Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 29, 2026

Experimental Methodology for Estimation of Local Heat Fluxes and Burning Rates in Steady Laminar Boundary Layer Diffusion Flames
10:29

Experimental Methodology for Estimation of Local Heat Fluxes and Burning Rates in Steady Laminar Boundary Layer Diffusion Flames

Published on: June 1, 2016

A novel data augmentation method and a data-driven prediction model for surface flashover at gas-solid interfaces

Chuyu Sun1, Haiyang Wang1, Gefei Wang1

  • 1Northwest Institute of Nuclear Technology, Xi'an, China.

Scientific Reports
|May 27, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Flame Photometry: Overview01:02

Flame Photometry: Overview

Flame photometry, also known as flame emission spectrometry, is a technique used for the qualitative and quantitative analysis of elements present in a sample using a flame as the source of excitation energy. The concept of flame photometry was realized in the early 1860s by Kirchhoff and Bunsen, who discovered that specific elements emit characteristic radiation when excited in flames. The first instrument developed for this purpose was used to measure sodium (Na) in plant ash using a Bunsen...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Sustainable Carbonyl Acetalization Enabled by Frustrated Ion-Pair under Mild Conditions.

The Journal of organic chemistry·2026
Same author

Development of a laser-triggered film switch for nanosecond rectangular pulse generator.

The Review of scientific instruments·2020
Same author

Balancing Catalytic Activity and Interface Energetics of Electrocatalyst-Coated Photoanodes for Photoelectrochemical Water Splitting.

ACS applied materials & interfaces·2018
Same author

Antitumor activity of caffeic acid 3,4-dihydroxyphenethyl ester and its pharmacokinetic and metabolic properties.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2013
Same author

Mitochondrial genome sequences of Artemia tibetiana and Artemia urmiana: assessing molecular changes for high plateau adaptation.

Science China. Life sciences·2013
Same author

Do hyperechoic thyroid nodules on B-ultrasound represent calcification?

The Journal of international medical research·2013

This study develops a machine learning model to predict surface flashover in electromagnetic pulse simulators. The Support Vector Machine (SVM) model demonstrated the highest accuracy, improving reliability for critical high-voltage applications.

Area of Science:

  • Electrical Engineering
  • Materials Science
  • Computational Physics

Background:

  • Surface flashover at gas-solid interfaces poses a significant risk to the reliability of electromagnetic pulse (EMP) simulators.
  • Accurate prediction of flashover events is crucial for ensuring the operational integrity of high-voltage equipment.

Purpose of the Study:

  • To develop and evaluate a machine-learning-based classification model for predicting surface flashover events over a wide range of surface distances (15-500 mm).
  • To address challenges of class imbalance in experimental data and ensure the physical consistency of the model's predictions.

Main Methods:

  • Construction of three experimental platforms (±80 kV to ±2000 kV) to collect 1245 data samples under diverse conditions (surface distance, voltage polarity, gas pressure, electrode configuration, voltage waveform).
Keywords:
Data augmentationFeature importance analysisSurface flashoverWeibull distribution

Related Experiment Videos

Last Updated: May 29, 2026

Experimental Methodology for Estimation of Local Heat Fluxes and Burning Rates in Steady Laminar Boundary Layer Diffusion Flames
10:29

Experimental Methodology for Estimation of Local Heat Fluxes and Burning Rates in Steady Laminar Boundary Layer Diffusion Flames

Published on: June 1, 2016

  • Implementation of a data augmentation technique using the three-parameter Weibull distribution to mitigate class imbalance and overfitting.
  • Training and comparison of six machine learning algorithms (SVM, MLP, RF, GB, XGBoost, LightGBM) using Bayesian hyperparameter optimization.

    • Main Results:

    • The Support Vector Machine (SVM) model achieved the highest performance with an F1 score of 0.9111 and an Area Under the Curve (AUC) of 0.9590.
    • Multilayer Perceptron (MLP) demonstrated the second-best performance.
    • Tree-based ensemble methods showed slightly lower F1 scores and a tendency towards overfitting, though feature importance and SHAP analysis confirmed physically consistent mechanisms.

    Conclusions:

    • The developed machine learning model, particularly the SVM approach, offers an effective method for predicting surface flashover in EMP simulators.
    • The proposed data augmentation strategy successfully addresses class imbalance issues.
    • The findings contribute to enhancing the reliability and predictive capabilities of high-voltage systems.