Prediction Of Volume Fraction Research Articles

Prediction of inlet gas volume fraction of rotary vane pump under variable operational conditions with 1DCNN-TL model utilizing vibration signals

The Rotary vane pump (RVP) exhibits promising potential in the lubricating oil system of aircraft engines. The entrainment of air into the lubricating oil flowing through the pump affects the suction and discharge flow rates of the RVP. Therefore, understanding the inlet gas volume fraction (IGVF) of the RVP is crucial to assess its capability to deliver sufficient lubricating oil for ensuring the safe operation of aircraft engines. This study presents a one-dimensional convolutional neural networks (1DCNN)-based transfer learning (TL) (1DCNN-TL) prediction model to predict IGVF for the RVP using experimental data from gas-liquid two-phase flow in the RVP. The model is pre-trained using the vibration signals under a specific differential pressure between the pump inlet and outlet to enable predictions of the IGVF under varying differential pressures. The 1DCNN serves as pre-trained model for analyzing the outcomes of different transfer tasks. The effect of different frozen layer numbers on training time and prediction accuracy of the neural network is explored. Subsequently, the influence of varied source domain data on prediction accuracy is investigated, revealing that for optimal TL results, stable condition data at 200 kPa should be preferred as the source domain. Then the 1DCNN-TL prediction model of IGVF of RVP under variable operational conditions is determined. The results indicate varying iteration convergence rates of the pre-trained model under a differential pressure of 200 kPa across different transfer tasks, with a final goodness of fit exceeding 0.958 after fine-tuning the model. The model demonstrates the high prediction accuracy and applicability, which can contribute to improving the reliability and safety of aircraft engines.

Comparison of Backscattered and Transmitted Gamma Rays Spectra for Prediction of Volume Fraction of Three-Phase Flows Using Machine Learning Model

Comparison of Backscattered and Transmitted Gamma Rays Spectra for Prediction of Volume Fraction of Three-Phase Flows Using Machine Learning Model

Oil-Air Distribution Prediction Inside Ball Bearing with Under-Race Lubrication Based on Numerical Simulation

Oil/air two-phase flow distribution in the bearings is the basis for bearing lubrication status identification and precise thermal analysis of the bearing. In order to understand the fluid behavior inside the under-race lubrication ball bearing and obtain an accurate oil volume fraction prediction model. A numerical study of ball bearing with under-race lubrication is carried out to study oil-gas two-phase distribution inside the bearing, and the influence of several parameters is quantified, like bearing rotating speed, oil flow rate, oil viscosity, and oil density. The results indicate that the oil fraction in the bearing cavity between the inner and outer ring shows a periodic distribution along the circumference direction, and the period is the same as the number of under-race oil supply holes. Oil distribution alone radial direction is affected by the outer-ring-guiding cage and centrifugal force, leading to oil accumulation near the outer ring. Different bearing running conditions and oil characteristics do not change the oil distribution trend alone in circumference and radial direction, but the difference ratio. Finally, based on the numerical simulation results, a formula for the average oil volume fraction prediction in the bearing ring cavity is constructed.

BPNN model based AI for the estimation of soot data from flame luminosity emissions in H2/N2 diluted ethylene laminar diffusion flames

Advanced combustion devices and alternative fuels like hydrogen require an estimation of the impact of such changes on engine exhaust emissions of regulated pollutants like soot. Huge experimental data are then required to be collected and post-processed, both in academic and industrial setups. Machine learning and artificial intelligence can be employed to reduce cost and time. This study presents a Back Propagation Neural Network (BPNN) model that has been validated and optimized for the simultaneous prediction of soot volume fraction, temperature and particle sizes from flame luminosity measurements. The compatibility, robustness and reliability of neural network models in terms of fuel composition and flow rate variations was analyzed , by varying both fuel flow rate and fuel stream dilution in axisymmetric diffusion flame burning in a coflow of air. BPNN model predicted results were contrasted against those obtained through laser diagnostics. A detailed analysis of the performance of BPNN model, based on an extensive experimental study revealed indifference to N2/H2 dilution and fuel flow rate variations. Furthermore, an original BPNN model is optimized to improve learning rate and to reduce computation cost, by applying a Bayesian algorithm which continuously monitors and minimizes an error function. It was concluded that a training set size of three was sufficient to predict soot field parameters with a fair prediction accuracy. These results have direct implication for the application of proposed technique in practical combustion equipment where operating parameter, e.g. Air–fuel ratio and EGR, show both gradual and instantaneous variations and affect both performance and emissions. These results clearly demonstrate the robustness of this technique which offers opportunities for real-time, in situ, monitoring of practical combustion devices. Hence, Real-time data of sooting characteristics of flames can be used to both monitor and control pollutant emissions by integrating a response strategy in the system.

