EN基于遗传算法改进BP神经网络的输电线路山火监测预警技术
Transmission Line Wildfire Monitoring and Early Warning Technology Based on Genetic Algorithm Improved BP Neural Network
- 电力大数据 2025年第11期
- 作者机构：
1. 贵州电网有限责任公司电网规划研究中心
2. 贵州电网有限责任公司
- 作者简介：
- 基金信息：贵州电网有限责任公司科技项目(GZKJXM20240374)
DOI：
中图分类号：-
纸质出版：2025
- 稿件说明：
移动端阅览
王立, 王伟, 陈飞, 等. 基于遗传算法改进BP神经网络的输电线路山火监测预警技术[J]. 电力大数据, 2025,(11).
王立, 王伟, 陈飞, et al. Transmission Line Wildfire Monitoring and Early Warning Technology Based on Genetic Algorithm Improved BP Neural Network[J]. 2025, (11).
摘要
针对山火灾害对输电线路安全运行造成的严重威胁，本文提出一种基于遗传算法优化BP神经网络的山火监测方法，以提升山火风险的实时识别与预测精度。首先，选取典型山火高风险区域的多源数据，包括气象、地形、植被、人类活动及火灾监测数据，利用皮尔逊相关分析与灰色关联分析识别出一氧化碳浓度、烟雾浓度和环境温度三项关键影响因子。其次，构建BP神经网络模型，将上述三项指标作为输入特征，通过遗传算法对神经网络的初始权值和阈值进行全局优化，以克服传统BP网络随机初始化导致的收敛速度慢和易陷入局部最优等问题。实验采用典型山火监测区域150组实测数据，结果表明，遗传算法优化的BP神经网络在6组独立实验中的平均收敛迭代次数为88.2次，仅为传统BP神经网络平均迭代次数175.2次的50.4%，收敛稳定性显著提升；模型预测精度方面，经优化的BP神经网络表现出更高的鲁棒性与一致性。本文方法在保证预测精度的同时，显著缩短了训练时间，验证了遗传算法在优化BP神经网络参数空间搜索中的有效性。
Abstract
To address the severe threat posed by mountain fire disasters to the safe operation of transmission lines
this study proposes a mountain fire monitoring method based on a genetic algorithm–optimized BP neural network to enhance the real-time identification and prediction accuracy of mountain fire risks. First
multisource data from typical high-risk fire areas—including meteorological
topographic
vegetation
human activity
and fire monitoring information—were analyzed. Pearson correlation and grey relational analysis identified three key influencing factors: carbon monoxide concentration
smoke concentration
and ambient temperature. Then
a BP neural network model was constructed using these three indicators as input features
and a genetic algorithm was applied to globally optimize the initial weights and thresholds of the network to overcome the slow convergence and local optimum issues associated with random initialization in traditional BP networks. Using 150 sets of field-measured data from typical mountain fire monitoring areas
experimental results show that the average convergence iteration count of the genetic algorithm–optimized BP neural network is 88.2
which is only 50.4% of that of the traditional BP neural network (175.2 iterations)
indicating a significant improvement in convergence stability. In terms of prediction accuracy
the optimized BP neural network exhibited higher robustness and consistency across all tests. The proposed method ensures prediction accuracy while substantially reducing training time
demonstrating the effectiveness of the genetic algorithm in optimizing the BP neural network’s parameter search space and providing an efficient and feasible technical approach for intelligent monitoring and early warning of mountain fire hazards in transmission line corridors.
关键词
Keywords
references
孙沛瑶,马灿娃,王兴南,等。配电网电力电缆火灾原因分析与防范技术研究 [J]. 电工技术,2024 (S2).SUN Peiyao, MA Canwa, WANG Xingnan, et al. Analysis of fire causes and prevention technology research of power cables in distribution network [J]. Electrical Engineering, 2024 (S2).
许德胜,李炎锋,杨泉。综合管廊电力舱电缆火灾研究进展 [J]. 消防科学与技术,2024, 43 (09): 1-6.
刘淑琴,卢骏殆,周恩泽,等。架空输电线路精细化山火监测告警技术 [J]. 广东电力,2022, 35 (06): 1-8.
