Machine Learning and transcritical sprays: A demonstration study of their potential in ECN Spray-A

Abstract

The present work investigates the application of Machine Learning and Artificial Neural Networks for tackling the complex issue of transcritical sprays, which are relevant to modern compression-ignition engines. Such conditions imply the departure of the classical thermodynamic perspective of ideal gas or incompressible liquid, necessitating the use of costly and elaborate thermodynamic closures to describe property variation and simulation methods. Machine Learning can assist in several ways in speeding up such calculations, either as a compact, trained thermodynamic model that can be coupled to the flow solver, or as a surrogate predictive tool of spray characteristics. In this work, such applications are demonstrated and their performance is assessed against more traditional approaches. Such applications involve the prediction of macroscopic spray characteristics, for example, the spray penetration over time, or the spray distribution in space and time, and predictions of fluid properties for the thermodynamic states encountered in such applications. Macroscopic characteristics can be adequately predicted by relatively simple network structures, involving just a hidden layer of 3–4 neurons, whereas prediction of thermodynamic states requires several layers of 5–20 neurons each. The results of integrating Artificial Neural Networks in transcritical sprays are rather promising; prediction of thermodynamic properties at pressures greater than 1bar has effectively zero error, yielding simulations indistinguishable from standard tabulated approaches with minimal overhead. When used as a regression method for time-histories either of spray characteristics or spray distributions, the results are within experimental uncertainty of similar experiments, not included in the training dataset.

Computation of Real-Fluid Thermophysical Properties Using a Neural Network Approach Implemented in OpenFOAM

“…In contrast, NNs have emerged as a remarkably efficient technique for classification and response prediction. In high-pressure, high-temperature conditions, NN methods are used to predict thermodynamic properties [18], and the tabulation method offers high-precision calculation results in a wide temperature and pressure range [16,17]. ML techniques are rapidly advancing in this era of big data, and there is high potential in exploring the combination between ML and combustion research and achieving remarkable results.…”

“…R. Maulik et al demonstrate the deployment of a deep neural network for compressing flow-field information using an autoencoder to demonstrate the ability to use state-of-the-art ML tools in the Python ecosystem [20,21]. In the realm of fluid mechanics, NNs are currently being explored as a complementary tool of CFD to expedite design processes [18]. Recent comprehensive reviews have highlighted various applications in fluid mechanics, encompassing flow feature extraction, turbulence modeling, optimization, and flow control [19].…”

Modeling and LES of high-pressure liquid injection under evaporating and non-evaporating conditions by a real fluid model and surface density approach

“…However, the storage memory requirements for the tables may become an issue as the table dimensions are extended for multi-species systems. Recently, other alternatives to the tabulation approach have also been proposed, such as using artificial neural network (ANN) as a regression model for the thermodynamic properties [42] or an in situ adaptive tabulation (ISAT) approach [82]. However, these approaches are still under investigation, and their efficiency for multi-component problems is not yet evaluated.…”

Numerical investigation of droplet evaporation in high-pressure dual-fuel conditions using a tabulated real-fluid model

“…Zhang and Yang [61] employed an in situ adaptive tabulation (ISAT) approach, where the table is constructed during the CFD simulation. Besides, Koukouvinis et al [33] employed an artificial neural network (ANN) as a regression model for the thermodynamic properties. However, these approaches are still under investigation and their efficiency for multi-component problems is not evaluated.…”