基于KPCA-ISHO-LSSVM的接地网腐蚀速率预测

为了提高接地网腐蚀速率预测精度，利用核主成分分析法对接地网腐蚀速率的主元进行提取，依据KPCA分析结果进行了指标重构，减少了接地网腐蚀预测模型建模工作量。通过收敛因子非线性调整及莱维飞行策略对斑点鬣狗算法进行改进，基于改进后的斑点鬣狗算法对最小二乘支持向量机的惩罚参数和核函数参数进行优化，建立了基于KPCA-ISHO-LSSVM的接地网腐蚀速率预测模型。仿真结果表明，经ISHO优化LSSVM接地网腐蚀速率预测模型的平均相对误差、均方根误差、全局最大相对误差均定系数分别为2.79%、0.139、3.53%和0.995，均优于其他接地网腐蚀预测模型，验证了模型的正确性和优越性。

Corrosion Rate Prediction of Grounding Grid Based on KPCA-ISHO-LSSVM

In order to improve the prediction accuracy of grounding grid corrosion rate， the paper uses kernel principal component analysis to extract the principal component of the grounding grid corrosion rate， and carries out index reconstruction according to KPCA analysis results， reducing the modeling workload of the grounding grid corrosion prediction model. In addition， the improved spotted hyena optimization （ISHO） algorithm is obtained by using the nonlinear adjustment of convergence factor and Levy flight strategy. The penalty parameters and kernel function parameters of least squares support vector machine （LSSVM） are optimized by ISHO， and the corrosion rate prediction model of the grounding grid based on KPCA-ISHO-LSSVM is established. The simulation results show that the average relative error， root mean square error and global maximum relative error of LSSVM grounding grid corrosion rate prediction model optimized by ISHO are 2.79%， 0.139%， 3.53% and 0.995 respectively， which are better than other grounding grid corrosion prediction models， verifying the correctness and superiority of the model.