基于图像深度学习的高压断路器操动机构锈蚀状态评估  

Rust status evaluation of high voltage circuit breaker operating mechanism based on image deep learning

作　　者：杨鼎革 丁彬 高健 牛博 赵陈琛 郭艺博 张国钢[2] YANG Ding-ge;DING Bin;GAO Jian;NIU Bo;ZHAO Chen-chen;GUO Yi-bo;ZHANG Guo-gang(State Grid Shaanxi Electric Power Research Institute, Xi’an 710100, China;State Key Laboratory of Electrical Insulation and Power Equipment, Xi’an Jiaotong University, Xi’an 710049, China)

机构地区：[1]国网陕西省电力公司电力科学研究院,陕西西安710100 [2]西安交通大学电力设备电气绝缘国家重点实验室,陕西西安710049

出　　处：《电工电能新技术》2022年第5期71-79,共9页Advanced Technology of Electrical Engineering and Energy

基　　金：国网陕西省电力有限公司科技项目(5226KY19004T)。

摘　　要：高压断路器在长期运行过程中会产生不同程度及不同形态的锈蚀,其操动机构的关键零部件连接处存在锈蚀时,会影响断路器分合闸速度,严重时将导致机构拒动,危及电力系统的供电安全。因此,对高压断路器操动机构进行锈蚀检测并评估其运行状态具有重要意义。本文提出一种基于图像深度学习的高压断路器操动机构锈蚀状态评估方法,首先,根据高压断路器的工作原理和结构特点,建立评价指标体系,并利用主客观综合赋权法,确定各指标综合权重;其次,利用YOLO深度学习算法识别操动机构的锈蚀位置和锈蚀等级,计算相关评价指标;最后,通过模糊综合评价方法,获得锈蚀状态的评价结果。对YOLOv3、YOLOv4和YOLOv5算法进行性能测试,表明YOLOv5算法在准确度和速度等方面综合表现更好;最后,对某台已投运的高压断路器进行锈蚀状态评估,与实际情况对比,验证了所提方法的合理性。The high voltage circuit breaker will produce different degrees and forms of corrosion after long-term operation.When the mechanical connections between the key parts of operating mechanism are rusted,it will affect the open-close speed of circuit breaker.In severe cases,the mechanism will fail to operate,endangering the power supply security of power system.Therefore,it is of great significance to detect the corrosion and evaluate the running status of operating mechanism.In this paper,a method to assess the rust degree of the operating mechanism of high voltage circuit breaker based on image deep learning is proposed.Firstly,the evaluation index system is established based on the operating principle and structure characteristics of circuit breaker and the comprehensive weight of each index is determined according to the combination weighting method of subjective and objective.Secondly,YOLO algorithm is used to identify the rust position and rust level of operating mechanism and determine the status evaluation index.Finally,the status evaluation result is obtained by applying fuzzy comprehensive evaluation algorithm.YOLOv3,YOLOv4 and YOLOv5 models have been tested and compared,and the results show that the comprehensive performance of YOLOv5 model is best in terms of accuracy and speed and etc.Finally,the method of rust status evaluation has been put into practical application with a case of high voltage circuit breaker in operation.Comparing the evaluation result with the practical situation,the rationality of the proposed method is verified.

关 键 词：高压断路器 操动机构 图像深度学习 锈蚀状态评估 YOLO算法 模糊综合评价 

分 类 号：TM561[电气工程—电器]