A defect detection framework using three-dimensional convolutional neural network (3D-CNN) with in-situ monitoring data in laser powder bed fusion process

Laser powder bed fusion (L-PBF) is a promising additive manufacturing (AM) technology for manufacturing complex-shaped metallic parts with high density. Since L-PBF has been rapidly developed and applied in various industries, the quality assurance of the printed part using the process became a topic of primary importance. In this respect, in-situ monitoring techniques have received increased attention in recent years for aiding the quality control of L-PBF process and the certification of the products. This study proposes a novel defect detection framework with a three-dimensional convolutional neural network (3D-CNN) and in-situ monitoring of light intensity for detecting both the lack-of-fusion and keyhole-induced defects. The proposed 3D-CNN model works with a 3D moving window to perform the local inspection using the measured light intensities in three-dimensional space to classify the type of defect. Furthermore, the model predicts the local volume fraction to provide insights into the degree of defect. To perform the classification and regression with a single 3D-CNN, the joint classification and regression approach was adopted to train the model using the results obtained with micro-computed tomography as the ground truth. In order to build the training dataset, the samples with artificial defects were fabricated in different process regimes with energy densities ranging from 19.84J/mm3 to 110.12J/mm3. After the training process, the proposed model was evaluated with the test specimens which contain randomized defects generated due to the excessively low and high energy input. The results showed that the proposed 3D-CNN-based defect detection framework can detect pores greater than 80μm induced by both lack-of-fusion and keyhole mode melting. The sensitivity of the proposed framework was evaluated, showing the true positive rate of 75.69% and 70.47% for lack-of-fusion and keyhole defects with a void volume larger than 0.0003mm3. The prediction of local volume fraction with R2 score of 0.91 was also achieved with the proposed 3D-CNN approach.

Prediction of fluids volume fraction and barium sulfate scale in a multiphase system using gamma radiation and deep neural network

In the oil industry, during the production of oil and gas, barium sulfate (BaSO4) scale may occur on the inner walls of the pipelines leading to the reduction of the internal diameter, making the fluids' passage difficult and complicating the calculation of the fluids volume fraction. This paper presents a methodology to predict volume fraction of fluids and BaSO4 scale thickness from obtaining spectra of two NaI(Tl) detectors that record the transmitted and scattered beams of gamma-rays. Theoretical models for a multiphase annular flow regime (gas-saltwater-oil-scale) were developed using MCNP6 code, which is a mathematical code based on the Monte Carlo method. The simulated data was used to train a deep neural network (DNN) to predict the volume fraction of gas, saltwater and oil, and the concentric scale thickness. A Python optimization library called Optuna was used for the hyperparameters search to design the DNN architecture. The methodology presented great results, especially for scale thickness prediction. Although the results for saltwater did not reach the same level, it was still possible to predict approximately 70% of the patterns up to 10% relative error. This achievement indicates the possibility to calculate the volume fraction of fluids and the concentric scale thickness in the offshore oil industry using gamma densitometry and deep learning models.

