基于软件无线电的静电放电瞬态信号检测方法及装置
By employing a software-defined radio-based method for detecting transient electrostatic discharge signals, and utilizing a dual-branch recognition model to acquire, digitize, and identify electrostatic discharge signals, this method solves the problems of large size, high cost, and insufficient recognition capability of existing equipment. It enables portable detection and efficient identification at engineering sites, improving recognition accuracy and real-time performance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHIJIAZHUANG TIEDAO UNIV
- Filing Date
- 2026-05-13
- Publication Date
- 2026-07-17
AI Technical Summary
Existing electrostatic discharge detection equipment is bulky and expensive, and portable devices lack the ability to identify and distinguish different types of transient electromagnetic interference signals, making it difficult to meet the portable detection needs of engineering sites. Furthermore, under limited computing power, it is difficult to achieve real-time detection and accurate identification.
A software-defined radio-based method for detecting transient electrostatic discharge signals is adopted. Electromagnetic radiation signals in the 5MHz-25MHz frequency band are collected, digitally processed, and buffered. Combined with moving average filtering and threshold decision mechanism, a dual-branch recognition model is used for signal recognition, including I/Q raw signal feature extraction and statistical feature learning, to achieve efficient recognition of electrostatic discharge signals.
While ensuring the portability and low cost of the device, it has achieved stable capture and efficient identification of transient signals, improved the ability to distinguish electrostatic discharge signals from other interference signals, and enhanced the identification accuracy and real-time performance. In particular, it can still maintain a high identification accuracy under the condition of limited computing resources on embedded platforms.
Smart Images
Figure CN122171922B_ABST