Flow Measurement and Instrumentation最新文献

The Oil and Gas Production Rate (OGPR) is one of the most significant processes that play an essential role in the oil industry. Predicting OGPR is critical for effective reservoir management and enhancing oil recovery. Traditional methods (TMs) and numerical simulations (NS) often struggle to process and analyze nonlinear, complex, and massive datasets. To avoid these challenges, artificial intelligence (AI) techniques and machine learning (ML) models have been proposed as an alternative solution due to their high efficiency and rapidity in handling complex data. In this study, a new hybrid model is developed by combining the strengths of Artificial Neural Networks (ANN) and Gradient Boosting (GB), using Linear Regression (LR) as a meta-model by stacking technique. It captures nonlinear relationships effectively and manages outliers, enhancing prediction accuracy. The novelty of this study lies in the hybrid ANN-GB-LR model's ability to integrate various machine learning techniques into a robust framework, leveraging the high learning capacity of ANN, the robust handling of outliers by GB, and the straightforward interpretability of LR. This creative combination handles the limitations of individual models and enhances the general predictive performance. The model was trained and tested using actual field data from the Halewah field in Yemen. Evaluation metrics, including Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²), were utilized to evaluate and compare the hybrid model with other ML models: Random Forest (RF), XGBoost (XGB), LR, Light Gradient Boosting Machine (LGBM), GB, and K-nearest neighbors (KNN). The hybrid ANN-GB-LR model achieved superior results, with an R² of 0.998, an RMSE of 11.06 for oil flow rate predictions, and an R² of 0.98 and an RMSE of 172.15 for gas flow rate predictions. These results significantly surpass the other models, demonstrating the hybrid model's outstanding ability to capture complex data and provide accurate predictions. The ANN-GB-LR model surpasses Traditional Methods in predicting OGPRs. It shows a strong and reliable tool for optimizing reservoir management. This study establishes a new standard for predictive modeling in the oil industry, providing a framework for future research to apply hybrid models in handling complex datasets.

The flow characteristics in wetlands and vegetated channels are depend on the physical structure, density, and pattern of vegetation. Estimating average velocity in vegetated wetlands requires an accurate determination of the drag coefficient. The innovation of this research lies in calculating the drag coefficient while considering the pattern shape, plant flexural rigidity, and vegetation structure. Laboratory experiments were conducted in a rectangular flume using a parallel pattern of Eleocharis plants at three densities: low, medium, and high, with discharge rates of 18.2, 23.7, and 28.8 L/s, respectively. Comparative analysis revealed that the equation proposed by Kothyari et al. (2009) [23] is just suitable for determining the drag coefficient on rigid cylinders with a staggered pattern and it should be improved for real vegetation with different pattern. A comprehensive equation was developed for real wetland vegetation, incorporating a new pattern coefficient for pattern shape (ζpp) and correction factor (η) to consider plant flexural rigidity and vegetation structure. The results demonstrate that this equation accurately predicts the drag coefficient (RMSE = 0.127, MAE = 0.107, and R² = 0.9059) in channels with real vegetation with parallel and staggered patterns.

Triangular labyrinth side weirs have significantly more discharge capacity than traditional nonlinear weirs, and the complex hydraulic parameter interaction mechanism has been the research focus. This study used Computational Fluid Dynamics (CFD) to analyze the side weir's flow characteristics. Then, the Bayesian optimization algorithm and Extreme Learning Machine (BELM) developed a prediction model for the side weir's discharge coefficient. Finally, Sobol's method performed a sensitivity analysis for hydraulic parameters. The results show that the main channel's streamline is evenly distributed and begins to shift when it is close to the side weir. The overflow front is increasing and secondary flow also increases. BELM's Mean Absolute Percentage Error and Root Mean Square Error are 8.793 % and 0.455 in the testing stage, respectively, declined by about 56.24 % and 32.29 % compared with ELM; Froude number F_r, weir crest angle θ and the ratio of overflow front length to weir head l/h₁ are the most critical hydraulic parameters affecting the discharge coefficient, the global sensitivity coefficients are 0.4393, 0.4218 and 0.4152, respectively.

Side weir is a hydraulic structure within a channel which is usually used to discharge excess water, to divert the flow, and to regulate water surface levels in rivers and irrigation and drainage networks. In general, piano key weirs (PKW) have been used as weirs perpendicular to the flow direction in straight channels. However, the use of the PKW as a side weir in the outer arch of the channels is a new approach to enhance the weir's performance. In this study, 289 tests were first performed on the B-type rectangular side piano key weir (RSPKW) at two arc angles of 30 and 120°. Then, Fuzzy Inference System (FIS), Adaptive Neuro-Fuzzy Inference System (ANFIS), ANFIS and Teaching Learning Based Optimization (TLBO), ANFIS and Grasshopper Optimization Algorithm (GOA), Extreme Learning Machine (ELM) and Outlier Robust ELM (ORELM) models were used to predict the weir discharge coefficient. The results showed that two optimization models of TLBO and GOA increased the accuracy of the ANFIS model. The results showed that the ANFIS-GOA model has accuracy of Root Mean Squared Error (RMSE) = 0.0361, Coefficient of determination (R²) = 0.9772, and Kling Gupta coefficient (KGE) = 0.9858. The ANFIS-TLBO, ANFIS, and FIS models were ranked, respectively. Also, the results showed that ELM and ORELM models have accuracy close to ANFIS-GOA and can be a suitable alternative for complex fuzzy models. According to the statistical analysis, it was found that the parameters of the ratio of weir height to flow depth at the upstream edge of weir (P/h₁), arc angle (α), and the ratio of height of the foundation to the main channel width (p_d/B) had the greatest role in the development of the models, respectively.

