输电线路导线覆冰AMPSO-BP神经网络预测模型

doi:10.12204/j.issn.1000-7229.2021.09.015

摘要/Abstract

摘要：

输电线路覆冰严重危害电网安全运行,因此,有必要开展线路覆冰预测研究。随着人工智能技术的不断发展,其在电网覆冰监测中的优势逐渐凸显。现有的基于覆冰增长物理模型和统计回归模型覆冰预测方法,一定程度上实现了通过微气象等因素预测覆冰增长的效果,但大都针对短期覆冰周期,对数据采集频率有很高的要求,实际工程中实现较为困难。因此文章统计分析了重庆市送变电公司2015—2019年线路观冰数据,得到了西南地区高湿环境下输电线路覆冰特性及规律,并依据覆冰增长物理过程选取了工程可测量气象参数作为覆冰影响因素,提出了一种基于自适应变异粒子群算法(adaptive mutation particle swarm optimization algorithm,AMPSO)优化BP神经网络的人工智能覆冰厚度预测模型,优化了BP神经网络的权值阈值选取,优化后的模型在预测精度上要强于单一BP神经网络与已有研究中提出的小波神经网络,具有良好的工程适用性。

关键词: 人工智能, 线路覆冰厚度预测, 自适应变异, BP神经网络

Abstract:

Icing of transmission line seriously threatens the safe operation of power system. Therefore, it is necessary to investigate icing prediction of transmission lines. With the development of its performance, artificial intelligence technology gradually shows advantages in power grid icing monitoring. To a certain extent, the existing statistical regression model of ice thickness prediction for transmission line can partly predict the ice accretion growth. However, these traditional models are only suitable for short icing periods and difficult to realize in actual engineering because of their requirement of high data acquisition frequency. This research collected the transmission line's ice observation data from 2015 to 2019 got by Chongqing Transmission and Transformation Engineering Co, Ltd.. By analyzing the data, the characteristics and rules of transmission line icing under high humidity environment in southwestern China are obtained. Then, according to the ice growth's physical process on transmission line, the research selects measurable parameters in practical work as the impact factor of ice accretion growth. On this basis, an artificial intelligence ice-thickness prediction model based on adaptive mutation particle swarm optimization (AMPSO) is proposed. According to the training results, the AMPSO-BP neural network is more accurate and reliable on ice thickness prediction, compared to the traditional BP neural network.

Key words: artificial intelligence, ice thickness prediction of transmission line, adaptive mutation, BP neural network

中图分类号:

TM75

李贤初, 张翕, 刘杰, 胡建林. 输电线路导线覆冰AMPSO-BP神经网络预测模型[J]. 电力建设, 2021, 42(9): 140-146.

LI Xianchu, ZHANG Xi, LIU Jie, HU Jianlin. Prediction of Transmission Line Icing Thickness Applying AMPSO-BP Neural Network Model[J]. ELECTRIC POWER CONSTRUCTION, 2021, 42(9): 140-146.

图/表 12

表1 输电线路覆冰增长影响因素

Table 1 Factors of transmission line icing growth

图1 日最低温度与单日覆冰增长厚度相关分析

Fig.1 Correlation analysis between daily minimum temperature and daily ice accretion thickness

图2 风速与单日覆冰增长厚度的相关分析

Fig.2 Correlation analysis between wind speed and daily ice accretion thickness

图3 空气相对湿度与单日覆冰增长厚度相关分析

Fig.3 Correlation analysis between air humidity and daily ice accretion thickness

表2 天气状况类别数据转换表

Table 2 Data conversion table of weather condition categories

图4 天气状况与日覆冰增长厚度的相关分析

Fig.4 Correlation analysis between weather condition category and daily ice accretion thickness

图5 基础覆冰厚度与单日覆冰增长的相关分析

Fig.5 Correlation analysis between basic icing thickness and daily ice accretion thickness

