| 刘艳丽,王浩,李佳原,张帆.基于多卷积和结构搜索的电弧故障检测模型[J].电子测量与仪器学报,2024,38(4):117-127 |
| 基于多卷积和结构搜索的电弧故障检测模型 |
| Arc fault detection model based on multi-convolution and structure search |
| |
| DOI： |
| 中文关键词: 电动汽车 电弧故障检测 轻量化卷积 遗传算法 精英保留策略 |
| 英文关键词:electric vehicle arc fault detection lightweight convolution genetic algorithm elite preservation strategy |
| 基金项目:国家自然科学基金（52104160）、2022年度葫芦岛市科技指导计划重点研发项目（2022JH2/07b）资助 |
|
|
| Author | Institution |
| Liu Yanli | Faculty of Electrical and Control Engineering, Liaoning Technical University, Huludao 125105, China |
| Wang Hao | Faculty of Electrical and Control Engineering, Liaoning Technical University, Huludao 125105, China |
| Li Jiayuan | Faculty of Electrical and Control Engineering, Liaoning Technical University, Huludao 125105, China |
| Zhang Fan | State Grid Huludao Power Supply Company, Huludao 125003, China |
|
| 摘要点击次数: 261 |
| 全文下载次数: 13378 |
| 中文摘要: |
| 串联型电弧故障主要由电路中电气接触点接触不良引起，是引发电动汽车电气火灾的主要原因之一，直接威胁着车内人员的生命安全。为对其进行研究，论文搭建了电动汽车直流串联型电弧故障实验平台，获取了系统处于不同工作状态下的电源端电压信号，分析了电弧故障对电源端电压的影响。在构建检测模型时，论文使用了卷积神经网络，引入轻量型的卷积操作并考虑了其在实际应用中的局限性。将常规卷积和轻量化卷积操作结合，构建了电弧故障检测的初步模型。接着以网络的规模和准确率为评估指标，通过具有精英保留策略的遗传算法对模型的外部结构和内部参数进行搜索。最终建立了适合电动汽车的电弧故障检测（arc fault detection，AFD）的检测模型AFDNet。该模型的检测准确率达到93.73%，在嵌入式设备Jetson Nano（JN）中的运行时间为10.82 ms。模型建立后，论文在网络的规模、准确性及实时性方面，将搜索算法的搜索结果与其他的网络结构进行比较，验证了搜索算法所得结果的合理性。并通过与其他检测方法对比，证明了电动汽车电弧故障检测模型AFDNet性能的优越。 |
| 英文摘要: |
| The series arc fault is mainly caused by poor contact of the electrical contact points in the circuit, which is one of the main causes of electric vehicle fires, directly threatening the life safety of the occupants. In order to study it, an experimental platform for DC series arc fault of electric vehicles was established. The voltage signals of the power supply terminal were obtained under various working conditions, and the impact of arc faults on the power supply terminal voltage was analyzed. When constructing the detection model, the paper used a convolutional neural network, introduced a lightweight convolution operation, and considered its limitations in practical applications. Combining conventional convolution and lightweight convolution operations, a preliminary model for arc fault detection was constructed. Then, with the scale and accuracy of the network as the evaluation index, the genetic algorithm with elite preservation strategy was used to search for the external structure and internal parameters of the model. Finally, the model AFDNet suitable for arc fault detection (AFD) of electric vehicles was established. The detection accuracy of the model is 93.73%, and the running time on the embedded device Jetson Nano（JN） is 10.82 ms. After establishing the model, the paper compared the search results of the algorithm with other network structures in relation to network size, accuracy, and real-time performance, verified the validity of the results obtained by the search algorithm. By comparing AFDNet with other detection methods, it was proven that the performance of the electric vehicle arc fault detection model was superior. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
