| 引用本文: | 吴迪,汤小兵,李鹏,等.基于深度神经网络的变电站继电保护装置状态监测技术[J].电力系统保护与控制,2020,48(5):81-85.[点击复制] |
| WU Di,TANG Xiaobing,LI Peng,et al.State monitoring technology of substation relay protection device based on deep neural network[J].Power System Protection and Control,2020,48(5):81-85[点击复制] |
|
| 摘要: |
| 监测变电站中继电保护装置的实时状态对避免设备损坏或故障，维持电网稳定运行有重要意义。传统的状态监测依赖于定期的人工检查，在耗费大量人力的同时，也难以做到不间断实时监测，且检测精度容易受到主观因素的限制。针对这一困境，提出基于深度神经网络与计算机视觉技术的变电站继电保护设备状态监测技术。利用平移变焦摄像机拍摄的变电站实时画面，首先进行图像去噪，并利用图像相关性进行图像配准。根据尺度不变特征变换(Scale-Invariant Feature Transform，SIFT)描述，使用深度神经网络进行图像分类，识别出设备的状态。同时，提出一种对标准图像配准框架的修改方案，使得算法在不同光照条件下具有更高鲁棒性。在实际应用中，该算法可以达到超过99%的检测准确率，大幅提升了变电站的安全性。 |
| 关键词: 变电站巡视 继电保护装置 深度神经网络 计算机视觉 |
| DOI：10.19783/j.cnki.pspc.190516 |
| 投稿时间：2019-05-09修订日期：2019-06-25 |
| 基金项目:国家自然科学青年基金项目资助(61602251) |
|
| State monitoring technology of substation relay protection device based on deep neural network |
| WU Di,TANG Xiaobing,LI Peng,YANG Zengli,WEN Bo,LI Hengxuan |
| (State Grid Hubei Electric Power Dispatching Control Center, Wuhan 430077, China;SP-NICE Technology Development Co., Ltd., Nanjing 211153, China;State Grid Hubei Electric Power Research Institute, Wuhan 430077, China) |
| Abstract: |
| Monitoring the real-time state of relay protections in electric power distribution substations is of significance for avoiding equipment damage and keeping the safety and stability of electrical network. Traditional state monitoring depends on regular manual inspection, which requires a great of manpower, and the character of real-time and accuracy will be restricted. To overcome this problem, a deep neural network and computer vision based monitoring strategy is proposed. First, it denoises the images collected by pan-tilt-zoom surveillance cameras, and then makes image registration according to correlations among images. Based on Scale-Invariant Feature Transform (SIFT) descriptor, the convolutional neural network can classify image and recognize the state of relay protections. Meanwhile, a modification of standard image registration framework is proposed to make model be of higher robustness under different lighting conditions. In real-world application, the accuracy of the proposed method can be higher than 99%, effectively improving the safety of substations. This work is supported by Youth Fund of National Natural Science Foundation of China (No. 61602251). |
| Key words: substations monitoring relay protections deep neural network computer vision |