Measurement method of wet gas two-phase flow rate based on the main frequency and the modulus of vector acceleration of swirl flowmeter

The swirl flowmeter is widely used in the wellhead measurement of low-permeability gas fields in China. In this study, the MEMS three-axis acceleration sensor (MEMS-TAAS) replaced the traditional piezoelectric sensor to distinguish the frequency signal from the interference noise. Based on the MEMS-TAAS, the vector acceleration signals of swirl flowmeter were acquired and analyzed simultaneously with the precession frequency signals to establish a wet gas two-phase flow measurement model. The method of establishing a liquid volume fraction prediction model based on the vector acceleration modulus parameter was pioneered. Finally, a dual-parameter wet gas measuring method under normal pressure was constructed using an iteration algorithm. The results demonstrate that this model’s relative errors are acceptable. This method effectively provides further development thought for swirl flowmeter which can achieve the accurate prediction of two-phase flow using only one swirl meter with a MEMS-TAAS, without the need for other flow meters or differential pressure sensors, especially for the low-liquid-fraction wet gas.

Using statistical features and a neural network to predict gas volume fractions independent of flow regime changes

This work presents a methodology based on nuclear techniques and Artificial Neural Networks (ANNs) for Gas Volume Fraction (GVF) predictions in two-phase flow independent of flow regime changes. Using gamma-ray principles attenuation with an appropriate geometry, consisting of a single detector and a single-energy gamma-ray source, it is possible to obtain data which could be adequately correlated to the GVF using neural network. The novelty of this study, in contrast to previous research, lies in the utilization of novel statistical features extracted from the discrete wavelet transform applied to the gamma-ray spectrum. Instead of analyzing the entire gamma-ray spectrum, this approach focuses on specific features, thereby mitigating unwanted noise and enhancing the efficiency of predictive capabilities in real conditions. The two-phase flow loop is used to provide the training and testing data for the network. The GVF was predicted using extracted feature from fourth stage of discrete wavelet transform precisely with mean absolute error less than 0.009.

Turbulent Flame Propagation in Hydrogen-Air and Methane-Air Mixtures in the Field of Synthetic Turbulence: Direct Numerical Simulation

A technique alternative to the direct numerical simulation of turbulent combustion of gas mixtures is proposed. It is based on the solution of the three-dimensional transport equations for species concentrations and the energy conservation equation in the “synthetic” field of constant-pressure homogeneous, isotropic and statistically stationary (forced) turbulence using the detailed reaction mechanism. The synthetic turbulence with given spatial and temporal correlation functions is generated using the Monte Carlo method, assuming that the components of the vector of fluctuation velocity obey the normal Gaussian distribution. The technique is applied to the problem of turbulent combustion of fuel-lean and stoichiometric mixtures of hydrogen and methane with air at a turbulence intensity up to 10 m/s. The calculated turbulent flame propagation velocities agree satisfactorily with the values measured in the fan-stirred bomb. The predicted volume fractions of active reaction centers H, O, and OH in a turbulent flame are shown to be less than in a laminar flame up to an order of magnitude, which also agrees with the experiment. In general, calculations indicate that the “wrinkled flame” model is applicable to fuel-lean and stoichiometric mixtures of hydrogen and methane with air at turbulence intensities up to 10 m/s

A Methodology for Analysis and Prediction of Volume Fraction of Two-Phase Flow Using Particle Swarm Optimization and Group Method of Data Handling Neural Network

Determining the volume percentages of flows passing through the oil transmission lines is one of the most essential problems in the oil, gas, and petrochemical industries. This article proposes a detecting system made of a Pyrex-glass pipe between an X-ray tube and a NaI detector to record the photons. This geometry was modeled using the MCNP version X algorithm. Three liquid-gas two-phase flow regimes named annular, homogeneous, and stratified were simulated in percentages ranging from 5 to 95%. Five time characteristics, three frequency characteristics, and five wavelet characteristics were extracted from the signals obtained from the simulation. X-ray radiation-based two-phase flowmeters’ accuracy has been improved by PSO to choose the best case among thirteen characteristics. The proposed feature selection method introduced seven features as the best combination. The void fraction inside the pipe could be predicted using the GMDH neural network, with the given characteristics as inputs to the network. The novel aspect of the current study is the application of a PSO-based feature selection method to calculate volume percentages, which yields outcomes such as the following: (1) presenting seven suitable time, frequency, and wavelet characteristics for calculating volume percentages; (2) the presented method accurately predicted the volume fraction of the two-phase flow components with RMSE and MSE of less than 0.30 and 0.09, respectively; (3) dramatically reducing the amount of calculations applied to the detection system. This research shows that the simultaneous use of time, frequency, and wavelet characteristics, as well as the use of the PSO method as a feature selection system, can significantly help to improve the accuracy of the detection system.

