400 results found
Kumar P, Zavala-Reyes JC, Kalaiarasan G, et al., 2023, Characteristics of fine and ultrafine aerosols in the London underground., Science of the Total Environment, Vol: 858, ISSN: 0048-9697
Underground railway systems are recognised spaces of increased personal pollution exposure. We studied the number-size distribution and physico-chemical characteristics of ultrafine (PM0.1), fine (PM0.1-2.5) and coarse (PM2.5-10) particles collected on a London underground platform. Particle number concentrations gradually increased throughout the day, with a maximum concentration between 18:00 h and 21:00 h (local time). There was a maximum decrease in mass for the PM2.5, PM2.5-10 and black carbon of 3.9, 4.5 and ~ 21-times, respectively, between operable (OpHrs) and non-operable (N-OpHrs) hours. Average PM10 (52 μg m-3) and PM2.5 (34 μg m-3) concentrations over the full data showed levels above the World Health Organization Air Quality Guidelines. Respiratory deposition doses of particle number and mass concentrations were calculated and found to be two- and four-times higher during OpHrs compared with N-OpHrs, reflecting events such as train arrival/departure during OpHrs. Organic compounds were composed of aromatic hydrocarbons and polycyclic aromatic hydrocarbons (PAHs) which are known to be harmful to health. Specific ratios of PAHs were identified for underground transport that may reflect an interaction between PAHs and fine particles. Scanning transmission electron microscopy (STEM) chemical maps of fine and ultrafine fractions show they are composed of Fe and O in the form of magnetite and nanosized mixtures of metals including Cr, Al, Ni and Mn. These findings, and the low air change rate (0.17 to 0.46 h-1), highlight the need to improve the ventilation conditions.
Wu P, Qiu F, Feng W, et al., 2022, <b>A non-intrusive reduced order model with Transformer neural network </b><b>and its application</b>, Physics of Fluids, ISSN: 1070-6631
<jats:p> In this paper, a novel method to construct non-intrusive reduced order model (ROM) is proposed. The method is based on proper orthogonal decomposition and Transformer neural network. Proper orthogonal decomposition is used to generate the basis functions of the low-dimensional flow field, and the coefficients are taken as low-dimensional flow field features. Transformer network is used to extract temporal feature relationships from low-dimensional features. Compared with Recurrent Neural Network and Convolutional Neural Network, Transformer network can better capture flow dynamics. At online stage, the input temporal flow sequences are calculated in parallel, and can effectively reduce online calculation time. The model proposed in this paper has been verified in two scenarios: two-dimensional flow past a cylinder and two-dimensional flow past a building group. Experimental results show that our model can better capture the flowing change details and has higher accuracy. Compared with the ROM based on Long Short Term Memory and Temporal Convolutional Network, the prediction error is reduced by 35% and 60%, and the time cost is reduced by 65% and 60%. Finally, we apply the ROMs to a practical three-dimensional complicated scenario, flow past London South Bank University, and discuss future development of ROMs. </jats:p>
Xiang J, Chen B, Latham JP, et al., 2022, Numerical simulation of rock erosion performance of a high-speed water jet using an immersed-body method, ISSN: 1365-1609
Water jet drilling (WJD) is an effective technique for drilling micro-holes in the subsurface for reservoir stimulation. This study aims to investigate numerically the failure mechanism of rock during WJD and to assess the WJD performance before drilling. A 3D fluid-solid coupling model is developed for simulating WJD by coupling a mechanical solver based on the combined finite-discrete element method (FDEM) with a fluid solver using an immersed-body method. The new numerical model is capable of simulating crack initiation and propagation and fragment removal under the impact load of a high-speed water jet. The poroelastic effect is implemented via Biot's theory of poroelasticity. The numerical results show that: (1) rock failure is only observed in the Gildehaus sandstone with the lowest strengths among the three types of rock tested, (2) most of the cracks are tensile failures and pure shear cracks are rare, mixed mode cracks account for 15%∼40% of the total crack number depending on the mechanical boundary conditions, (3) increased water back pressure significantly suppresses jet erosion. The poroelastic effect on the rock failure is insignificant in the mesoscale simulations and will be further investigated using a microscale model in future.
