摘要
目前变电站巡检机器人广泛应用于变电站巡检过程中,主要巡检高压电力设备绝缘子、均压环等外部配件。在巡检过程中,机器人配备红外成像仪、紫外成像仪存储高压电力设备光子分布图、温度分布图,建立设备红外与紫外图像数据库。一方面,机器人在巡检过程中应有效规避变电站较高电场强度区域,在巡检过程中应以最短距离遍历变电站典型高压电力设备,且机器人机械臂可有效进行图像多角度采集。另一方面,在图像采集过程中应实现机器人对设备绝缘子、均压环图像区域分割、聚焦和光子采集操作,且应用深度学习方法实现采集图片与原始图像库的自动匹配比较,判别高压电力设备运行状态进而发现潜伏性绝缘故障。其中最短低场强路径与遍历设备路线应用免疫蚁群算法自动实现,且图像数据库深度学习与自动匹配模块应用模糊神经网络实现。联合免疫蚁群算法与模糊神经网络应用于变电站巡检机器人路径规划及视觉图像后处理,对于变电站高压电力设备智能巡检具有一定理论和工程指导价值。
At present,substation inspection robot is widely used in the process of substation inspection.It mainly inspects the insulator,grading ring and other external accessories of high-voltage power equipment.In the process of inspection,the robot is equipped with infrared imager and ultraviolet imager to store the photon distribution map and temperature distribution map of high-voltage power equipment,and establish the ultraviolet and infrared image database of the equipment.In the process of inspection,the robot should avoid the area with higher electric field intensity,and traverse the typical high-voltage electrical equipment in the substation in the shortest distance,and the robot arm can effectively carry out image multi-angle acquisition.On the other hand,during the image acquisition process,the robot should realize the segmentation,focusing and photon acquisition operations of the equipment insulator and the equalizing ring image area.The deep learning method is used to realize the automatic matching and comparison between the collected pictures and the original image database,so as to identify the operation status of high-voltage power equipment,and then to find the latent insulation fault.Among them,the shortest low-field-strength path and the traversal equipment route were automatically realized by the immune ant colony algorithm,and the image database deep learning and automatic matching module was realized by fuzzy neural network.The joint immune ant colony algorithm and fuzzy neural network were applied to the path planning and visual image post-processing of the substation inspection robot,which had certain theoretical and engineering guidance value for the intelligent inspection of the substation high-voltage power equipment.
作者
张施令
ZHANG Shiling(State Grid Chongqing Electric Power Company Chongqing Electric Power Research Institute,Chongqing 401123,China)
出处
《电工技术》
2020年第23期4-8,共5页
Electric Engineering
