| 田世岗,王智勇,高洪鑫,李海嘉,郭凤仪,王健.全线路串联电弧故障在线检测方法及装置研究[J].电子测量与仪器学报,2025,39(12):104-114 |
| 全线路串联电弧故障在线检测方法及装置研究 |
| Research on on-line detection method and device for full-circuit series arc fault |
| |
| DOI： |
| 中文关键词: 串联电弧故障 轻量级模型 嵌入式设备 在线检测 |
| 英文关键词:series arc fault lightweight model embedded device on-line detection |
| 基金项目:辽宁省教育厅基金(LJ242410147030，LJ212410147022)项目资助 |
|
|
| Author | Institution |
| Tian Shigang | State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources，
North China Electric Power University, Beijing 102206, China |
| Wang Zhiyong | Faculty of Electrical and
Control Engineering,Liaoning Technical University, Huludao 125105, China |
| Gao Hongxin | Faculty of Electrical and
Control Engineering,Liaoning Technical University, Huludao 125105, China |
| Li Haijia | Faculty of Electrical and
Control Engineering,Liaoning Technical University, Huludao 125105, China |
| Guo Fengyi | College of
Electrical and Electronic Engineering,Wenzhou University, Wenzhou 325035, China |
| Wang Jian | State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources，
North China Electric Power University, Beijing 102206, China |
|
| 摘要点击次数: 659 |
| 全文下载次数: 499 |
| 中文摘要: |
| 为提升低压交流电力系统中串联电弧故障（SAF）的检测效率与精度，以工业电动机配电线路为对象，通过电弧故障实验构建数据集，并设计了基于MobileViT架构的轻量级SAF识别模型。该识别模型采用轻量级卷积模块和Transformer模块分别提取电流信号中的局部特征和全局特征，并使用Unfold-Transformer-Fold机制以及全局平均池化层减少模型参数量和计算复杂度。进一步通过TensorRT推理优化器和推理引擎对该模型进行部署优化，大幅提升了其在嵌入式设备中的推理速度，并据此研制了全线路SAF在线检测装置。该检测装置具备灵活的部署特性，当安装于变频器前端时，可同时监测变频器前端和后端的SAF；安装在后端时也能实现后端SAF的精准监测。测试结果表明，该装置平均运行时间不超过0.874 ms，识别准确率在97.20%以上，能够满足IEC62606标准的要求和工业场景应用需求。此外，对比实验表明该装置优于现有电弧故障探测器产品，能够为研发工业电弧故障断路器提供参考。 |
| 英文摘要: |
| To improve the detection efficiency and accuracy of series arc fault (SAF) in low-voltage alternating current power system, this study takes industrial motor distribution circuits as the object, constructs datasets through arc fault experiments, and designs a lightweight SAF identification model based on MobileViT architecture. The model uses lightweight convolution modules and transformer modules to extract local and global features from the current signal respectively, and uses the unfold-transformer-fold mechanism and global average pooling to achieve parameter and complexity reduction. Further, the TensorRT inference optimizer and engine are used to deploy and optimize the model, which significantly improves the inference speed of the model in embedded devices, and based on this, the full-circuit SAF on-line detection device is developed. The detection device has flexible deployment characteristics: when installed at the front end of the frequency converter, it can simultaneously monitor the SAF of the front and back end of the frequency converter. It can also achieve precise monitoring of the SAF of the back end when installed at the back end. The test results show that the average runtime of the device is less than 0.874 ms, and the accuracy is above 97.20%, which can meet the requirements of IEC62606 standard and industrial scenarios. In addition, the comparison experiments show that the device is superior to the existing arc fault detector products and can provide a reference for the development of industrial arc fault circuit breakers. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