It remains uncertain whether the flow state at the spool valve is laminar or turbulent under small openings. The annular slit flow and the damping hole flow are proposed to be equated to model the spool valve flow. The mutual transition criterion between laminar and turbulent flows is developed. The results indicate that the flow turns from transitional flow to turbulence as the valve opening increases to 5.2 μm. The flow coefficient increases linearly in transitional flow and remains constant in turbulence. Laminar flow may occur when the annular gap's length exceeds 9.45 μm. The effect of structural parameters including overlap, radial clearance, wear fillet, and temperature on flow transition is discussed. Wear on the valve port counteracts the positive overlap. Flow gain continues to rise, pressure gain increases and then falls, reaching a maximum of 5 × 10¹² Pa/m. Valve performance exhibits a brief ramp-up time. The theoretical model and analysis aim to elucidate the flow characteristics and performance evolution of the spool valve.

The main function of the bleed valve (BV) is to release part of the air from the axial compressor to prevent the aero-engine from stalling and surging. The stuck fault of the BV seriously affects the stable operation and safety of the aero-engine. An anti-stick BV design incorporating an eccentric valve plate is proposed to mitigate the issues of valve sticking caused by contamination particles and deformation. To address the issue of large flow field torque (FFT) during the operation of the anti-stick BV, computational fluid dynamics (CFD) methods were employed to investigate the FFT across various opening angles and flow channel structures. The results indicate that the FFT is primarily induced by the asymmetry of pressure distribution at the surfaces of the valve plate. The main strategies to reduce the FFT resulting from the valve plate structure include increasing the maximum closing angle β, reducing the valve thickness, and shifting the inlet surface closer to the shaft. The optimized valve plate structure reduces the maximum FFT of the BV by 60.7 %. Experimental testing of the optimized prototype demonstrates significantly improved opening and closing characteristics.

The void fraction is one of the basic parameters to study the gas-liquid two-phase flow, which has great significance to the transportation of oil pipelines and the design of nuclear reactor cooling towers. However, due to the complex and variable nature of gas-liquid two-phase flow, accurately measurement of the void fraction has remained a challenging task in both scientific research and industrial applications. According to the principle of electromagnetic wave propagation, a coaxial line phase sensor was designed, a hybrid dielectric constant model based on the homogeneous flow was established and a void fraction based on hybrid dielectric constant model was proposed. The experiments were carried out on the high-precision gas-liquid two-phase flow simulation experimental setup at Hebei University, China (70 data points), and the void fraction model was inspected and verified. Five typical hybrid dielectric constant correlations were compared. Introducing the frequency weight, optimizing the hybrid dielectric constant model based on the Series – Parallel correlation, a new void fraction prediction correlation of slug flow was proposed and evaluated. The results indicated that the mean absolute percentage error (MAPE) of the new void fraction correlation is 1.02 % and the all of the relative errors are within ±5 % error band.

The lithography immersion flow field is highly sensitive to minor variations due to the precision demands of lithography. The scanning flow induces pressure fluctuations on the lens surface, subsequently impacting the quality of exposure. Previous measurement methods have encountered sparse distribution measurements on the lens surface due to limitations in sensor size and flow field dimensions. In this manuscript, the authors propose a modal fusion flow field reconstruction method, effectively integrating sensor-based experimental methods and equation-based computational methods. This method achieves high-resolution measurements of stress distribution and velocity distribution. Initially, a simulation of the flow field under operational conditions is conducted to acquire a dataset, followed by decomposing the dataset into modes to establish a modal library. Throughout the measurement process, the modal library is dynamically restructured based on sensor signal using a sparse representation method to forecast the flow field, and subsequently, the flow field is corrected in accordance with the Navier-Stokes equation.

The flow structure and the phase inversion have great influence on the flow measurement in vertical upward oil-water two-phase flow. This paper attempts to investigate the flow patterns in oil-water flows through a vertical upward large pipe with the designed mini-conductance array probes measurement system and the vertical multi-electrode array (VMEA) measurement system. According to the output waveform of the mini-conductance array probes, the oil-in-water flow, transition flow and water-in-oil flow can be identified effectively. The fluctuating signals of the VMEA is processed by the recurrence plot and the time-frequency representation, the results show that the VMEA conductance signal with average measurement characteristics can realize an effective identification of the above three flow patterns, which has a good agreement with the results of the mini-conductance array probes. Finally, via comparing with previous published flow pattern transition boundary models in different pipe diameters, it is founded that the boundary line of the transition to oil-in-water based on the kinematic wave-based model and the observation-based model in the same diameter pipe are consistent with our experimental data. And the pipe diameter affects the flow pattern transition, compared with the boundary in small diameter pipe, the phase inversion requires a larger oil velocity, and the transition zone becomes narrower in large diameter pipe.

This work introduces the development of bubble measurement method utilizing a three-dimensional (3D) reconstruction technique from multi-view images. Multiple synchronized cameras were positioned around a water container, and calibration was performed to obtain external and internal camera parameters. Images of bubbles emerging from a nozzle were captured, and a machine learning technique was used to extract bubble silhouettes as foreground probability distributions, enabling the extraction of bubbles from images obtained with a simple lighting setup. These distributions were then projected onto a 3D voxel space using the visual hull method. It was confirmed that the method can successfully capture bubble generation, detachment, and rise behaviors, offering insights into understanding bubble dynamics and potential applications in 3D computational fluid dynamics validation.