黄道春,卢威,姚涛,等。植被火条件下导线 - 板短空气间隙泄漏电流特性研究 [J]. 电工技术学报,2019, 34 (16).HUANG Daochun, LU Wei, YAO Tao, et al. Research on leakage current characteristics of short air gap between conductor and plate under vegetation fire conditions [J]. Transactions of China Electrotechnical Society, 2019, 34 (16).
王彤,周恩泽,黄道春,等。高海拔植被火条件下导线-板间隙直流击穿特性影响因素分析 [J]. 广东电力,2024, 37 (08).WANG Tong, ZHOU Enze, HUANG Daochun, et al. Analysis of influencing factors on DC breakdown characteristics of conductor-plate gap under high-altitude vegetation fire conditions [J]. Guangdong Electric Power, 2024, 37 (08).
John W. Muhs, Masood Parvania, Mohammad Shahidehpour. Wildfire Risk Mitigation: A Paradigm Shift in Power Systems Planning and Operation[J]. IEEE Open Access Journal of Power and Energy, 2020, 7: 366 - 375.
Yu Liu, Chuanping Wu, Baohui Chen, et al. Study on Distribution Regularity of Overhead Transmission Line nearby Wildfires [C]//2019 IEEE 3rd Conference on Energy Internet and Energy System Integration (EI2). IEEE, 2019.
王胜,王飞。输电线路山火风险分布研究及应用 [J]. 湖北电力,2016, 40 (02).WANG Sheng, WANG Fei. Research and application of mountain fire risk distribution of transmission lines [J]. Hubei Electric Power, 2016, 40 (02).
何诚,舒立福,刘柯珍,等。广西地区山火引起高压线路跳闸环境特征研究 [J]. 消防科学与技术,2020, 39 (12).HE Cheng, SHU Lifu, LIU Kezhen, et al. Study on environmental characteristics of high-voltage line tripping caused by mountain fires in Guangxi [J]. Fire Science and Technology, 2020, 39 (12).
张雪峰,韩俊玉,张云,等。山火诱发高压输电线路跳闸典型事故分析 [J]. 消防科学与技术,2016, 35 (03).ZHANG Xuefeng, HAN Junyu, ZHANG Yun, et al. Analysis of typical accidents of high-voltage transmission line tripping induced by mountain fires [J]. Fire Science and Technology, 2016, 35 (03).
周志宇。山火灾害下电网输电线路跳闸风险评估研究 [D]. 华北电力大学 (北京), 2024.
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).YUAN Sikun, LI Shuai, WANG Jinyu, et al. Research on mountain fire monitoring and early warning technology for transmission lines [J]. Manufacturing Automation, 2023, 45 (11).
周恺,张睿智,叶宽,等。基于静止气象卫星时空变化的山火监测算法及验证 [J]. 消防科学与技术,2025, 44 (03).ZHOU Kai, ZHANG Ruizhi, YE Kuan, et al. Mountain fire monitoring algorithm and verification based on spatio-temporal changes of geostationary meteorological satellites [J]. Fire Science and Technology, 2025, 44 (03).
赵勇,李斌,王开成,等。基于红外成像的输电线路山火自动预警监测技术优化 [J]. 粘接,2025, 52 (10).ZHAO Yong, LI Bin, WANG Kaicheng, et al. Optimization of automatic early warning monitoring technology for mountain fires in transmission lines based on infrared imaging [J]. Adhesion, 2025, 52 (10).
Akshada Bhoir, Gayatri Ghone, Pranali Chavhan, et al. Enhancing Forest Safety: Sensor-Assisted Detection and Prevention of Wildfires [C]//2024 8th International Conference on Computing, Communication, Control and Automation (ICCUBEA). IEEE, 2024.
Michal Kvet, Lucia Fidesová, Karol Matiasko. Experimental comparison of syntax and semantics of DBS Oracle and MySQL[C]//2016 19th Conference of Open Innovations Association (FRUCT). IEEE, 2016.