Phillips T, Heaney CE, Benmoufok E, et al., 2022, Multi-Output Regression with Generative Adversarial Networks (MOR-GANs), Applied Sciences, Vol: 12, Pages: 1-24, ISSN: 2076-3417
Regression modelling has always been a key process in unlocking the relationships betweenindependent and dependent variables that are held within data. In recent years, machine learninghas uncovered new insights in many fields, providing predictions to previously unsolved problems.Generative Adversarial Networks (GANs) have been widely applied to image processing producinggood results, however, these methods have not often been applied to non-image data. Seeing thepowerful generative capabilities of the GANs, we explore their use, here, as a regression method. Inparticular, we explore the use of the Wasserstein GAN (WGAN) as a multi-output regression method.The resulting method we call Multi-Output Regression GANs (MOR-GANs) and its performanceis compared to a Gaussian Process Regression method (GPR) - a commonly used non-parametricregression method that has been well tested on small datasets with noisy responses. The WGANregression model performs well for all types of datasets and exhibits substantial improvements overthe performance of the GPR for certain types of datasets, demonstrating the flexibility of the GAN asa model for regression.
Woodward H, Schroeder A, Le Cornec C, et al., 2022, High resolution modelling of traffic emissions using the large eddy simulation code Fluidity, Atmosphere, Vol: 13, ISSN: 2073-4433
The large eddy simulation (LES) code Fluidity was used to simulate the dispersion of NOx traffic emissions along a road in London. The traffic emissions were represented by moving volume sources, one for each vehicle, with time-varying emission rates. Traffic modelling software was used to generate the vehicle movement, while an instantaneous emissions model was used to calculate the NOx emissions at 1 s intervals. The traffic emissions were also modelled as a constant volume source along the length of the road for comparison. A validation of Fluidity against wind tunnel measurements is presented before a qualitative comparison of the LES concentrations with measured roadside concentrations. Fluidity showed an acceptable comparison with the wind tunnel data for velocities and turbulence intensities. The in-canyon tracer concentrations were found to be significantly different between the wind tunnel and Fluidity. This difference was explained by the very high sensitivity of the in-canyon tracer concentrations to the precise release location. Despite this, the comparison showed that Fluidity was able to provide a realistic representation of roadside concentration variations at high temporal resolution, which is not achieved when traffic emissions are modelled as a constant volume source or by Gaussian plume models.
Heaney C, Liu X, Go H, et al., 2022, Extending the capabilities of data-driven reduced-order models to make predictions for unseen scenarios: applied to flow around buildings, Frontiers in Physics, Vol: 10, Pages: 1-16, ISSN: 2296-424X
We present a data-driven or non-intrusive reduced-order model (NIROM) which is capable of making predictions for a significantly larger domain than the one used to generate the snapshots or training data. This development relies on the combination of a novel way of sampling the training data (which frees the NIROM from its dependency on the original problem domain) and a domain decomposition approach (which partitions unseen geometries in a manner consistent with the sub-sampling approach). The method extends current capabilities of reduced-order models to generalise, i.e., to make predictions for unseen scenarios. The method is applied to a 2D test case which simulates the chaotic time-dependent flow of air past buildings at a moderate Reynolds number using a computational fluid dynamics (CFD) code. The procedure for 3D problems is similar, however, a 2D test case is considered sufficient here, as a proof-of-concept. The reduced-order model consists of a sampling technique to obtain the snapshots; a convolutional autoencoder for dimensionality reduction; an adversarial network for prediction; all set within a domain decomposition framework. The autoencoder is chosen for dimensionality reduction as it has been demonstrated in the literature that these networks cancompress information more efficiently than traditional (linear) approaches based on singular value decomposition. In order to keep the predictions realistic, properties of adversarial networks are exploited. To demonstrate its ability to generalise, once trained, the method is applied to a larger domain which has a different arrangement of buildings. Statistical properties of the flows from the reduced order model are compared with those from the CFD model in order to establish how realistic the predictions are.
