition. The focus was on investigating the effects of product recycling and determining the optimal feed tray position within the distillation column. Technip’s feed gas composition was selected due to its relevance in real-world applications, influencing the efficiency of methane recovery. The results indicated that maximum methane recovery occurred with zero product recycling and increasing the number of trays significantly enhanced methane recovery in the column overhead. Specifically, the analysis revealed a direct correlation between the number of trays and methane recovery efficiency. To support these findings, mathematical models were developed: one for predicting the optimal feed tray position represented as y=−0.01x2 +x−3y=−0.01x2+x−3, and two models for calculating the required number of trays for desired fractions of methane and natural gas liquids (NGLs) in the overhead. These models are expressed as y=2E−06x2 −3E−05x+0.8931y=2E−06x2 −3E−05x+0.8931 for methane and y=5E−07x2 −5E−05x+0.0352y=5E−07x2−5E−05x +0.0352 for NGLs. The accuracy and reliability of these models were validated through simulation results. In conclusion, this study demonstrates that optimizing tray configurations and minimizing product recycling can significantly enhance methane recovery processes. The developed models provide valuable tools for engineers and industry practitioners aiming to improve natural gas recovery efficiency in operational settings.
Optimizing Natural Gas Liquid Recovery: Efficient and Cost-Effective Methods for Enhanced Performance
The oil and gas industry, a cornerstone of the modern economy for nearly a century and a half, is now witnessing the full potential of the natural gas sector. Historically, natural gas has often been an unwanted byproduct of crude oil production, frequently vented or flared. However, technological advancements are enabling more effective and economical methods for capturing, processing, transporting, and utilizing this valuable resource. This research, crucial for the industry's future, focuses on the challenges of safely processing, storing, and transporting natural gas while maximizing output, particularly in the context of natural gas liquids (NGLs). The primary objective of this study is to explore various methods for enhanced NGL recovery from natural gas, highlighting the growing demand for these valuable components. Key findings indicate that several existing processes, including absorption, cryogenic separation, and membrane technology, offer significant potential for deep NGL recovery. Membrane technology stands out due to its efficiency and cost-effectiveness. These findings suggest that optimizing NGL recovery processes can play a crucial role in meeting the world's increasing demand for cleaner energy and specialty chemicals. The recommendations for future research underscore the need for further exploration of membrane technology's application in NGL recovery and the importance of continued innovation in separation processes to enhance overall efficiency and sustainability in the natural gas industry.
Comparative Characterization of Saltwater from Kula, Nembe, and Kwale in the Niger Delta, Nigeria
Three samples of water from Kwale, Nembe, and Kula in the Niger Delta were collected and characterized, and the following properties: pH, Temperature, Dissolved Oxygen, Turbidity, Acidity, Alkalinity, Electrical conductivity, Salinity, Oil and Grease, Total Hydrocarbon (THC), Heavy metals, BTEX and Poly Aromatic Hydrocarbon (PAH) were determined. The result of some of the key parameters showed that the Salinity of the Kula water sample is highest with a salt concentration of 13,115mg/L(at 30°C) followed by the Nembe water sample with a salt concentration of 2,500mg/L (at 29.68°C) and Kwale with a small salt concentration of 60mg/L (at 28.67°C). The electrical conductivity of the three water samples followed the same trend as salinity with Kula, Nembe, and Kwale water samples having electric conductivity of 20,101ïS/cm (at 30°C), 1,489ïS/cm (at 29.68°C), and 122ïS/cm (at 28.67°C) respectively. The Polimomatric hydrocarbon content in the three water samples showed that the Nembe water sample has the highest polimomatric hydrocarbon of 0.969mg/L followed by the Kwale water sample with 0.705mg/L and Kula water sample with 0.229mg/L. Interestingly the results also showed that n-pentacosane concentration is the highest component of the Total Petroleum Hydrocarbon (TPH) in the Kula and Kwale samples while n-hexacosane concentration is the highest component of the TPH in the Nembe water sample. This explains why the Nembe water sample is cloudier than the Kwale and Kula water samples. But in BTEX composition the total BTEX is highest in Nembe water, followed by Kwale and the least of these components is in Kula water.
