We present EngineBench, the first machine learning (ML) oriented database to
use high quality experimental data for the study of turbulent flows inside
combustion machinery. Prior datasets for ML in fluid mechanics are synthetic or
use overly simplistic geometries. EngineBench is comprised of real-world
particle image velocimetry (PIV) data that captures the turbulent airflow
patterns in a specially-designed optical engine. However, in PIV data from
internal flows, such as from engines, it is often challenging to achieve a full
field of view and large occlusions can be present. In order to design optimal
combustion systems, insight into the turbulent flows in these obscured areas is
needed, which can be provided via inpainting models. Here we propose a novel
inpainting task using random edge gaps, a technique that emphasises realism by
introducing occlusions at random sizes and orientations at the edges of the PIV
images. We test five ML methods on random edge gaps using pixel-wise,
vector-based, and multi-scale performance metrics. We find that UNet-based
models are more accurate than the industry-norm non-parametric approach and the
context encoder at this task on both small and large gap sizes. The dataset and
inpainting task presented in this paper support the development of more
general-purpose pre-trained ML models for engine design problems. The method
comparisons allow for more informed selection of ML models for problems in
experimental flow diagnostics. All data and code are publicly available at
this https URL

我们提出了 EngineBench，这是第一个以高质量实验数据为基础的机器学习（ML）导向数据库，用于研究燃烧机械内的湍流流动。通过使用实际世界的粒子图像测速（PIV）数据，EngineBench 捕捉了特殊设计的光学发动机中的湍流气流模式。我们还提出了一种新颖的修复任务，使用随机边缘缺口的修复技术来突出 PIV 图像边缘处的遮挡。我们发现 UNet 模型在这一任务上比行业常用的非参数方法和上下文编码器更准确。本文章提供的数据集和修复任务支持开发更通用的预训练 ML 模型用于发动机设计问题，并允许更明智地选择实验流动诊断问题的 ML 模型。所有数据和代码都可以在给定的链接地址公开获取。

EngineBench: 透明燃烧室中的流动重建 III 光学发动机

EngineBench: Flow Reconstruction in the Transparent Combustion Chamber  III Optical Engine

In this study, a deep learning based conditional density estimation technique
known as conditional variational auto-encoder (CVAE) is used to fill gaps
typically observed in particle image velocimetry (PIV) measurements in
combustion systems. The proposed CVAE technique is trained using time resolved
gappy PIV fields, typically observed in industrially relevant combustors.
Stereo-PIV (SPIV) data from a swirl combustor with very a high vector yield is
used to showcase the accuracy of the proposed CVAE technique. Various error
metrics evaluated on the reconstructed velocity field in the gaps are presented
from data sets corresponding to three sets of combustor operating conditions.
In addition to accurate data reproduction, the proposed CVAE technique offers
data compression by reducing the latent space dimension, enabling the efficient
processing of large-scale PIV data.

使用基于深度学习的条件变分自编码器 (CVAE) 技术填补燃烧系统中常见的粒子图像测速 (PIV) 测量中的空白，通过时间分辨率的可观测商业相关燃烧器中的缺失 PIV 场进行训练，通过对三组燃烧器操作条件数据集的重建速度场评估不同误差指标来展示该技术的准确性，除了精确的数据重建，该方法还通过减少潜在空间维度实现数据压缩，实现对大规模 PIV 数据的高效处理。