周将军,李波,谭艳军,等。输电线路山火无人机监测与灭火技术研究 [J]. 消防科学与技术,2020, 39 (02).ZHOU Jiangjun, LI Bo, TAN Yanjun, et al. Research on UAV monitoring and fire extinguishing technology for mountain fires on transmission lines [J]. Fire Science and Technology, 2020, 39 (02).
刘宏,王天正,张海,等。基于毫米波雷达山火监测技术研究 [J]. 武汉大学学报 (工学版), 2020, 53 (01).LIU Hong, WANG Tianzheng, ZHANG Hai, et al. Research on mountain fire monitoring technology based on millimeter-wave radar [J]. Engineering Journal of Wuhan University, 2020, 53 (01).
叶水勇,李亚茹,王文林,等。山火监测与智能识别预警系统的应用 [J]. 国网技术学院学报,2019, 22 (05).YE Shuiyong, LI Yaru, WANG Wenlin, et al. Application of mountain fire monitoring and intelligent identification early warning system [J]. Journal of State Grid Technology College, 2019, 22 (05).
赵宇欣,王恒康。输电线路山火监测预警系统的应用研究 [J]. 科技创新与应用,2017 (34).ZHAO Yuxin, WANG Hengkang. Application research of mountain fire monitoring and early warning system for transmission lines [J]. Technology Innovation and Application, 2017 (34).
杨桉淇,蔡士东,赵思晨,等。基于物联网技术的智能山火报警系统 [J]. 智能计算机与应用,2024, 14 (04).YANG Anqi, CAI Shidong, ZHAO Sichen, et al. Intelligent mountain fire alarm system based on Internet of Things technology [J]. Intelligent Computer and Applications, 2024, 14 (04).
何大四,金瑀琪,张祖铭,等. BP 神经网络回归预测模型的改进 [J]. 机械工程与自动化,2025, 54 (01).HE Dasi, JIN Yuqi, ZHANG Zuming, et al. Improvement of BP neural network regression prediction model [J]. Mechanical Engineering Automation, 2025, 54 (01).
尤晓东,苏崇宇,汪毓铎. BP 神经网络算法改进综述 [J]. 民营科技,2018 (04).YOU Xiaodong, SU Chongyu, WANG Yuduo. Review on improvement of BP neural network algorithm [J]. Private Science Technology, 2018 (04).
Jiankang Lu, Zhengdian Xu, Renrui Wang, et al. Optimal Performance-Preserving Control of Active Suspension Considering Parameter Uncertainty and Genetic Algorithm Optimization [J]. IEEE Access, 2025, 13.
冯智莉,易国洪,李普山,等。并行化遗传算法研究综述 [J]. 计算机应用与软件,2018, 35 (11).FENG Zhili, YI Guohong, LI Pushan, et al. Review on parallel genetic algorithm [J]. Computer Applications and Software, 2018, 35 (11).
刘懿莹,栾松,张师。基于遗传算法优化 BP 神经网络的配电网线损分析方法研究 [J]. 电气开关,2025, 63 (01).LIU Yiying, LUAN Song, ZHANG Shi. Research on distribution network line loss analysis method based on genetic algorithm optimized BP neural network [J]. Electrical Switchgear, 2025, 63 (01).
寇文珍,唐仲杰,崇磊,等。基于 BP 神经网络和遗传算法的光伏电站功率预测 [J]. 光源与照明,2024 (11).KOU Wenzhen, TANG Zhongjie, CHONG Lei, et al. Power prediction of photovoltaic power station based on BP neural network and genetic algorithm [J]. Light Sources Illumination, 2024 (11).基金项目:贵州电网有限责任公司科技项目(GZKJXM20240374)王立(1977),男,高级工程师,从事输电线路电气工程设计研究,E-mail:2945716082 @qq.com。
孙沛瑶,马灿娃,王兴南,等。配电网电力电缆火灾原因分析与防范技术研究 [J]. 电工技术,2024 (S2).SUN Peiyao, MA Canwa, WANG Xingnan, et al. Analysis of fire causes and prevention technology research of power cables in distribution network [J]. Electrical Engineering, 2024 (S2).