表3 基础覆冰厚度与单日覆冰增长相关数据

Table 3 Analysis of basic icing thickness and daily ice accretion thickness

图6 AMPSO-BP神经网络结构

Fig.6 Structure diagram of AMPSO-BP neural network

表4 模型覆冰预测结果

Table 4 Prediction results of the modelmm

图7 模型覆冰预测结果

Fig.7 Icing prediction results of the model

表5 3种预测方法的误差统计

Table 5 Error statistics of three prediction methods

参考文献 22

[1]	孙才新. 大气环境与电气外绝缘[M]. 北京: 中国电力出版社, 2002.
[2]	何明慧. 基于进化算法的神经网络研究与优化[D]. 合肥: 安徽大学, 2018.
	HE Minghui. Research and optimization of neural network based on evolutionary algorithm[D]. Hefei: Anhui University, 2018.
[3]	GOODWIN E J, MOZER J D, GIOIA A M D. Predicting ice and snow loads for transmission line[R]. Proceedings of the First IWAIS, 1983.
[4]	MAKKONEN L. Modeling of ice accretion on wires[J]. Journal of Climate and Applied Meteorology, 1984, 23(6):929-939.
[5]	蒋兴良, 姜方义, 汪泉霖, 等. 基于最优时间步长模型的输电导线雾凇覆冰预测[J]. 电工技术学报, 2018, 33(18):4408-4418.
	JIANG Xingliang, JIANG Fangyi, WANG Quanlin, et al. Prediction of rime accretion on transmission line based on optimal time step model[J]. Transactions of China Electrotechnical Society, 2018, 33(18):4408-4418.
[6]	庄文兵, 祁创, 熊小伏, 等. 计及气象因素时间累积效应的输电线路覆冰预测[J]. 电力系统保护与控制, 2019, 47(17):6-13.
	ZHUANG Wenbing, QI Chuang, XIONG Xiaofu, et al. Transmission line icing forecast considering the time cumulative effect of meteorological factors[J]. Power System Protection and Control, 2019, 47(17):6-13.
[7]	阳林, 郝艳捧, 黎卫国, 等. 架空输电线路在线监测覆冰力学计算模型[J]. 中国电机工程学报, 2010, 30(19):100-105.
	YANG Lin, HAO Yanpeng, LI Weiguo, et al. A mechanical calculation model for on-line icing-monitoring system of overhead transmission lines[J]. Proceedings of the CSEE, 2010, 30(19):100-105.
[8]	GOODWIN E J III, MOZER J D, DIGIOIA A M J, et al. Predicting ice and snow loads for transmission lines design[C]// Proceedings First IWAIS, Hanover, HN, USA: IAC, 1983: 267-273.
[9]	张暕. 架空输电线路覆冰机理及预测模型的研究[D]. 北京: 华北电力大学, 2018.
	ZHANG Jian. Research on mechanism and prediction model of icing on overhead transmission lines[D]. Beijing: North China Electric Power University, 2018.
[10]	邓亚琪, 刘晓欣, 姜燕波, 等. 高海拔地区输电线路覆冰机理及除防冰技术研究[J]. 电工技术, 2017(7):55-57, 88.
[11]	郑振华, 刘建生. 遗传算法与BP神经网络相结合的输电线路覆冰厚度预测方法[J]. 电网与清洁能源, 2014, 30(4):27-30, 35.
	ZHENG Zhenhua, LIU Jiansheng. Prediction method of ice thickness on transmission lines based on the combination of GA and BP neural network[J]. Power System and Clean Energy, 2014, 30(4):27-30, 35.
[12]	谢勇. 基于支持向量机的输电线覆冰预测研究[D]. 成都: 西华大学, 2016.
	XIE Yong. Icing forecast of power lines based on support vector machine[D]. Chengdu: Xihua University, 2016.
[13]	游朗. 输电线路覆冰厚度短期预测模型研究[D]. 北京: 华北电力大学, 2017.
	YOU Lang. Research on short-term prediction models of ice thickness of transmission line[D]. Beijing: North China Electric Power University, 2017.
[14]	赵建坤. 架空输电线路覆冰厚度预测模型研究[D]. 北京: 华北电力大学, 2016.
	ZHAO Jiankun. Research on icing thickness prediction model of overhead transmission lines[D]. Beijing: North China Electric Power University, 2016.
[15]	焦晗, 黄陈蓉, 李焱飞. 基于PSO-RBF的输电线路覆冰预测研究[J]. 电工电气, 2018(6):33-36.
	JIAO Han, HUANG Chenrong, LI Yanfei. Prediction research on transmission line icing based on particle swarm optimization-radial basis function[J]. Electrotechnics Electric, 2018(6):33-36.
[16]	MATSUSHITA T, NISHIO F. Localinfluence on occurrence of freezing rain and precipitation icing in Japan[C]// 17th International Workshop on Atmospheric Icing of Structures (IWAIS). 2017.
[17]	VEAL A, SKEA A. Method of forecasting icing by meteorology modelC]// [17th International Workshop on Atmospheric Icing of Structures (IWAIS). Montreal: Canada, 2017.
[18]	董海霞, 邹杰. 基于AMPSO算法的无人机任务分配问题研究[J]. 电光与控制, 2018, 25(2):28-32.
	DONG Haixia, ZOU Jie. Multi-UAV task allocation based on AMPSO algorithm[J]. Electronics Optics & Control, 2018, 25(2):28-32.
[19]	孙朋杰. 导线覆冰气象参数模型的研究与验证[D]. 南京: 南京信息工程大学, 2012.
	SUN Pengjie. An icing conductor model based on meteorological parameters and its verification[D]. Nanjing: Nanjing University of Information Science & Technology, 2012.
[20]	马天男. 基于大数据的电网覆冰灾害预测与风险管理研究[D]. 北京: 华北电力大学, 2017.
	MA Tiannan. Prediction and risk management of power grid icing disaster based on big data[D]. Beijing: North China Electric Power University, 2017.
[21]	任源. 基于改进粒子群算法的输电线路覆冰研究[D]. 西安: 西安理工大学, 2019.
	REN Yuan. Research on transmission line ice coating based on improved particle swarm optimization[D]. Xi'an: Xi'an University of Technology, 2019.
[22]	杨静, 李英娜, 赵振刚, 等. 基于相空间重构小波神经网络的短期覆冰预测[J]. 传感器与微系统, 2019, 38(9):108-111.
	YANG Jing, LI Yingna, ZHAO Zhengang, et al. Short-term icing forecasting based on phase space reconstruction wavelet neural network[J]. Transducer and Microsystem Technologies, 2019, 38(9):108-111.