Mountain Fire Spread Speed Combined Forecasting Model for Transmission Line Based on EMD and ELM

LI Jinwei; WANG Qi; HE Hongtai; PEI Guanrong

doi:10.3969/j.issn.1000-7229.2015.03.005

PDF(523 KB)

Electric Power Construction ›› 2015, Vol. 36 ›› Issue (3) : 27-32. DOI: 10.3969/j.issn.1000-7229.2015.03.005

Mountain Fire Spread Speed Combined Forecasting Model for Transmission Line Based on EMD and ELM

LI Jinwei1, WANG Qi1, HE Hongtai2, PEI Guanrong2

Author information +

History +

Abstract

According to the impact of mountain fire of transmission line in complex environment, the mountain fire prediction model was proposed based on the methods of empirical mode decomposition （EMD） and extreme learning machine （ELM）. Firstly, the noise of collected wind speed time series was analyzed by using wavelet transform, and the classification and reconstruction were carried out according to the different sequences, in order to reconstruct new wind speed time series. Secondly, the factors of the mountain fire were decomposed into a series of sub-sequences with different characteristics scales by using EMD. Thirdly, cross-validation method and phase space reconstruction method were used to determine various parameters and input dimensions of machine learning, and then the modeling and forecasting analysis was carried out for the mountain fire of transmission line by using ELM. The simulation results show that the combined forecasting model for the mountain fire of transmission lines based on EMD and ELM can effectively predict fire spread speed within 24 h, which can provide the possibility to realize the online prediction of the mountain fire in transmission line with high precision.

Key words

mountain fire / empirical mode decomposition（EMD） / multi-resolution analysis / extreme learning machine（ELM）

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

LI Jinwei, WANG Qi, HE Hongtai, PEI Guanrong. Mountain Fire Spread Speed Combined Forecasting Model for Transmission Line Based on EMD and ELM[J]. Electric Power Construction. 2015, 36(3): 27-32 https://doi.org/10.3969/j.issn.1000-7229.2015.03.005

References

［1］廖旎焕, 胡智宏, 马莹莹, 等. 电力系统短期负荷预测方法综述［J］. 电力系统保护与

控制, 2011, 39（1）: 47-52.
Liao Nihuan, Hu Zhihong, Ma Yingying, et al. Review of the short-term load forecasting methods of electric power system

［J］.Power System Protection and Control, 2011, 39（1）: 47-52.
［2］黄乐, 舒双燕. 南方电网2010 年第一季度线路山火跳闸情况分析［J］. 广东电力, 2011, 24（3）: 95-97.
Huang Le, Shu Shuangyan. Analysis on fault trips caused by forest fire in CSG in the first quarter of year 2010［J］.

Guangdong Electric Power, 2011, 24（3）: 95-97.
［3］宋国兵, 蔡新雷, 高淑萍, 等. 高压直流输电线路故障定位研究综述［J］. 电力系统保护与控制, 2012, 40（5）: 133-137.
Song Guobing, Cai Xinlei, Gao Shuping, et al. Survey of fault location research for HVDC transmission lines［J］. Power

System Protection and Control, 2012, 40（5）: 133-137.
［4］李勇, 陶雄俊, 陈立. 输电线路山火故障分析及预防［J］. 湖北电力, 2010, 34（6）: 49-50.
Li Yong, Tao Xiongjun, Chen Li. The analysis and precautions of forest fire fault to transmission line［J］. Hubei Electric

Power, 2010, 34（6）: 49-50.
［5］吴田, 胡毅, 阮江军, 等. 交流输电线路模型在山火条件下的击穿机理［J］. 高电压技术, 2011, 37（5）: 1115-1122.
Wu Tian, Hu Yi, Ruan Jiangjun, et al. Air gap breakdown mechanism of model AC transmission line under forest fires［J］. High