许德胜,李炎锋,杨泉。综合管廊电力舱电缆火灾研究进展 [J]. 消防科学与技术,2024, 43 (09): 1-6.
刘淑琴,卢骏殆,周恩泽,等。架空输电线路精细化山火监测告警技术 [J]. 广东电力,2022, 35 (06): 1-8.
黄道春,卢威,姚涛,等。植被火条件下导线 - 板短空气间隙泄漏电流特性研究 [J]. 电工技术学报,2019, 34 (16).HUANG Daochun, LU Wei, YAO Tao, et al. Research on leakage current characteristics of short air gap between conductor and plate under vegetation fire conditions [J]. Transactions of China Electrotechnical Society, 2019, 34 (16).
王彤,周恩泽,黄道春,等。高海拔植被火条件下导线-板间隙直流击穿特性影响因素分析 [J]. 广东电力,2024, 37 (08).WANG Tong, ZHOU Enze, HUANG Daochun, et al. Analysis of influencing factors on DC breakdown characteristics of conductor-plate gap under high-altitude vegetation fire conditions [J]. Guangdong Electric Power, 2024, 37 (08).
John W. Muhs, Masood Parvania, Mohammad Shahidehpour. Wildfire Risk Mitigation: A Paradigm Shift in Power Systems Planning and Operation[J]. IEEE Open Access Journal of Power and Energy, 2020, 7: 366 - 375.
Yu Liu, Chuanping Wu, Baohui Chen, et al. Study on Distribution Regularity of Overhead Transmission Line nearby Wildfires [C]//2019 IEEE 3rd Conference on Energy Internet and Energy System Integration (EI2). IEEE, 2019.
王胜,王飞。输电线路山火风险分布研究及应用 [J]. 湖北电力,2016, 40 (02).WANG Sheng, WANG Fei. Research and application of mountain fire risk distribution of transmission lines [J]. Hubei Electric Power, 2016, 40 (02).
何诚,舒立福,刘柯珍,等。广西地区山火引起高压线路跳闸环境特征研究 [J]. 消防科学与技术,2020, 39 (12).HE Cheng, SHU Lifu, LIU Kezhen, et al. Study on environmental characteristics of high-voltage line tripping caused by mountain fires in Guangxi [J]. Fire Science and Technology, 2020, 39 (12).
张雪峰,韩俊玉,张云,等。山火诱发高压输电线路跳闸典型事故分析 [J]. 消防科学与技术,2016, 35 (03).ZHANG Xuefeng, HAN Junyu, ZHANG Yun, et al. Analysis of typical accidents of high-voltage transmission line tripping induced by mountain fires [J]. Fire Science and Technology, 2016, 35 (03).
周志宇。山火灾害下电网输电线路跳闸风险评估研究 [D]. 华北电力大学 (北京), 2024.
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).YUAN Sikun, LI Shuai, WANG Jinyu, et al. Research on mountain fire monitoring and early warning technology for transmission lines [J]. Manufacturing Automation, 2023, 45 (11).
周恺,张睿智,叶宽,等。基于静止气象卫星时空变化的山火监测算法及验证 [J]. 消防科学与技术,2025, 44 (03).ZHOU Kai, ZHANG Ruizhi, YE Kuan, et al. Mountain fire monitoring algorithm and verification based on spatio-temporal changes of geostationary meteorological satellites [J]. Fire Science and Technology, 2025, 44 (03).
赵勇,李斌,王开成,等。基于红外成像的输电线路山火自动预警监测技术优化 [J]. 粘接,2025, 52 (10).ZHAO Yong, LI Bin, WANG Kaicheng, et al. Optimization of automatic early warning monitoring technology for mountain fires in transmission lines based on infrared imaging [J]. Adhesion, 2025, 52 (10).
Akshada Bhoir, Gayatri Ghone, Pranali Chavhan, et al. Enhancing Forest Safety: Sensor-Assisted Detection and Prevention of Wildfires [C]//2024 8th International Conference on Computing, Communication, Control and Automation (ICCUBEA). IEEE, 2024.
