摘要
在高电压环境下,SF_(6)气体在断路器的接头和密封件等关键部位的泄漏过程因放电、过热及水蒸气的存在而变得更为复杂和迅速。在这种条件下,SF_(6)气体在高电场强度和电磁干扰的双重作用下,会迅速分解,生成有害气体,不仅加剧了泄漏过程的复杂性,也增加了其难以直接观察的特性。为此,提出高电压分解下SF_(6)断路器气体泄漏快速预警算法研究。利用像素层自适应分割算法和自适应阈值帧间差分法提取SF_(6)气体泄漏潜在区域,通过形态学开闭运算和区域连通法处理潜在区域中存在的内部空洞、边缘不完整、区域不连贯等问题,再基于气体泄漏扩散时的面积增长特性,区分泄漏气体与其他运动物体,排除误警、虚警等情况,量化平均差分像素点为泄漏程度,依据报警阈值对SF_(6)断路器气体泄漏快速预警。实验结果表明,所提方法在SF_(6)断路器气体泄漏潜在区域检测中的吞吐率、目标轮廓完整度和交并比较高,且在预警中的AUC值较高。
Under high voltage environment,the leakage process of SF_(6)gas in key parts of circuit breaker joints and seals becomes more complicated and rapid due to discharge,overheating and the presence of water vapor.Under such conditions,SF_(6)gas will rapidly decompose and generate harmful gases under the dual action of high electric field strength and electromagnetic interference,which not only aggravates the complexity of the leakage process,but also increases its difficult to directly observe the characteristics.Therefore,a study on the rapid early warning algo-rithm for SF_(6)circuit breaker gas leakage under high voltage decomposition is proposed.The potential area of SF_(6)gas leakage is extracted using the pixel-level adaptive segmentation algorithm and the adaptive threshold inter-frame difference method.The problems of internal cavities,incomplete edges,and incoherent regions in the potential area are processed through morphological opening and closing operations and regional connectivity methods.Then,based on the area growth characteristics of gas leakage and diffusion,the leakage gas is distinguished from other moving objects to eliminate false alarms,false positives,and other situations.The average differential pixel points are quantified as the degree of leakage,and the rapid early warning of SF_(6)circuit breaker gas leakage is performed according to the alarm threshold.Experimental results show that the proposed method has high throughput rate,tar-get contour integrity,and intersection-over-union in the detection of potential areas of SF_(6)circuit breaker gas leak-age,and a high AUC value in early warning.
作者
张建禄
吴超
岳永刚
翟春雨
武剑灵
方国宝
ZHANG Jianglu;WU Chao;YUE Yonggang;ZHAI Chunyu;WU Jianling;FANG Guobao(Inner Mongolia EHV Power Supply Company,Hohhot 010080,China)
出处
《电测与仪表》
北大核心
2025年第3期104-111,共8页
Electrical Measurement & Instrumentation
基金
内蒙古电力公司2023年科技项目(LX11237054)。
