Prediction of vacuum surface flashover thresholds: comparison of physical, statistical, and machine learning models
- 25 September 2026
- journal article
- Published by IOP Publishing in Journal of Physics D: Applied Physics
- Vol. 59 (38) , 385207
Abstract
Vacuum surface flashover remains a major constraint for a variety of high-voltage vacuum insulation systems. Because flashover is governed by numerous coupled effects of material, geometry, voltage waveform, surface condition, and discharge history, reliable flashover threshold prediction using statistical and physics-based models remains challenging. To address this issue, a first-of-its-kind machine-learning (ML) based framework for vacuum surface flashover is proposed. First, a comprehensive vacuum flashover database is constructed. Six ML models were evaluated on the original dataset, and random forest (RF) and Histogram Gradient Boosting (HGB) demonstrated superior performance to the others. To further increase the prediction accuracy, several data augmentation methods were employed to increase the size of the database. It was found that threefold PureBootstrap performed the best, achieving a column shapes score of 96.10% and a column pair trends score of 97.78%. After augmentation, the dataset containing 902 samples and 19 features was used to further train RF and HGB for flashover threshold prediction. Compared with the J. C. Martin empirical formula and physical model based on the secondary electron emission avalanche, the ML models achieve substantially better prediction performance, with R 2 values of 0.92 for RF and 0.93 for HGB, higher than 0.24 and 0.22 for the J. C. Martin formula and the physical model, respectively. The employed ML models are interpretable, and illustrated that insulation system geometry and applied voltage waveform are among the most critical factors determining the flashover threshold. This work offers novel insights into flashover risk assessment in vacuum insulation design.Keywords
Funding Information
- National Natural Science Foundation of China (52537007)
This publication has 81 references indexed in Scilit:
- Pt decorated core-shell ZnS:Cu doped epoxy composites: Achieving enhanced breakdown strength and defect visualizationChemical Engineering Journal, 2026
- Gradient distribution of trap states in polymer dielectrics induced by electric field for enhanced insulation propertiesChemical Engineering Journal, 2025
- Enhancing few-shot learning using targeted mixupApplied Intelligence, 2025
- Beneficial role of manganese dioxide for reducing surface resistivity to increase surface flashover voltage of vacuum insulating ceramicsCeramics International, 2024
- Intelligent prediction of 110kV insulator lightning flashover criteria based on random forestElectric Power Systems Research, 2024
- Tapinarof validates the aryl hydrocarbon receptor as a therapeutic target: A clinical reviewJournal of Allergy and Clinical Immunology, 2023
- Deep attention SMOTE: Data augmentation with a learnable interpolation factor for imbalanced anomaly detection of gas turbinesComputers in Industry, 2023
- Flashover voltage and time prediction of polluted silicone rubber insulator based on artificial neural networksElectric Power Systems Research, 2023
- Influence of pulse front steepness on vacuum flashover characteristicsApplied Surface Science, 2018
- Surface modification of epoxy resin using He/CF 4 atmospheric pressure plasma jet for flashover withstanding characteristics improvement in vacuumApplied Surface Science, 2017