An AI-assisted partial discharge detection and diagnosis method
By employing an AI-assisted partial discharge detection and diagnosis method, and utilizing a cascaded AI model and a multi-dimensional knowledge base, an intelligent end-to-end process from data acquisition to diagnostic results has been achieved. This solves the problem of relying on human experience in existing technologies, and improves detection efficiency and accuracy.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- GLOBAL SCI & TECH (SHANGHAI) CO LTD
- Filing Date
- 2025-11-26
- Publication Date
- 2026-07-24
AI Technical Summary
Current partial discharge detection relies on engineers' professional experience, lacks real-time interactive intelligent guidance, and lacks self-optimization capabilities, resulting in low detection efficiency and a high false detection rate.
The AI-assisted partial discharge detection and diagnosis method achieves full-process intelligence from data acquisition to diagnostic results through a first AI model and a second AI model connected in series. Combined with a multi-dimensional knowledge base and a time-sharing reuse mechanism, it provides real-time interactive suggestions and self-optimization.
It improves the level of automation and standardization of testing, reduces reliance on expert experience, enhances the accuracy and efficiency of diagnosis, and can provide reliable diagnostic recommendations in complex environments.
Smart Images

Figure HDA0005706921330000011