论文部分内容阅读
为提高露天矿边坡变形预测精度,利用协同进化粒子群(CEPSO)优化多核相关向量机(MK-RVM)的参数,构建协同进化多核相关向量机(CEPSO-MK-RVM),并将此模型应用于露天矿边坡变形预测。将CEPSO-MK-RVM的结果与协同进化多项式核函数相关向量机(CEPSO-PolyRVM)、协同进化高斯核函数相关向量机(CEPSO-Gauss-RVM)及修正果蝇优化下的支持向量回归(MFOA-SVR)的结果进行对比,并分析CEPSO对MK-RVM参数的优化效果。结果表明,CEPSO比标准粒子群优化(PSO)算法具有更好的优化效率及最优解;用CEPSO-MK-RVM模型得到的结果,4个精度指标均优于其余3种方法,边坡变形预测的精度得到有效提高。
In order to improve the prediction precision of slope deformation in open pit mine, the co-evolutionary multicomponent correlation vector machine (CEPSO-MK-RVM) was optimized by using the co-evolutionary particle swarm optimization (CEPSO) Applied to slope deformation prediction of open pit mine. The results of CEPSO-MK-RVM were compared with CEPSO-PolyRVM, CEPSO-Gaussian-RVM and modified MFOA -SVR), and analyzed the optimization effect of CEPSO on MK-RVM parameters. The results show that the CEPSO has better optimization efficiency and better solution than the standard Particle Swarm Optimization (PSO) algorithm. The results of the CEPSO-MK-RVM model show that the four precision indexes are better than the other three methods. The slope deformation The accuracy of prediction is effectively improved.