基于多特征融合的输电通道山火识别方法

doi:10.3969/j.issn.1008-0198.2024.03.002

湖南电力 ›› 2024, Vol. 44 ›› Issue (3): 9-14.doi: 10.3969/j.issn.1008-0198.2024.03.002

• 特约专栏: 输变电设备数字化运检技术 • 上一篇下一篇

基于多特征融合的输电通道山火识别方法

叶俊, 邱志斌, 杨泽鼎, 赖东阳

南昌大学能源与电气工程系,江西南昌 330031

收稿日期:2024-04-09 修回日期:2024-04-21 出版日期:2024-06-25 发布日期:2024-07-10
通信作者: 叶俊(2000),男,硕士研究生在读,研究方向为电力视觉与图像处理。
作者简介:邱志斌(1991),男,副教授,博士,研究方向为输变电设备外绝缘、电力视觉与人工智能、电磁场数值计算。
基金资助:
江西省“双千计划”创新领军人才长期(青年)项目(jxsq2019101071)

Transmission Channel Hill Fire Identification Method Based on Multi-Feature Fusion

YE Jun, QIU Zhibin, YANG Zeding, LAI Dongyang

Department of Energy and Electrical Engineering, Nanchang University, Nanchang 330031, China

Received:2024-04-09 Revised:2024-04-21 Online:2024-06-25 Published:2024-07-10

摘要/Abstract

摘要： 针对输电通道山火频发引起线路跳闸的问题,提出一种基于多特征融合的输电通道山火识别方法。利用伽马变换和Sobel算子对输电线路山火图像进行图像增强处理,并使用由超像素分割、区域生长法及形态学处理构成的多级分割算法获取火焰区域的图像;提取分割后火焰图像的颜色特征和纹理特征,采用串行特征融合方式进行融合之后输入BP神经网络分类器进行训练,实现对输电通道山火的识别。实验结果表明,该方法对山火识别的总体精度达到92.7%,可以为电力运维人员进行输电通道山火监测提供参考。

关键词: 特征融合, 山火, 分类器, Sobel算子

Abstract: :According to the daily inspection requirements of power grid, a method of transmission channel fire identification based on multi-feature fusion is proposed to solve the problem of frequent transmission channel fire trip.The images of transmission line wildfires are enhanced by gamma transform and Sobel operator, and multistage segmentation algorithm consisting of superpixel segmentation, region growth method and morphological processing are used to obtain the images of flame regions. The color and texture features are extracted from segmented flame images and fused using a serial feature fusion approach and a BP neural network classifier is trained to achieve recognition of transmission channel wildfires. Experimental results demonstrate an overall accuracy rate of 92.7% for the proposed method, providing valuable guidance for power operation and maintenance personnel in monitoring fire incidents within transmission channels.

Key words: feature fusion, hill fire, classifier, Sobel operator

中图分类号:

TM726

叶俊, 邱志斌, 杨泽鼎, 赖东阳. 基于多特征融合的输电通道山火识别方法[J]. 湖南电力, 2024, 44(3): 9-14.

YE Jun, QIU Zhibin, YANG Zeding, LAI Dongyang. Transmission Channel Hill Fire Identification Method Based on Multi-Feature Fusion[J]. Hunan Electric Power, 2024, 44(3): 9-14.

参考文献

[1]陆佳政,刘毓,吴传平,等.输电线路山火卫星监测与告警算法研究[J].中国电机工程学报,2015,35(21):5511-5519.
[2]DONG S H,DING Y J,MA L S,et al.Design of mountain fire prevention monitoring system for transmission lines based on machine vision algorithms[J].International Journal of Emerging Electric Power Systems,2023,24(4):529-539.
[3]LI J S,CHEN J,YU H,et al.Wildfire monitoring technologies of transmission line corridors based on Fengyun-3E satellite imaging[J].Frontiers in Energy Research,2023,11:1265516.
[4]黄新波,张瑜,朱波.智能变电设备监控与决策辅助系统数据库的设计与实现[J].高压电器,2016,52(3):15-22.
[5]王莹,李文辉.基于多特征融合的高精度视频火焰检测算法[J].吉林大学学报(工学版),2010,40(3):769-775.
[6]严云洋,唐岩岩,郭志波,等.融合色彩和轮廓特征的火焰检测[J].微电子学与计算机,2011,28(10):137-141,145.
[7]荣建忠,姚卫,高伟,等.基于多特征融合技术的火焰视频探测方法[J].燃烧科学与技术,2013,19(3):227-233.
[8]吴茜茵,严云洋,杜静,等.多特征融合的火焰检测算法[J].智能系统学报,2015,10(2):240-247.
[9]BORDBAR H,ALINEJAD F,CONLEY K,et al.Flame detection by heat from the infrared spectrum:Optimization and sensitivity analysis[J].Fire Safety Journal,2022,133:103673.
[10]苑司坤,李帅,王津宇,等.输电线路山火监测预警技术研究[J].制造业自动化,2023,45(11):31-35.
[11]张婧,郭风成,左泽丹,等.融合多方向Sobel算子的相干斑各向异性扩散抑制[J].遥感技术与应用,2023,38(5):1118-1125.
[12]赵园喜,邱志斌,朱轩,等.基于SSIM-Sobel与多特征融合的绝缘子缺陷识别方法[J].智慧电力,2023,51(12):74-79.
[13]杨先凤,李小兰,贵红军.改进的自适应伽马变换图像增强算法仿真[J].计算机仿真,2020,37(5):241-245.
[14]王宏昕.远程视频火焰的识别方法研究与仿真[J].计算机仿真,2016,33(7):355-358.
[15]邢晓强,黄新波,纪超,等.基于多特征融合的输电线路山火识别预警系统设计与实现[J].广东电力,2018,31(6):107-113.
[16]武昕,严萌,郭一凡,等.基于结构化特征图谱的组合支持向量机非侵入式负荷辨识[J].电力系统自动化,2022,46(12):210-219.
[17]周志华.机器学习[M].北京:清华大学出版社,2016.
[18]林友勤,郑学善,余印根,等.基于BP神经网络的斜拉索损伤识别方法[J].南昌大学学报(工科版),2023,45(4):370-376.
[19]荣建忠.基于多特征的火焰图像探测研究及实现[D].合肥:中国科学技术大学,2012.
[20]周恩泽,黄勇,龚博,等.基于朴素贝叶斯网络的输电走廊山火风险评估模型[J].南方电网技术,2021,15(8):120-129.
[21]CAMPBELL T W,RODER H,GEORGANTAS R W,et al.Exact shapley values for local and model-true explanations of decision tree ensembles[J].Machine Learning with Applications,2022,9:100345.
[22]彭紫扬,陈诺天,易俊飞,等.基于改进RetinaNet算法的输电线路电力器件及异常目标检测[J].湖南电力,2023,43(5):79-84.

基于多特征融合的输电通道山火识别方法

Transmission Channel Hill Fire Identification Method Based on Multi-Feature Fusion

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价