Skip to content
This repository includes the code utilized for real-time diagnostics of plasma devices based on machine learning methods.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.ipynb_checkpoints
Estimation of Separation Distance from Electroacoustic Emission.ipynb
README.md
Substrate discrimination from OES.ipynb
Temperature_Prediction_from_OES.ipynb
dat_test.csv
dat_test_dsep.csv
dat_test_o2.csv
dat_test_pull.csv
dat_train.csv
sounnd_test2.csv
sounnd_train2.csv

README.md

Machine Learning for Real-time Diagnostics of Cold Atmospheric Plasma Soruces

This repository includes the data and the code relating to results presented in the paper. Each Jupyter notebook corresponds to one of the case studies investigated in detail in the paper using the datasets described below.

Datasets

dat_train.csv - optical emission spectra for the N2 second positive transition, fitted rotational and vibrational temperatures and operating conditions (power, flow, substrate type) compiled into comma seperated values file

dat_test.csv - optical emission spectra for the N2 second positive transition, fitted rotational and vibrational temperatures and operating conditions (power, flow, substrate type) compiled into comma seperated values file

dat_test_dsep.csv - optical emission spectra for the N2 second positive transition, fitted rotational and vibrational temperatures and operating conditions (power, flow, substrate type, seperation distance) compiled into comma seperated values file

dat_test_o2.csv - optical emission spectra for the N2 second positive transition, fitted rotational and vibrational temperatures and operating conditions (power, flow, substrate type, additive o2 concentration (%) compiled into comma seperated values file

dat_test_pull.csv - optical emission spectra for the N2 second positive transition, fitted rotational and vibrational temperatures and operating conditions (power, flow, substrate type) recorded as glass substrate pulled from under the APPJ

sounnd_train2.csv - Fast Fourier transform of the electroacustic emission of the plasma flashlight and the measured device-tip-to-substrate seperation distance compiled into comma seperated values file

sounnd_test.csv - Fast Fourier transform of the electroacustic emission of the plasma flashlight and the measured device-tip-to-substrate seperation distance compiled into comma seperated values file

You can’t perform that action at this time.