论文部分内容阅读
引入改进的粒子群算法对小波核函数最小二乘支持向量机进行优化,提出了位移时间序列预测的改进粒子群优化小波最小二乘支持向量机预测模型(APSO-WLSSVM)。该模型具有小波变换的良好时、频域分辨能力和支持向量机的非线性学习能力;同时利用粒子群算法优化小波最小二乘支持向量机的参数,避免了人为选择参数的盲目性,从而提高了模型的预测精度。为证明该模型的优越性,将该模型与传统的高斯核函数支持向量机模型的预测结果作了对比,结果表明该模型较传统方法预测精度有了明显提高。最后将该模型用于锦屏一级水电站左岸边坡和导流洞进行变形预测,预测结果表明该方法科学可靠,在岩土体位移时序预测中具有良好的实际应用价值。
An improved Particle Swarm Optimization (PSO) algorithm is proposed to optimize the least-squares support vector machine (SVM) based on wavelet kernel function. An improved Particle Swarm Optimization (LS-SVM) prediction model based on APSO-WLSSVM is proposed. The model has good time-frequency domain discrimination ability of wavelet transform and nonlinear learning ability of SVM. At the same time, the particle swarm optimization algorithm is used to optimize the parameters of wavelet LS-SVM, which avoids the blindness of artificial selection parameters and enhances The model’s prediction accuracy. In order to prove the superiority of this model, this model is compared with the prediction of the traditional Gaussian kernel SVM model. The results show that this model has significantly improved the prediction accuracy compared with the traditional method. Finally, the model is applied to the deformation prediction of left bank slope and diversion tunnel of Jinping I Hydropower Station. The prediction results show that the method is scientific and reliable, and has good practical application value in predicting displacement sequence of rock and soil mass.