Mass flow rate measurement of gas-liquid two-phase flow using acoustic-optical-Venturi mutisensors

The measurement of multiphase flow parameters is essential for the online monitoring of industrial production and energy metering. In this paper, a multi-sensor experimental measurement device is designed based on NIR, acoustic emission sensors, and throated Venturi. The measurement information is decomposed using modal decomposition, and the characteristic variables of the gas volume fraction are extracted by flow noise decoupling and light attenuation analysis. A new gas volume fraction model is proposed based on Gradient Boosting Decision Tree (GBDT) through feature-level fusion, and the Mean Absolute Percentage Error (MAPE) of the gas volume fraction prediction models is within 4% for the three flow patterns. A new flow rate model is established based on the Homogeneous and Collins models. Laboratory results indicate that the MAPE of the flow rate model is 1.56%, and 98.61% relative deviations are within ±20% error band. The study provides a new method for online measurement of multiphase fluid motion and a theoretical basis for sensing mechanism and measurement of multiphase flow.

Pressure effects on soot formation and evolution in turbulent jet flames

In this study, two series of pressurized turbulent jet sooting flames at 1, 3, and 5 bar with either fixed jet velocity or fixed Reynolds number are simulated to study the pressure effects on soot formation and evolution. Through a radiation flamelet progress variable approach with a conditional soot subfilter probability density function (PDF) model to consider the turbulence–chemistry–soot interactions, quantitatively good agreements are achieved for soot volume fraction (SVF) predictions compared with the experimental data, regardless different turbulent intensities and residence times. SVF source terms are then discussed to show the pressure effects on nucleation, condensation, surface growth, and oxidation at different axial positions in these flames. It is found that surface growth and oxidation increase by about three orders of magnitude from 1 to 5 bar, while nucleation and condensation only increase within one order of magnitude. The stronger SVF scaling on pressure than measured data is found to be attributed to the inaccurate surface growth and oxidation scaling on pressure. Further analysis indicates that (i) the uncertainty of C2H2 prediction at elevated pressures is likely a major reason for the too strong surface growth scaling; and (ii) taking account of pressure effects in the conditional subfilter PDF modeling for turbulence–soot–chemistry interactions is likely a key to improve oxidation prediction. The results in this study open up the possibilities for improving future turbulent sooting flame modeling by improving C2H2 chemistry and turbulence–chemistry–soot modeling at elevated pressures.

Thermal Creep Behavior and Creep Crystallization of Al-Mg-Si Aluminum Alloys.

The experimental temperature is 613.15~763.15 K, and the strain rate is 0.01~10 s-1. The hot compression creep test of the 6082-T6 aluminum alloy sample is carried out by Gleeble-3500 hot compression simulation compressor, and its creep behavior is studied by scanning electron microscope. The results show that the DRX crystal has an irregular shape and that content of the Mg phase, Si phase, and Mn phase in the crystal are the main factors to change the color of DRX crystal. Temperature and strain rate are important factors affecting dynamic recrystallization. Reducing temperature and increasing strain rate will weaken dynamic recrystallization, and DRX critical condition and peak stress (strain) will increase. The constitutive equation of hot creep of 6082 aluminum alloy was established by introducing the work hardening rate-rheological stress curve, and the relationship between DRX critical condition, peak stress (strain) and parameter Z during creep was explored. Based on the Av rami equation, the prediction equation of the DRX volume fraction is established. With the increase of strain, DRX volume fraction is characterized by slow increase, then rapid increase and then slowly increase. In the hot -forming extrusion process of 6082 aluminum alloy, according to the volume fraction prediction equation, the DRX can be reduced, and the internal structure of the material can be optimized by changing the extrusion conditions and particle size.

