基于IAOA-LSSVM的输电线路覆冰厚度预测研究  

Research on transmission line icing thickness prediction based on IAOA-LSSVM

作　　者：涂婧琳 王洪亮[1] TU Jinglin;WANG Hongliang(Faculty of Civil Aviation and Aeronautics,Kunming University of Science and Technology,Kunming 650500,China)

机构地区：[1]昆明理工大学民航与航空学院,云南昆明650500

出　　处：《现代电子技术》2024年第21期113-118,共6页Modern Electronics Technique

基　　金：国家自然科学基金项目(62163021);云南省基础研究专项(202301AT070420)。

摘　　要：为民用机场提供电力支撑的场外输电线路一旦线体外表面覆冰达到了一定厚度,易导致输电导线舞动甚至损坏电力设备,影响民用机场的运行。为了能够给机场提供更稳定的电力支撑,保证机场电力设施的稳定运行,提出改进算术优化算法优化最小二乘法支持向量机(IAOA-LSSVM)的输电线路覆冰厚度预测模型,引入双曲正切因子并结合Lévy飞行策略改进算术优化算法,通过IAOA算法不断优化LSSVM模型中的正则化参数C与核函数参数σ,最后使用实测所得的气象数据及覆冰厚度数据对改进后的预测模型进行验证,并与优化前的预测模型及其他常用模型进行仿真对比,实验结果表明:IAOA-LSSVM预测模型精度更高,证明了该方法在输电线路覆冰厚度的预测运用中的较高准确性。Once the off-site transmission line that provides power support for civil airports reaches a certain icing thickness,it is prone to causing the transmission wires to brandish and even damaging the power equipment,affecting the operation of civil airports.In order to provide more stable power support for the airport and ensure the stable operation of the airport's power facilities,a transmission line icing thickness prediction model based on the least squares support vector machine optimized by improved arithmetic optimization algorithm(IAOA-LSSVM)is proposed.The hyperbolic tangent factor combined with the Lévy flight strategy is introduced to improve the arithmetic optimization algorithm(AOA).The improved AOA(IAOA)algorithm is used to continuously optimize the regularization parameter C and the kernel function parameterσin the LSSVM model.Finally,the measured meteorological data and icing thickness data are used to verify the improved prediction model.The improved prediction model is simulated and contrasted with the prediction model before optimization and the other commonly used models.The experimental results show that the IAOA-LSSVM prediction model has the highest accuracy,which proves that the proposed method has high accuracy in the prediction of transmission line icing thickness.

关 键 词：算术优化算法 覆冰厚度 输电线路 最小二乘法支持向量机 覆冰预测 Lévy飞行策略 

分 类 号：TN709-34[电子电信—电路与系统] TM75[电气工程—电力系统及自动化]