基于轮廓线与特征融合的电网变电设备三维自动化运检方法

因工作环境的复杂性，变电设备成为智能电网中故障频率最高的装置之一，易发生设备接地故障、保险熔断故障、绝缘材料老化等问题，为提高电网变电设备三维自动化运检精度，提出基于轮廓线与特征融合的电网变电设备三维自动化运检方法研究。采集电网变电设备三维图像，获取电网变电设备三维图像初始轮廓点，筛选变电设备轮廓点，依照顺序连接提取出的关键轮廓点，得到变电设备三维图像轮廓线，结合形态学滤波算法，对图像进行开、闭运算，依据轮廓线的闭合情况，分割出目标图像与背景图像，提取包括HOG特征与LBP特征的变电设备目标图像特征，经过特征融合后，构造最优分类超平面，制定电网变电设备三维自动化运检规则，判定变电设备运维情况，最终实现变电设备的三维自动化运检。实验数据显示：该方法识别出变电设备的正常与异常状态，在不同实验工况背景下，应用提出方法获得的变电设备运检精度达到了96%。提高了变电设备的自动化运检的识别及运检精度，满足现今变电设备的运检需求。

3D Automatic Operation Inspection Method of Power Grid Substation Equipment Based on Contour and Feature Fusion

Due to the complexity of the working environment, substation equipment has become one of the devices with the highest fault frequency in the smart grid, which is prone to equipment grounding faults, fuse fuse faults, and aging of insulating materials. A research on the three-dimensional automatic inspection method of power grid substation equipment based on the fusion of contour lines and features is proposed. Collect the three-dimensional image of the power grid substation equipment, obtain the initial contour points of the three-dimensional image of the power grid substation equipment, filter the contour points of the substation equipment, connect the extracted key contour points in sequence, obtain the contour line of the three-dimensional image of the substation equipment, and combine the morphological filtering algorithm, perform opening and closing operations on the image, segment the target image and the background image according to the closure of the contour line, extract the target image features of the substation equipment including the HOG feature and the LBP feature, and construct the optimal classification hyperplane after feature fusion. Formulate three-dimensional automatic inspection rules for power grid substation equipment, determine the operation and maintenance of substation equipment, and finally realize three-dimensional automatic inspection of substation equipment. The experimental data show that the method can identify the normal and abnormal states of the substation equipment, and under the background of different experimental conditions, the operation inspection accuracy of the substation equipment obtained by the proposed method reaches 96%. The identification and inspection accuracy of automatic inspection of substation equipment are improved, and the inspection requirements of current substation equipment are met.