Numerical investigations of soot generation during wood-log combustion

• Particle-scale biomass combustion model with soot formation is established. • Virtual-particle-based thermally-thick model and two-equation soot model are integrated. • Improved prediction of soot volume fraction for a single-particle combustion experiment is achieved. • Soot generation during wood log combustion depends highly on flame structure and the packing of wood logs. Soot formation is an important challenge in the design of modern wood stoves, as soot not only deteriorates the combustion efficiency but also poses threats to human health. Although soot formation in biomass combustion has been studied previously, the investigation at wood stove level is still rare due to its complex nature. In this paper, numerical simulations are performed to uncover the basic trends of soot formation during wood log combustion. The soot formation model is developed based on a particle-resolved biomass combustion algorithm, where the intraparticle heat and mass transfer effect, soot mass fraction and particle size are all resolved. Besides, simplified tar and precursor models are used in solving the reaction kinetics of soot formation. The integrated model is first validated through the combustion simulation of a micron-sized coal particle in air, where the predicted flame temperature and the soot volume fraction show improved agreement with experimental data compared to a previous modeling work. Thereafter, the soot formation during wood-log combustion in a confined stove is studied. Different combustion behaviors are observed for varying numbers of wood logs and for variations in the wood-log stacking. Additionally, the flow field temperature, tar, soot, and oxygen concentrations during the combustion are analyzed. Finally, the influences of the air intake rate, the relative distance between wood logs, and temperature boundary condition on the soot formation are discussed. This work provides useful information for the design and the optimization of modern wood stoves.

Assessment of physical soot inception model in normal and inverse laminar diffusion flames

Despite the extensive studies, accurate and reliable modeling of the soot inception process, especially at high pressure conditions, amenable to multi-dimensional flame simulations remains a challenge. In this study, the physical inception model was comprehensively evaluated in the fully-resolved simulations of laminar normal diffusion flame (NDF) and inverse diffusion flame (IDF) at elevated pressures. The effects of inception models on polycyclic aromatic hydrocarbons (PAHs) and soot predictions were quantitatively analyzed, including the selection of soot precursors and collision efficiency models. The results show that the quantitative PAH predicted by different collision efficiency models can differ by an order of magnitude. Compared to the constant efficiency, the temperature-dependent collision efficiency was found to improve the quantitative PAH predictions and the prediction of the spatial soot distribution in NDF, with an increased level of soot on the flame centerline. The inclusion of small-sized PAH species (such as A2, A2R5, and A3) as soot precursors was also found to improve the quantitative prediction of soot volume fraction. The physical inception model performs well in NDF using the optimal parameters. Moreover, simultaneous measurements of PAH and soot were performed in IDF configuration for the evaluation of the physical inception model. Contrary to NDF, PAHs and soot are formed on the outer side of the flame and cannot be oxidized in IDF. The experiment observed that the PAHs concentration increased in the post-flame region, while the soot concentration remained unchanged. However, the opposite trend was obtained in simulations, that is, the PAHs concentration decreased while the soot concentration increased, because the physical inception model predicts the inception behavior in the post-flame area, resulting in persistent transformation of PAHs into soot particles. To improve the predictions in IDF, the radical effects in the inception process need to be considered in the model.

Evaluation of nuclear data analysis techniques for volume fraction prediction in the flow meter

Abstract The volume fraction percentage measurement in multiphase flows is a vital need in the oil, gas and petroleum industries. Thus, diverse and precise techniques should be presented for achieving this purpose. In this research, the water-oil two-phase flows were simulated using the MCNPX code in operational and real conditions in the oil district of Kharg. A single source 137Cs and a NaI (Tl) detector were used to provide the required data for volume fraction prediction. Then, the ANN, Gaussian, Linear Regression, and Fourier techniques were applied to the acquired nuclear data in order to compare and identify the suitable and precise method for predicting the volume fraction. Using the ANN, Gaussian, Linear Regression, and Fourier techniques, the volume fraction was predicted with a mean relative error percentage of less than 8.71, 10.14, 16.07, and 12.45%, respectively. Also, the root mean square error quantities were calculated 1.05, 1.18, 1.36, and 1.27, respectively. The results reveal that the ANN method has superior in comparison with the other methods.