Voltage Engineering, 2011, 37（5）: 1115-1122.
［6］吴田, 阮江军, 胡毅, 等. 500 kV 输电线路的山火击穿特性及机制研究［J］. 中国电机工程学报, 2011, 31（34）: 163-170.
Wu Tian, Ruan Jiangjun, Hu Yi, et al. Study on forest fire induced breakdown of 500 kV transmission line in terms of

characteristics and mechanism［J］.Proceedings of the CSEE,2011,31（34）：163-170.
［7］宋嘉婧，郭创新，张金江，等. 山火条件下的架空输电线路停运概率模型［J］. 电网技术，2013，37（1）：100-105.
Song Jiajing, Guo Chuangxin, Zhang Jinjiang, et al. A probabilistic model of overhead transmission line outage due to forest

fire［J］. Power System Technology, 2013, 37（1）: 100-105.
［8］Mphale K, Heron M, Ketlhwaafetse R, et al. Interferometry measurement of ionization in a grassfire［J］. Meteorology and

Atmospheric Physics, 2010, 106（2-3）: 191-203.
［9］Naidoo P, Swift D A. Large particle initiated breakdown of an atmospheric air gap: relating to AC power line faults

caused by sugar cane fires ［C］//The 8th International Symposium on High Voltage, Engineering. Yokohama, 1993.
［10］Kim I. Flashover characteristics of vertical-type model power line in the presence of combustion flash［J］. Journal of

the Korean Institute of Illuminating and Electrical Installation Engineer, 2009, 23（5）: 58-65.
［11］李家国，顾行发，余涛. 澳大利亚东南部森林山火HJ卫星遥感监测［J］. 北京航空航天大学学报, 2010, 36（10）: 1221-1224.
Li Jiaguo, Gu Xingfa, Yu Tao. Detection of Australian southeast forest fire using HJ satellite［J］.Journal of Beijing

University of Aeronautics and Astronautics, 2010,36（10）:1221-1224.
［12］梁允，李哲，曲燕燕，等. 极轨气象卫星在输电线路防山火监测中的应用［J］. 河南科学，2013，31（10）: 1664-1667.
Liang Yun, Li Zhe, Qu Yanyan, et al. The polar orbit meteorological satellite and its application in monitoring mountain fire

for transmission line［J］.Henan Science,2013，31（10）:1664-1667.
［13］雷国伟，何伟明，林健枝. 架空输电线路走廊防山火综合监测系统实现与应用［J］. 电气技术，2013（12）:112-115.
［14］王海晖，朱霁平，姜伟，等.森林地表火行为估算的数学模型［J］.火灾科学，1994，3（1）：33-41.
Wang Haihui, Zhu Jiping, Jiang Wei, et al. A mathematical model for estimating surface fire behavior［J］. Fire Safety

Science, 1994,3（1）:33-41.
［15］Byram G M.Combustion of forest fuels［M］.New York，USA：McGraw Hil，1959：61-89.
［16］张景忠，肖非，廉明起.林火行为相关参数综合测报仪的研究［J］.东北林业大学学报，2000，28（6）：112-115.
Zhang Jingzhong, Xiao Fei, Lian Mingqi. The comprehensive measuring instrument of parameters relating to forest fire behavior

［J］.Journal of Northeast Forestry University,2000,28（6）:112-115.
［17］Huang N E，Shen Z，Long S R, et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-

stationary time series analysis［J］.Proceedings of the Royal Society London A，1998（454）：903-995.
［18］袁琦，周卫东，李淑芳，等.基于ELM 和近似熵的脑电信号检测方法［J］.仪器仪表学报，2012，33（3）：514-519.
Yuan Qi, Zhou Weidong, Li Shufang, et al. Approach of EEG detection based on ELM and approximate entropy［J］. Chinese

Journal of Scientific Instrument,2012,33（3）:514-519.
［19］Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and application［J］. Neurocomputing, 2006, 70（1-3）:

489-501.