基于PSO-LSSVM的过电压识别

为了获得理想的过电压识别结果，提出了粒子群优化算法优化最小二乘支持向量机参数的过电压识别方法。首先采用小波变换对过电压原始信号进行分解，提取过电压信号的特征量，然后将过电压信号的特征量作为最小二乘支持向量机的输入，建立过电压识别分类器，并采用粒子群优化算法估计最小二乘支持向量机的参数，最后采用实测的过电压数据进行仿真实验，测试其可行性。结果表明，本文方法可以对各种类型的过电压信号进行准确分类和识别，识别结果稳定，且过电压识别率要高于其它方法。

Over-voltage identification based on PSO-LSSVM

In order to obtain the ideal result of over-voltage identification, a novel over-voltage identification method is proposed based on using particle swarm optimization algorithm is used to optimize the parameters of least square support vector machine. Firstly, wavelet transform is used to decompose the original signal to extract feature parameters of over voltage signal, and secondly features of over-voltage signal is used as the inputs of least square support vector machine, and voltage identification model is established, and particle swarm optimization algorithm is used to estimate parameters of least square support vector machine, finally, simulation experiment is carried out by using the measured over voltage data, and the feasibility is tested. The results show that the proposed method can accurately classify and identify all kinds of over-voltage signals, the recognition results are stable, and the over voltage recognition rate is higher than other methods.