Numerical simulation method of a circulating fluidized bed reactor using a modified MP-PIC solver of OpenFOAM

There are some previous works for simulating a bubbling fluidized bed (BFB) reactor using OpenFOAM's MPPICFoam solver, but those for circulating fluidized bed (CFB) reactors are few. In this study, the MPPICFoam solver was verified with a BFB reactor by comparing the solver's simulation results with the experiment and simulation results from the literature. By introducing the inter-boundary particle circulation function and a new module for setting sand particle size distribution, simulations were performed for a 0.1 MW th pilot-scale CFB combustor under isothermal conditions. The modified solver for the CFB reactor gives similar results as the experiment and commercial computational fluid dynamics (CFD) tool, well-predicting the pressure distribution and solid volume fraction in the riser. • MPPICFoam solver reliability for lab-scale bubbling fluidized-bed reactor verified. • Accurate solver prediction of solid volume fraction (horizontal) distribution. • Model used for numerical simulation to study riser hydrodynamics of a CFB combustor. • Particle size distribution module and new circulating boundary conditions added. • Improved solver shows superior predicted experimental results in dense bed region.

Prediction of Solid-State Phase Transformations for the Ti-6Al-4V Alloy

Ti-6Al-4V alloy is the most relevant titanium alloy, finding applications in multiple high-value industries. The production of Ti-6Al-4V components by selective laser melting is particularly challenging, due to the highly localized heat input and large temperature gradients, which affect the material’s microstructure and final mechanical properties. The main objective of this work is to develop a metallurgical framework able to describe the solid-state phase transformations of Ti-6Al-4V during processing. The predicted volume fraction of each solid phase is used to estimate strains induced by the thermal cycle and the phase transformations independently. The presented numerical model considers a single finite element subjected to heat fluxes that impose two sequential heating/cooling cycles, replicating the laser movement. The numerical results emphasize the importance of predicting phase volume fraction fields for an accurate estimation of the material’s volume change. In fact, changing the heating/cooling rates resulted in completely different final microstructures and a 0.5% difference on the material’s volume change relative to its initial volume, which would correspond to a stress increment of approximately 200 MPa if the linear elastic material was fully constrained.

Flow regime identification and gas volume fraction prediction in two-phase flows using a simple gamma-ray gauge combined with parallel artificial neural networks

Volume fraction and regime identification are considered as two main goals in the multiphase flow measurement. By developing the applications of artificial neural networks (ANN), new approaches have been introduced in the multiphase measurements. In the present work, prediction of gas volume fraction and identification of five different flow regimes including Bubble, Dispersed, Pluged, Annular, and Slug regimes were carried out using the simplest form of a radiation measurement system and proposing a simple structure of ANN including two independent MLP networks which are working in parallel. All data used for training and testing the networks were recorded using a simple radiation-based setup involving a137Cs gamma-ray source and one NaI(Tl) detector in the experimental setup with real dynamic conditions of fluids in a test loop. Extracted features from the recorded spectrum by the detector include full-energy peak and total counts. Overall results showed that all introduced flow regimes have been successfully identified by one of the proposed ANNs while GVFs have been predicted precisely using another one with a mean relative error of less than 3%.

Prediction of volume fraction of primary α phase in dual-phase titanium alloy based on laser ultrasonic

The volume fraction of the primary α phase affects the mechanical and processing properties of the dual-phase titanium alloy, its online detection is necessary and important for product quality control. In this study, samples with different microstructural characteristics were obtained by solution treated from 920 °C to 1000 °C, and the volume fraction of the primary α phase was counted by Image-Pro Plus software. Then, calculate the velocity of ultrasonic longitudinal waves in different samples and time-frequency analysis according to the signals obtained from the laser ultrasonic experiment. Finally, a prediction model of the volume fraction of the primary α phase linearly related to the ultrasonic longitudinal wave velocity was established, and the linear fit has a higher R2 than 0.96. This study can provide a reference for the online detection of phase volume fraction.