Refractive index determination of dynamic droplets in a flow by analyzing light scattering signals with a machine learning approach

This container includes the measurement data, python script and weights of trained machine learning model associated with the scientific work, which will be presented in 2025 at the Turbulence, Heat and Mass Transfer 11 conference in Tokyo.

Title: Refractive Index Determination of Dynamic Droplets in Flow by Analyzing Light Scattering Signals with a Machine Learning Approach  Authors: W. SchaeferAffiliation: ai-quanton GmbH, Dr.-Werner-Freyberg-Str. 7, 69514 Laudenbach, Germany  Contact: [e-mail] 

The following data files are provided:

Dataset_40_4ch1234.rar (unpacked: Dataset_40_4ch1234.pth)

M1_SegmentsTHR40.csv

SegmentsTHR40.rar (unpacked: M1_SegmentsTHR40.csv ... M55_SegmentsTHR40.csv)

Model_weights_4ch1234.pth

Dataset_40_4ch1234.pth is a file, containing a ready-to-use dataset of 4-channel signals prepared for use in Python scripts.

M1_SegmentsTHR40.csv is an example of a file used for storing and loading light scattering signals of individual droplets with corresponding additional data. The meaning of each column is:

'MID' – measurement ID

'FID' – frame ID

'SID' – signal ID

'CID' – channel ID

'NOP' – number of parts

'PNM' – part number

'TCH' – trigger channel

'TLE' – trigger level

'TID' – trigger ID

'CON' – label used for training

SegmentsTHR40.rar is an archived folder containing .csv files, the same format as M1_SegmentsTHR40.csv.

Model_weights_4ch1234.pth contains weights for a model trained on data from all 4 channels.

External files:

The correcponding repository to this dataset is published on Azure Dev Ops: https://dev.azure.com/ai-quanton/PBa202This repository contains the Python script developed for a neural network that determines the refractive index of single droplets by analyzing light scattering signals generated as they pass through a Gaussian beam. 

The script is designed to build and test a machine learning model capable of accurately predicting refractive indices from light scattering data in dynamic spray environments.