A method and system for assessing the vulnerability of electrical equipment under strong electromagnetic pulse.
By fusing experimental and simulation data of electrical equipment using the Co-Kriging model and support vector machine method, an electromagnetic coupling parameter response proxy model and effect relationship model are established. This solves the accuracy problem of electrical equipment vulnerability assessment in existing technologies and achieves high-precision assessment under small sample conditions.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XIAN THERMAL POWER RES INST CO LTD
- Filing Date
- 2023-02-23
- Publication Date
- 2026-06-30
AI Technical Summary
Existing technologies for assessing the vulnerability of electrical equipment under strong electromagnetic pulses suffer from low accuracy and high cost of simulation data, while experimental observation data have small sample sizes, making it difficult to accurately assess the vulnerability of the equipment.
By employing the Co-Kriging model to integrate experimental and simulation data, and combining it with the support vector machine method, a proxy model for the electromagnetic coupling parameter response and the effect relationship model at key locations of electrical equipment are established to improve the accuracy of the assessment.
By integrating different data types, computational bias is reduced and the accuracy of electromagnetic pulse vulnerability assessment is improved. In particular, it can provide vulnerability probabilities in small sample cases, thereby improving the accuracy of assessment results.
Smart Images

Figure CN116306258B_ABST