摘要
电缆接头绝缘劣化会导致热损耗的增加进而引起接头表面温度上升,同时表面温度受到运行负荷、环境温度等多方面因素的影响,总体上劣化程度与温度数据表现出非线性分布的情况。为此,提出了基于改进麻雀搜索算法(Improved Sparrow Search Algorithm, ISSA)优化的核极限学习机(Kernel Based Extreme Learning Machine, KELM)的电缆接头绝缘劣化程度预测方法。首先通过实验来验证电缆接头多物理耦合模型的计算准确性,并通过耦合计算模型来获取不同劣化程度、载荷和环境温度下的电缆接头表面温度分布,用于构建训练集、验证集和测试集。其次基于鸟群算法(Bird Swarm Algorithm, BSA)中飞行行为的思想优化麻雀搜索算法,保证了全局收敛又不失种群多样性,有效跳出局部最优。然后通过ISSA算法对KELM的惩罚系数C和核函数σ进行优化,得到绝缘劣化状态预测模型。研究结果表明,改进麻雀算法优化的核极限学习机(ISSA-KELM)的预测效果明显优于其他模型。
The deterioration of cable joints will lead to the increase of heat loss, and then lead to the rise of surface temperature of the joints.At the same time, the surface temperature is affected by many factors such as operating load, environmental temperature.In general, the relationship between deterioration degree and temperature data shows a non-linear distribution.For this reason, a prediction method based on improved sparrow search algorithm(ISSA) optimization for kernel extreme learning machine(KELM) is proposed to predict the insulation deterioration degree of cable joints.Firstly, based on the experimental validation of the multi-physical coupling model of cable joints, the surface temperature distribution data of cable joints at different deterioration levels, loads and ambient temperatures are obtained for building the training set, validation set and test set.Secondly, the sparrow search algorithm is optimized based on the idea of flight behavior in the bird swarm algorithm(BSA),which ensures global convergence without losing population diversity and effectively jumps out of local optimum.Then, ISSA algorithm is used to optimize the penalty coefficient C and the kernel function σ of KELM and the prediction model of insulation deterioration state is obtained.Research results show that the predictive effect of ISSA-KELM is much better than that of other models.
作者
徐四勤
黄向前
杨昆
张占龙
甘鹏飞
XU Si-qin;HUANG Xiang-qian;YANG Kun;ZHANG Zhan-long;GAN Peng-fei(Anqing Power Supply Company,State Grid Anhui Electric Power Co.,Ltd,Anqing,Anhui 246000,China;State Key Laboratory of Power Transmission Equipment&System Security and New Technology,Chongqing University,Chongqing 400044,China)
出处
《计算机科学》
CSCD
北大核心
2022年第10期132-137,共6页
Computer Science
基金
国网安徽省电力有限公司科技项目(5212D019015A)。
关键词
电缆接头
绝缘劣化
麻雀搜索算法
核极限学习机
Cable joints
Insulation deterioration
Sparrow search algorithm
Kernel extreme learning machine
