基于多尺度时空特征深度融合神经网络的输电线路火点判识方法  

Wildfire Identification Method for Transmission Lines Based on Deep Fusion Neural Network with Multi-scale Spatio-temporal Features

作　　者：王开正 周顺珍 王健 付一桐 周若涵 曾瑶 WANG Kaizheng;ZHOU Shunzhen;WANG Jian;FU Yitong;ZHOU Ruohan;ZENG Yao(Faculty of Electric Power Engineering,Kunming University of Science and Technology,Kunming 650500,China)

机构地区：[1]昆明理工大学电力工程学院,昆明650500

出　　处：《高电压技术》2025年第3期1145-1157,共13页High Voltage Engineering

基　　金：国家自然科学基金(52107017);云南省科技厅基础研究专项青年项目(202201AU070172)。

摘　　要：目前的输电线路山火卫星监测技术对火点的监测精度高,但仍有许多山火漏报和误报,尤其是小型山火。为弥补提取火点时空特征方面的不足,该文提出了一种基于多尺度时空特征深度融合神经网络的输电线路火点判识方法。该算法首先根据Himawari-8(H-8)静止卫星的遥感数据,选取12个输入特征以构建多时空样本库。然后依据改进后的特征提取器Spatial-CNN(S-CNN)和Temporal-LSTM(T-LSTM)联合构建融合网络SCNN&TLSTM,以自动提取多尺度时空特征并融合后进行火点判识。与多种机器学习方法对比以验证网络的有效性,其中SVM、LSTM、CNN、Res-LSTM和Res-SPP总体精度分别为74.81%、77.61%、80.51%、84.13%和86.04%,然而SCNN&TLSTM能够提取更丰富的深层时空特征,总体精度可达90.61%。所提方法已应用于某省级电网输电线路山火监测,为保障电网安全稳定运行提供了可靠支撑。The current satellite wildfire monitoring technology for wildfires near transmission lines has high monitoring accuracy,but there are still many underreported and misreported wildfires,especially for small wildfire.To overcome the shortcomings in extracting spatio-temporal fire features,this paper proposes a wildfire identification method for transmis-sion lines based on a deep fusion neural network with multi-scale spatio-temporal features.This algorithm first selects 12 input features to construct a multi-temporal sample library based on remote sensing data from the Himawari-8(H-8)geo-stationary satellite.Then the fusion network SCNN&TLSTM is jointly constructed based on the improved feature extractor Spatial-CNN(S-CNN)and Temporal-LSTM(T-LSTM)to automatically extract the multi-scale spatio-temporal features and fuse them for the wildfire identification.A comparison with various machine learning methods is conducted to verify the effectiveness of the proposed network,where the overall accuracies of SVM,LSTM,CNN,Res-LSTM,and Res-SPP are 74.81%,77.61%,80.51%,84.13%and 86.04%,respectively.However,SCNN&TLSTM can extract richer deep spatio-temporal features,achieving an overall accuracy of 90.61%.The proposed method has been applied to wild-fire monitoring on transmission lines of a provincial power grid,providing reliable support to ensure the safe and stable operation of power grids.

关 键 词：输电线路山火 火点判识 时空特征 Himawari-8静止卫星 融合网络 SCNN&TLSTM 

分 类 号：TM75[电气工程—电力系统及自动化]