Buchan AG, Cacuci DG, Dargaville S, et al., 2022, Optimised Adjoint Sensitivity Analysis Using Adjoint Guided Mesh Adaptivity Applied to Neutron Detector Response Calculations, ENERGIES, Vol: 15
Hamzehloo A, Bahlali ML, Salinas P, et al., 2022, Modelling saline intrusion using dynamic mesh optimization with parallel processing, ADVANCES IN WATER RESOURCES, Vol: 164, ISSN: 0309-1708
Heaney CE, Wolffs Z, Tómasson JA, et al., 2022, An AI-based non-intrusive reduced-order model for extended domains applied to multiphase flow in pipes, Physics of Fluids, Vol: 34, Pages: 1-22, ISSN: 1070-6631
The modeling of multiphase flow in a pipe presents a significant challenge for high-resolution computational fluid dynamics (CFD) models due to the high aspect ratio (length over diameter) of the domain. In subsea applications, the pipe length can be several hundreds of meters vs a pipe diameter of just a few inches. Approximating CFD models in a low-dimensional space, reduced-order models have been shown to produce accurate results with a speed-up of orders of magnitude. In this paper, we present a new AI-based non-intrusive reduced-order model within a domain decomposition framework (AI-DDNIROM), which is capable of making predictions for domains significantly larger than the domain used in training. This is achieved by (i) using a domain decomposition approach; (ii) using dimensionality reduction to obtain a low-dimensional space in which to approximate the CFD model; (iii) training a neural network to make predictions for a single subdomain; and (iv) using an iteration-by-subdomain technique to converge the solution over the whole domain. To find the low-dimensional space, we compare Proper Orthogonal Decomposition with several types of autoencoder networks, known for their ability to compress information accurately and compactly. The comparison is assessed with two advection-dominated problems: flow past a cylinder and slug flow in a pipe. To make predictions in time, we exploit an adversarial network, which aims to learn the distribution of the training data, in addition to learning the mapping between particular inputs and outputs. This type of network has shown the potential to produce visually realistic outputs. The whole framework is applied to multiphase slug flow in a horizontal pipe for which an AI-DDNIROM is trained on high-fidelity CFD simulations of a pipe of length 10 m with an aspect ratio of 13:1 and tested by simulating the flow for a pipe of length 98 m with an aspect ratio of almost 130:1. Inspection of the predicted liquid volume
Wu P, Pan K, Ji L, et al., 2022, Navier-stokes Generative Adversarial Network: a physics-informed deep learning model for fluid flow generation, NEURAL COMPUTING & APPLICATIONS, Vol: 34, Pages: 11539-11552, ISSN: 0941-0643
Cheng M, Fang F, Navon IM, et al., 2022, Spatio-Temporal Hourly and Daily Ozone Forecasting in China Using a Hybrid Machine Learning Model: Autoencoder and Generative Adversarial Networks, JOURNAL OF ADVANCES IN MODELING EARTH SYSTEMS, Vol: 14
Arcucci R, Casas CQ, Joshi A, et al., 2022, Merging Real Images with Physics Simulations via Data Assimilation, 27th International European Conference on Parallel and Distributed Computing (Euro-Par), Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 255-266, ISSN: 0302-9743
Jolaade M, Silva VLS, Heaney CE, et al., 2022, Generative Networks Applied to Model Fluid Flows, 22nd Annual International Conference on Computational Science (ICCS), Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 742-755, ISSN: 0302-9743
Silva VLS, Salinas P, Jackson MD, et al., 2021, Machine learning acceleration for nonlinear solvers applied to multiphase porous media flow, Computer Methods in Applied Mechanics and Engineering, Vol: 384, Pages: 1-17, ISSN: 0045-7825
A machine learning approach to accelerate convergence of the nonlinear solver in multiphase flow problems is presented here. The approach dynamically controls an acceleration method based on numerical relaxation. It is demonstrated in a Picard iterative solver but is applicable to other types of nonlinear solvers. The aim of the machine learning acceleration is to reduce the computational cost of the nonlinear solver by adjusting to the complexity/physics of the system. Using dimensionless parameters to train and control the machine learning enables the use of a simple two-dimensional layered reservoir for training, while also exploring a wide range of the parameter space. Hence, the training process is simplified and it does not need to be rerun when the machine learning acceleration is applied to other reservoir models. We show that the method can significantly reduce the number of nonlinear iterations without compromising the simulation results, including models that are considerably more complex than the training case.
