基于PSO-SVM算法的输电线路覆冰舞动预测模型

Prediction model of galloping of iced transmission lines based on PSO-SVM algorithm

输电线路舞动往往会导致金具磨损、闪络、断线等电力事故,对电力系统的安全具有很大的负面影响。利用ANSYS软件模拟不同档距、风速等状态下覆冰四分裂导线在平均风与脉动风作用下的动态响应,进而根据模拟获得的数据集和PSO-SVM(particle swarm optimization-support vector machines)算法构建了四分裂导线覆冰舞动预警模型,将档距、风速、初始风攻角作为模型的输入,覆冰导线是否舞动作为输出。同时,为验证该预测模型的实用性及有效性,将PSO-SVM模型与其他智能算法如BP(back propagation)、支持向量机(support vector machine, SVM)、遗传算法优化支持向量机(genetic algorithm-optimization support vector, GA-SVM)模型的预测结果进行比较,结果表明PSO-SVM模型的预测结果精度更高,对输电线路覆冰舞动预警具有一定的参考意义。

Iced transmission line galloping often leads to electric power accidents, such as, hardware wear, flashover and disconnection, these accidents have a great negative impact on security of power system. Here, the finite element software ANSYS was used to simulate dynamic responses of iced quad-bundled conductor with different spans, wind speeds and other conditions under actions of average wind and fluctuating wind. Then, according to the simulated data set and PSO-SVM algorithm, an early warning model for galloping of iced quad-bundled conductor was established taking span, wind speed and initial wind attack angle as inputs of the model and whether iced conductor gallop as output. Meanwhile, in order to verify the practicability and effectiveness of this model, the prediction results of PSO-SVM model were compared with those of BP, SVM and GA-SVM models using other intelligent algorithms. The results showed that the prediction results of PSO-SVM model are more accurate;the prediction model based on PSO-SVM algorithm has a certain reference significance for early warning galloping of iced transmission lines.