arXiv subjects

Jean-Charles de Hemptinne

Publications and source records attributed to Jean-Charles de Hemptinne.

3 recordsLinked to original sources

arXiv2024

Real-fluid simulation of ammonia cavitation in a heavy-duty fuel injector

The reduction of greenhouse gases (GHG) emitted into the earth's atmosphere, such as carbon dioxide, has obviously become a priority. Replacing fossil fuels with cleaner renewable fuels (such as ammonia) in internal combustion engines for heavy-duty vehicles is one promising solution to reduce GHG emissions. This paper aims to study the cavitation formation in a heavy-duty injector using ammonia as fuel. The simulation is carried out using a fully compressible two-phase multi-component real-fluid model (RFM) developed in the CONVERGE CFD solver. In the RFM model, the thermodynamic and transport properties are stored in a table which is used during the run-time. The thermodynamic table is generated using the in-house Carnot thermodynamic library based on vapor-liquid equilibrium calculations coupled with a real-fluid equation of state. The RFM model allows to consider the effects of the dissolved non-condensable gas such as nitrogen on the phase change process. The obtained numerical results have confirmed that the model can tackle the phase transition phenomenon under the considered conditions. In contrast to previous numerical studies of the cavitation phenomenon using hydrocarbon fuels, the formed cavitation pockets were found to be primarily composed of ammonia vapor due to its high vapor pressure, with minimal contribution of the dissolved non-condensable nitrogen.

physics.flu-dyn↗

arXiv2023

HMOE: Hypernetwork-based Mixture of Experts for Domain Generalization

Due to domain shifts, machine learning systems typically struggle to generalize well to new domains that differ from those of training data, which is what domain generalization (DG) aims to address. Although a variety of DG methods have been proposed, most of them fall short in interpretability and require domain labels, which are not available in many real-world scenarios. This paper presents a novel DG method, called HMOE: Hypernetwork-based Mixture of Experts (MoE), which does not rely on domain labels and is more interpretable. MoE proves effective in identifying heterogeneous patterns in data. For the DG problem, heterogeneity arises exactly from domain shifts. HMOE employs hypernetworks taking vectors as input to generate the weights of experts, which promotes knowledge sharing among experts and enables the exploration of their similarities in a low-dimensional vector space. We benchmark HMOE against other DG methods under a fair evaluation framework -- DomainBed. Our extensive experiments show that HMOE can effectively separate mixed-domain data into distinct clusters that are surprisingly more consistent with human intuition than original domain labels. Using self-learned domain information, HMOE achieves state-of-the-art results on most datasets and significantly surpasses other DG methods in average accuracy across all datasets.

cs.LG↗

arXiv2022

PTFlash : A deep learning framework for isothermal two-phase equilibrium calculations

Phase equilibrium calculations are an essential part of numerical simulations of multi-component multi-phase flow in porous media, accounting for the largest share of the computational time. In this work, we introduce a GPUenabled, fast, and parallel framework, PTFlash, that vectorizes algorithms required for isothermal two-phase flash calculations using PyTorch, and can facilitate a wide range of downstream applications. In addition, to further accelerate PTFlash, we design two task-specific neural networks, one for predicting the stability of given mixtures and the other for providing estimates of the distribution coefficients, which are trained offline and help shorten computation time by sidestepping stability analysis and reducing the number of iterations to reach convergence. The evaluation of PTFlash was conducted on three case studies involving hydrocarbons, CO 2 and N 2 , for which the phase equilibrium was tested over a large range of temperature, pressure and composition conditions, using the Soave-Redlich-Kwong (SRK) equation of state. We compare PTFlash with an in-house thermodynamic library, Carnot, written in C++ and performing flash calculations one by one on CPU. Results show speed-ups on large scale calculations up to two order of magnitudes, while maintaining perfect precision with the reference solution provided by Carnot.

physics.chem-ph↗