Obeysekara A, Salinas P, Heaney CE, et al., 2021, Prediction of multiphase flows with sharp interfaces using anisotropic mesh optimisation, Advances in Engineering Software, Vol: 160, Pages: 1-16, ISSN: 0965-9978
We propose an integrated, parallelised modelling approach to solve complex multiphase flow problems with sharp interfaces. This approach is based on a finite-element, double control-volume methodology, and employs highly-anisotropic mesh optimisation within a framework of high-order numerical methods and algorithms, which include adaptive time-stepping, metric advection, flux limiting, compressive advection of interfaces, multi-grid solvers and preconditioners. Each method is integral to increasing the fidelity of representing the underlying physics while maximising computational efficiency, and, only in combination, do these methods result in the accurate, reliable, and efficient simulation of complex multiphase flows and associated regime transitions. These methods are applied simultaneously for the first time in this paper, although some of the individual methods have been presented previously. We validate our numerical predictions against standard benchmark results from the literature and demonstrate capabilities of our modelling framework through the simulation of laminar and turbulent two-phase pipe flows. These complex interfacial flows involve the creation of bubbles and slugs, which involve multi-scale physics and arise due to a delicate interplay amongst inertia, viscous, gravitational, and capillary forces. We also comment on the potential use of our integrated approach to simulate large, industrial-scale multiphase pipe flow problems that feature complex topological transitions.
Titus Z, Heaney C, Jacquemyn C, et al., 2021, Conditioning surface-based geological models to well data using artificial neural networks, Computational Geosciences: modeling, simulation and data analysis, Vol: 26, Pages: 779-802, ISSN: 1420-0597
Surface-based modelling provides a computationally efficient approach for generating geometrically realistic representations of heterogeneity in reservoir models. However, conditioning Surface-Based Geological Models (SBGMs) to well data can be challenging because it is an ill-posed inverse problem with spatially distributed parameters. To aid fast and efficient conditioning, we use here SBGMs that model geometries using parametric, grid-free surfaces that require few parameters to represent even realistic geological architectures. A neural network is trained to learn the underlying process of generating SBGMs by learning the relationship between the parametrized SBGM inputs and the resulting facies identified at well locations. To condition the SBGM to these observed data, inverse modelling of the SBGM inputs is achieved by replacing the forward model with the pre-trained neural network and optimizing the network inputs using the back-propagation technique applied in training the neural network. An analysis of the uncertainties associated with the conditioned realisations demonstrates the applicability of the approach for evaluating spatial variations in geological heterogeneity away from control data in reservoir modelling. This approach for generating geologically plausible models that are calibrated with observed well data could also be extended to other geological modelling techniques such as object- and process-based modelling.
Phillips TRF, Heaney CE, Smith PN, et al., 2021, An autoencoder‐based reduced‐order model for eigenvalue problems with application to neutron diffusion, International Journal for Numerical Methods in Engineering, Vol: 122, Pages: 3780-3811, ISSN: 0029-5981
Using an autoencoder for dimensionality reduction, this article presents a novel projection‐based reduced‐order model for eigenvalue problems. Reduced‐order modeling relies on finding suitable basis functions which define a low‐dimensional space in which a high‐dimensional system is approximated. Proper orthogonal decomposition (POD) and singular value decomposition (SVD) are often used for this purpose and yield an optimal linear subspace. Autoencoders provide a nonlinear alternative to POD/SVD, that may capture, more efficiently, features or patterns in the high‐fidelity model results. Reduced‐order models based on an autoencoder and a novel hybrid SVD‐autoencoder are developed. These methods are compared with the standard POD‐Galerkin approach and are applied to two test cases taken from the field of nuclear reactor physics.
Salinas P, Regnier G, Jacquemyn C, et al., 2021, Dynamic mesh optimisation for geothermal reservoir modelling, Geothermics, Vol: 94, Pages: 1-13, ISSN: 0375-6505
Modelling geothermal reservoirs is challenging due to the large domain and wide range of length- and time-scales of interest. Attempting to represent all scales using a fixed computational mesh can be very computationally expensive. Application of dynamic mesh optimisation in other fields of computational fluid dynamics has revolutionised the accuracy and cost of numerical simulations. Here we present a new approach for modelling geothermal reservoirs based on unstructured meshes with dynamic mesh optimisation. The resolution of the mesh varies during a simulation, to minimize an error metric for solution fields of interest such as temperature and pressure. Efficient application of dynamic mesh optimisation in complex subsurface reservoirs requires a new approach to represent geologic heterogeneity and we use parametric spline surfaces to represent key geological features such as faults and lithology boundaries. The resulting 3D surface-based models are mesh free; a mesh is created only when required for numerical computations. Dynamic mesh optimisation preserves the surfaces and hence geologic heterogeneity. The governing equations are discretised using a double control volume finite element method that ensures heat and mass are conserved and provides robust solutions on distorted meshes. We apply the new method to a series of test cases that model sedimentary geothermal reservoirs. We demonstrate that dynamic mesh optimisation yields significant performance gains, reducing run times by up to 8 times whilst capturing flow and heat transport with the same accuracy as fixed meshes.
Wu P, Gong S, Pan K, et al., 2021, Reduced order model using convolutional auto-encoder with self-attention, PHYSICS OF FLUIDS, Vol: 33, ISSN: 1070-6631
Cheng M, Fang F, Navon IM, et al., 2021, A real-time flow forecasting with deep convolutional generative adversarial network: Application to flooding event in Denmark, PHYSICS OF FLUIDS, Vol: 33, ISSN: 1070-6631
Zheng J, Wu X, Fang F, et al., 2021, Numerical study of COVID-19 spatial-temporal spreading in London, PHYSICS OF FLUIDS, Vol: 33, ISSN: 1070-6631
Tajnafoi G, Arcucci R, Mottet L, et al., 2021, Variational Gaussian process for optimal sensor placement, Applications of Mathematics, Vol: 66, Pages: 287-317, ISSN: 0373-6725
Sensor placement is an optimisation problem that has recently gained great relevance. In order to achieve accurate online updates of a predictive model, sensors are used to provide observations. When sensor location is optimally selected, the predictive model can greatly reduce its internal errors. A greedy-selection algorithm is used for locating these optimal spatial locations from a numerical embedded space. A novel architecture for solving this big data problem is proposed, relying on a variational Gaussian process. The generalisation of the model is further improved via the preconditioning of its inputs: Masked Autoregressive Flows are implemented to learn nonlinear, invertible transformations of the conditionally modelled spatial features. Finally, a global optimisation strategy extending the Mutual Information-based optimisation and fine-tuning of the selected optimal location is proposed. The methodology is parallelised to speed up the computational time, making these tools very fast despite the high complexity associated with both spatial modelling and placement tasks. The model is applied to a real three-dimensional test case considering a room within the Clarence Centre building located in Elephant and Castle, London, UK.
Lyu Z, Lei Q, Yang L, et al., 2021, A novel approach to optimising well trajectory in heterogeneous reservoirs based on the fast-marching method, Journal of Natural Gas Science and Engineering, Vol: 88, Pages: 1-12, ISSN: 1875-5100
To achieve efficient recovery of subsurface energy resources, a suitable trajectory needs to be identified for the production well. In this study, a new approach is presented for automated identification of optimum well trajectories in heterogeneous oil/gas reservoirs. The optimisation procedures are as follows. First, a productivity potential map is generated based on the site characterisation data of a reservoir (when available). Second, based on the fast-marching method, well paths are generated from a number of entrance positions to a number of exit points at opposite sides of the reservoir. The well trajectory is also locally constrained by a prescribed maximum curvature to ensure that the well trajectory is drillable. Finally, the optimum well trajectory is selected from all the candidate paths based on the calculation of a benefit-to-cost ratio. If required, a straight directional well path, may also be derived through a linear approximation to the optimised non-linear trajectory by least squares analysis. Model performance has been demonstrated in both 2D and 3D. In the 2D example, the benefit-to-cost ratio of the optimised well is much higher than that of a straight well; in the 3D example, laterals of various curvatures are generated. The applicability of the method is tested by exploring different reservoir heterogeneities and curvature constraints. This approach can be applied to determine the entrance/exit positions and the well path for subsurface energy system development, which is useful for field applications.
Burridge HC, Bhagat RK, Stettler MEJ, et al., 2021, The ventilation of buildings and other mitigating measures for COVID-19: a focus on wintertime, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol: 477, Pages: 1-31, ISSN: 1364-5021
The year 2020 has seen the emergence of a global pandemic as a result of the disease COVID-19. This report reviews knowledge of the transmission of COVID-19 indoors, examines the evidence for mitigating measures, and considers the implications for wintertime with a focus on ventilation.
Phillips T, Heaney C, Tollit B, et al., 2021, Reduced-order modelling with domain decomposition applied to multi-group neutron transport, Energies, Vol: 14, ISSN: 1996-1073
Solving the neutron transport equations is a demanding computational challenge. This paper combines reduced-order modelling with domain decomposition to develop an approach that can tackle such problems. The idea is to decompose the domain of a reactor, form basis functions locally in each sub-domain and construct a reduced-order model from this. Several different ways of constructing the basis functions for local sub-domains are proposed, and a comparison is given with a reduced-order model that is formed globally. A relatively simple one-dimensional slab reactor provides a test case with which to investigate the capabilities of the proposed methods. The results show that domain decomposition reduced-order model methods perform comparably with the global reduced-order model when the total number of reduced variables in the system is the same with the potential for the offline computational cost to be significantly less expensive.
Heaney CE, Buchan AG, Pain CC, et al., 2021, Reduced-order modelling applied to the multigroup neutron diffusion equation using a nonlinear interpolation method for control-rod movement, Energies, ISSN: 1996-1073
Kumar P, Kalaiarasan G, Porter AE, et al., 2021, An overview of methods of fine and ultrafine particle collection for physicochemical characterisation and toxicity assessments., Science of the Total Environment, Vol: 756, Pages: 1-22, ISSN: 0048-9697
Particulate matter (PM) is a crucial health risk factor for respiratory and cardiovascular diseases. The smaller size fractions, ≤2.5 μm (PM2.5; fine particles) and ≤0.1 μm (PM0.1; ultrafine particles), show the highest bioactivity but acquiring sufficient mass for in vitro and in vivo toxicological studies is challenging. We review the suitability of available instrumentation to collect the PM mass required for these assessments. Five different microenvironments representing the diverse exposure conditions in urban environments are considered in order to establish the typical PM concentrations present. The highest concentrations of PM2.5 and PM0.1 were found near traffic (i.e. roadsides and traffic intersections), followed by indoor environments, parks and behind roadside vegetation. We identify key factors to consider when selecting sampling instrumentation. These include PM concentration on-site (low concentrations increase sampling time), nature of sampling sites (e.g. indoors; noise and space will be an issue), equipment handling and power supply. Physicochemical characterisation requires micro- to milli-gram quantities of PM and it may increase according to the processing methods (e.g. digestion or sonication). Toxicological assessments of PM involve numerous mechanisms (e.g. inflammatory processes and oxidative stress) requiring significant amounts of PM to obtain accurate results. Optimising air sampling techniques are therefore important for the appropriate collection medium/filter which have innate physical properties and the potential to interact with samples. An evaluation of methods and instrumentation used for airborne virus collection concludes that samplers operating cyclone sampling techniques (using centrifugal forces) are effective in collecting airborne viruses. We highlight that predictive modelling can help to identify pollution hotspots in an urban environment for the efficient collection of PM mass. This review provides
