吴晨曦,李博亚,孙弼洋,钟素鹏
WU Chenxi,LI Boya,SUN Biyang,ZHONG Supeng

• 1:国网浙江省电力有限公司超高压分公司

摘要(Abstract)：

为提高输电线路状态评估的准确率，提出一种先聚类再回归的输电线路状态画像与评估模型。首先，设计自组织神经网络对输电线路原始数据进行降维，自适应地提取若干类代表性特征信息，无需人工提取特征和依据主观经验选择聚类数；然后，将代表性特征数据输入LSTM（长短期记忆）网络中，LSTM网络将前向学习和反向学习相结合，对模型进行双向训练与评估，建立输电线路核心数据与状态的非线性映射关系，提高电网场景下的输电线路状态评估准确率。实验结果表明，所提模型在实际数据集上取得了较好的评估效果，评估准确率高于常用的支持向量机、人工神经网络、稀疏自动编码机等方法。
To improve the transmission line status evaluation accuracy,the paper proposes a transmission line status portrait and assessment model based on clustering and later regression. Firstly,the self-organizing neural network(SONN)is designed to reduce the dimensionality of the original data of the transmission lines and to adaptively extract several types of representative feature information without manual feature extraction and selection of the number of clusters based on subjective experience. Secondly,the representative data is fed into the LSTM(long shortterm memory)networks. The networks combine forward learning and reverse learning to conduct bidirectional training,evaluate the model,establish the nonlinear mapping relationship between the core data and the transmission line state,and improve the evaluation accuracy of the state of the transmission line in the power grid scenario. The experimental results show that the model proposed in this paper has achieved good evaluation results on the actual data set;specifically,it is superior to conventional support vector machine,artificial neural network,sparse automatic encoding machine,and other methods in evaluation accuracy.

关键词(KeyWords)： 输电线路状态评估;双向长短期记忆网络;自组织神经网络;降维
transmission line status assessment;bidirectional long short-term memory network;self-organizing neural network;dimension reduction

Abstract:

Keywords:

基金项目(Foundation): 国网浙江省电力有限公司科技项目（5211MR20004V）

作者(Author): 吴晨曦,李博亚,孙弼洋,钟素鹏
WU Chenxi,LI Boya,SUN Biyang,ZHONG Supeng

DOI: 10.19585/j.zjdl.202210005

参考文献(References)：

• [1] RAMOS G,SANCHEZ J L,TORRES A,et al. Power systems security evaluation using Petri nets[J]. IEEE Transactions on Power Delivery,2009,25(1):316-322.
• [2]祝贺.输电塔脉动风时程模拟的自回归模型技术[J].浙江电力，2006,25(2):6-8.
• [3]李立浧.基于层次分析法的架空输电线路状态评估[J].电气时代，2020(2):30-32.
• [4] HAO Y P,YAO Z H,WANG J K,et al.A classification method for transmission line icing process curve based on hierarchical K-means clustering[J].Energies,2019,12(24):4786.
• [5]胡志坤，赵超越，王振东，等.基于边缘计算和无人机巡检图像的输电杆塔关键部位隐患智能识别[J].浙江电力，2020,39(10):21-27.
• [6] GUI P,JIANG Y W,ZANG D,et al.Assessing the depth of language processing in patients with disorders of consciousness[J].Nature Neuroscience,2020,23(6):761-770.
• [7] XU Y Q,FANG M,CHEN L,et al.Reinforcement learning with multiple relational attention for solving vehicle routing problems[J].IEEE Transactions on Cybernetics,2022,52(10):11107-11120.
• [8]杨挺，赵黎媛，王成山.人工智能在电力系统及综合能源系统中的应用综述[J].电力系统自动化，2019,43(1):2-14.
• [9]王艳艳，张文正，沈佳辉，等.基于机器学习的云平台故障排查方法[J].浙江电力，2021,40(12):124-130.
• [10]张琦，韩祯祥，曹绍杰，等.用于暂态稳定评估的人工神经网络输入空间压缩方法[J].电力系统自动化，2001,25(2):32-35.
• [11]石万宇，魏军强，赵云灏.基于改进麻雀算法-支持向量机的输电线路故障诊断[J].浙江电力，2021,40(11):38-45.
• [12] AUGUTIS J,ZUTAUTAITE I,RADZIUKYNAS V,et al.Application of bayesian method for electrical power system transient stability assessment[J].International Journal of Electrical Power&Energy Systems,2012,42(1):465-472.
• [13] JIANG P,LI R R,LIU N N,et al.A novel composite electricity demand forecasting framework by data processing and optimized support vector machine[J].Applied Energy,2020(1):114243.
• [14]赵凯，侯玉强.基于自组织映射神经网络K-means聚类算法的风电场多机等值建模[J].浙江电力，2019,38(8):30-36.
• [15] LIANG H Q,LIU Y D,SHENG G H,et al.Fault-cause identification method based on adaptive deep belief network and time-frequency characteristics of travelling wave[J].IET Generation,Transmission&Distribution,2019,13(5):724-732.
• [16] ZHAI Y J,YANG X,WANG Q M,et al.Hybrid knowledge R-CNN for transmission line multifitting detection[J].IEEE Transactions on Instrumentation and Measurement,2021(3):1-12.
• [17] ZHENG C,WANG S R,LIU Y L,et al.A novel equivalent model of active distribution networks based on LSTM[J].IEEE transactions on Neural Networks and Learning Systems,2019,30(9):2611-2624.
• [18] WICKRAMASINGHE C S, AMARASINGHE K,MANIC M. Deep self-organizing maps for unsupervised image classification[J]. IEEE Transactions on Industrial Informatics,2019,15(11):5837-5845.
• [19]卞蓓蕾，江炯，刘鹏.输电线路人机协同立体巡检系统设计[J].浙江电力，2022,41(5):61-68.
• [20]葛晓琳，史亮，刘亚，等.考虑需求响应不确定性的电动汽车负荷Sigmoid云模型预测[J].中国电机工程学报，2020,40(21):6913-6925.
• [21]国家电网公司.架空输电线路运行状态评估技术导则：DL/T 1249—2013[S].北京：中国电力出版社，2013.