Machine learning for real-time diagnostics of cold atmospheric plasma sources

Dogan Gidon, Xuekai Pei, Angelo D. Bonzanini, David B. Graves, Ali Mesbah

Research output: Contribution to journalArticlepeer-review

38 Scopus citations

Abstract

Real-time diagnostics of cold atmospheric plasma (CAP) sources can be challenging due to the requirement for expensive equipment and complicated analysis. Data analytics that rely on machine learning (ML) methods can help address this challenge. In this paper, we demonstrate the application of several ML methods for real-time diagnosis of CAPs using informationrich optical emission spectra and electro-acoustic emission. We show that data analytics based on ML can provide a simple and effective means for estimation of operation-relevant parameters such as rotational and vibrational temperature and substrate characteristic in real-time. Our findings indicate a great potential promise for ML for real-time diagnostics of CAPs.

Original languageEnglish (US)
Article number8685139
Pages (from-to)597-605
Number of pages9
JournalIEEE Transactions on Radiation and Plasma Medical Sciences
Volume3
Issue number5
DOIs
StatePublished - Sep 2019
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Atomic and Molecular Physics, and Optics
  • Instrumentation
  • Radiology Nuclear Medicine and imaging

Keywords

  • Cold atmospheric plasma (CAP)
  • Electroacoustic signal
  • Gaussian process (GP)
  • K-means clustering
  • Linear regression
  • Machine learning (ML)
  • Optical emission spectrum (OES)
  • Real-time diagnostics

Fingerprint

Dive into the research topics of 'Machine learning for real-time diagnostics of cold atmospheric plasma sources'. Together they form a unique fingerprint.

Cite this