Quilodrán-Casas C, Silva VS, Arcucci R, et al., 2021, Digital twins based on bidirectional LSTM and GAN for modelling COVID-19
The outbreak of the coronavirus disease 2019 (COVID-19) has now spreadthroughout the globe infecting over 100 million people and causing the death ofover 2.2 million people. Thus, there is an urgent need to study the dynamics ofepidemiological models to gain a better understanding of how such diseasesspread. While epidemiological models can be computationally expensive, recentadvances in machine learning techniques have given rise to neural networks withthe ability to learn and predict complex dynamics at reduced computationalcosts. Here we introduce two digital twins of a SEIRS model applied to anidealised town. The SEIRS model has been modified to take account of spatialvariation and, where possible, the model parameters are based on official virusspreading data from the UK. We compare predictions from a data-correctedBidirectional Long Short-Term Memory network and a predictive GenerativeAdversarial Network. The predictions given by these two frameworks are accuratewhen compared to the original SEIRS model data. Additionally, these frameworksare data-agnostic and could be applied to towns, idealised or real, in the UKor in other countries. Also, more compartments could be included in the SEIRSmodel, in order to study more realistic epidemiological behaviour.
Amendola M, Arcucci R, Mottet L, et al., 2021, Data Assimilation in the Latent Space of a Convolutional Autoencoder, Pages: 373-386, ISSN: 0302-9743
Data Assimilation (DA) is a Bayesian inference that combines the state of a dynamical system with real data collected by instruments at a given time. The goal of DA is to improve the accuracy of the dynamic system making its result as real as possible. One of the most popular technique for DA is the Kalman Filter (KF). When the dynamic system refers to a real world application, the representation of the state of a physical system usually leads to a big data problem. For these problems, KF results computationally too expensive and mandates to use of reduced order modeling techniques. In this paper we proposed a new methodology we called Latent Assimilation (LA). It consists in performing the KF in the latent space obtained by an Autoencoder with non-linear encoder functions and non-linear decoder functions. In the latent space, the dynamic system is represented by a surrogate model built by a Recurrent Neural Network. In particular, an Long Short Term Memory (LSTM) network is used to train a function which emulates the dynamic system in the latent space. The data from the dynamic model and the real data coming from the instruments are both processed through the Autoencoder. We apply the methodology to a real test case and we show that the LA has a good performance both in accuracy and in efficiency.
Padrino JC, Srinil N, Kurushina V, et al., 2021, A One-Dimensional Mechanistic Model For Tracking Unsteady Slug Flow
A novel one-dimensional slug tracking mechanistic model for unsteady, upward gas-liquid slug flow in inclined pipes is presented. The model stems from the first principles of mass and momentum conservation applied to a slug unit cell consisting of a slug body of liquid and a region of stratified flow containing an elongated bubble and a liquid film. The slug body front and rear are treated as surfaces of discontinuity where mass and momentum balances or "jump laws"are prescribed. The former is commonly applied in mechanistic models for slug flow, whereas the latter is typically overlooked, thereby leading to the assumption of a continuous pressure profile at these points or to the adoption of a pressure drop due to the fluid acceleration on a heuristic basis. Our analysis shows that this pressure change arises formally from the momentum jump law at the slug body front. The flow is assumed to be isothermal, the gas is compressible, the pressure drop in the elongated bubble region is accounted for, the film thickness is considered uniform, and weight effects in the pressure from the interface level are included. Besides specifying momentum jump laws at both borders of the slug body, another novel feature of the present model is that we avoid adopting the quasi-steady approximation for the elongated bubble-liquid film region, and thus the unsteady terms in the mass and momentum balances are kept. The present model requires empirical correlations for the slug body length and the elongated bubble nose velocity. The non-linear equations are discretized and solved simultaneously for all the slug unit cells filling the pipe. Timespace variation of the slug body and film lengths, liquid holdup and void fraction, and pressures, among other quantities, can be predicted, and model performance is evaluated by comparing with data in the literature.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.