Michal Kvet, Lucia Fidesová, Karol Matiasko. Experimental comparison of syntax and semantics of DBS Oracle and MySQL[C]//2016 19th Conference of Open Innovations Association (FRUCT). IEEE, 2016.
周将军,李波,谭艳军,等。输电线路山火无人机监测与灭火技术研究 [J]. 消防科学与技术,2020, 39 (02).ZHOU Jiangjun, LI Bo, TAN Yanjun, et al. Research on UAV monitoring and fire extinguishing technology for mountain fires on transmission lines [J]. Fire Science and Technology, 2020, 39 (02).
刘宏,王天正,张海,等。基于毫米波雷达山火监测技术研究 [J]. 武汉大学学报 (工学版), 2020, 53 (01).LIU Hong, WANG Tianzheng, ZHANG Hai, et al. Research on mountain fire monitoring technology based on millimeter-wave radar [J]. Engineering Journal of Wuhan University, 2020, 53 (01).
叶水勇,李亚茹,王文林,等。山火监测与智能识别预警系统的应用 [J]. 国网技术学院学报,2019, 22 (05).YE Shuiyong, LI Yaru, WANG Wenlin, et al. Application of mountain fire monitoring and intelligent identification early warning system [J]. Journal of State Grid Technology College, 2019, 22 (05).
赵宇欣,王恒康。输电线路山火监测预警系统的应用研究 [J]. 科技创新与应用,2017 (34).ZHAO Yuxin, WANG Hengkang. Application research of mountain fire monitoring and early warning system for transmission lines [J]. Technology Innovation and Application, 2017 (34).
杨桉淇,蔡士东,赵思晨,等。基于物联网技术的智能山火报警系统 [J]. 智能计算机与应用,2024, 14 (04).YANG Anqi, CAI Shidong, ZHAO Sichen, et al. Intelligent mountain fire alarm system based on Internet of Things technology [J]. Intelligent Computer and Applications, 2024, 14 (04).
何大四,金瑀琪,张祖铭,等. BP 神经网络回归预测模型的改进 [J]. 机械工程与自动化,2025, 54 (01).HE Dasi, JIN Yuqi, ZHANG Zuming, et al. Improvement of BP neural network regression prediction model [J]. Mechanical Engineering Automation, 2025, 54 (01).
尤晓东,苏崇宇,汪毓铎. BP 神经网络算法改进综述 [J]. 民营科技,2018 (04).YOU Xiaodong, SU Chongyu, WANG Yuduo. Review on improvement of BP neural network algorithm [J]. Private Science Technology, 2018 (04).
Jiankang Lu, Zhengdian Xu, Renrui Wang, et al. Optimal Performance-Preserving Control of Active Suspension Considering Parameter Uncertainty and Genetic Algorithm Optimization [J]. IEEE Access, 2025, 13.
冯智莉,易国洪,李普山,等。并行化遗传算法研究综述 [J]. 计算机应用与软件,2018, 35 (11).FENG Zhili, YI Guohong, LI Pushan, et al. Review on parallel genetic algorithm [J]. Computer Applications and Software, 2018, 35 (11).
刘懿莹,栾松,张师。基于遗传算法优化 BP 神经网络的配电网线损分析方法研究 [J]. 电气开关,2025, 63 (01).LIU Yiying, LUAN Song, ZHANG Shi. Research on distribution network line loss analysis method based on genetic algorithm optimized BP neural network [J]. Electrical Switchgear, 2025, 63 (01).
寇文珍,唐仲杰,崇磊,等。基于 BP 神经网络和遗传算法的光伏电站功率预测 [J]. 光源与照明,2024 (11).KOU Wenzhen, TANG Zhongjie, CHONG Lei, et al. Power prediction of photovoltaic power station based on BP neural network and genetic algorithm [J]. Light Sources Illumination, 2024 (11).基金项目:贵州电网有限责任公司科技项目(GZKJXM20240374)王立(1977),男,高级工程师,从事输电线路电气工程设计研究,E-mail:2945716082 @qq.com。
0
浏览量
27
下载量
0
CSCD
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
AI问答- 技术支持由北京北大方正电子有限公司提供 京ICP备09064830号-19
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies