电弧故障的检测方法和装置、存储介质及电子设备
By extracting and weighting the frequency domain features of the current signal, and combining singular value decomposition and ELM neural network, the accuracy problem of arc fault detection is solved, and efficient identification and accurate detection of weak arc faults are achieved.
CN116338402BActive Publication Date: 2026-07-17JIANGSU ZHONGTIAN POWER TECHNOLOGY CO LTD +1
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- JIANGSU ZHONGTIAN POWER TECHNOLOGY CO LTD
- Filing Date
- 2023-03-27
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
The accuracy of arc fault detection in existing technologies is low, especially in the case of DC arc faults, where weak arc faults cannot be effectively identified, leading to frequent false detections or missed detections.
Method used
By extracting and weighting the frequency domain features of the acquired current signal, constructing the Hankel matrix for singular value decomposition, and combining it with the Extreme Learning Machine (ELM) neural network for fault identification, accurate detection of arc faults can be achieved.
Benefits of technology
It improves the accuracy of arc fault detection, effectively identifies weak arc faults, reduces the false detection rate, and ensures the safety of electrical systems.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116338402B_ABST
Abstract
本申请公开了一种电弧故障的检测方法和装置、存储介质及电子设备，其中，包括：获取第一电流信号的第一频域特征向量，其中，第一电流信号为离散信号，第一频域特征向量包括第一电流信号在频域上的N个频段的频域特征，第一电流信号包括在目标电路中采集到的电流信号；对第一频域特征向量进行加权处理，得到第一加权频域特征向量，其中，第一加权频域特征向量中的第d个加权频域特征是第一频域特征向量中的第d个频域特征与第d个权重的乘积；对第一频域特征加权向量进行去噪处理，得到第一电流信号的电弧特征；根据电弧特征确定目标电路是否出现电弧故障。采用上述技术方案，解决了相关技术中在电弧故障的检测过程中出现的准确率较低的问题。
Need to check novelty before this filing date? Find Prior Art