基于PSO-SVM模型的面板堆石坝堆石料参数反演分析  

Application of PSO-SVM Model in Parameter Inversion Analysis of Face Rock-fill Dam's Rock-fill

作　　者：肖兵[1] 宋志诚[1] 屠丹[1] 李华斌[1] 张胜利 

机构地区：[1]三峡大学水利与环境学院,湖北宜昌443002

出　　处：《水电能源科学》2015年第3期54-56,共3页Water Resources and Power

摘　　要：针对常用的参数反演分析法存在的不足,将粒子群算法(PSO)与支持向量机(SVM)相结合来对堆石料参数进行反演,即先利用粒子群算法优化支持向量机,再利用优化后的支持向量机进行参数反演分析,借助Matlab中相关工具箱编制了相应的程序,建立了基于PSO-SVM的堆石料参数反演模型,并通过大量实测数据进行训练和测试。结果表明,基于PSO-SVM的堆石料参数反演模型可行、有效。Aiming at the shortcomings of common parameter inversion analysis method,combined PSO with SVM is used to inverse the parameters of rock-fill.Firstly,particle swarm optimization algorithm is used to optimize support vector machine.And then the parameter inversion analysis is implemented by using the optimized support vector machine.The program is developed by using Matlab toolbox.The parameter inversion model of rock-fill based PSO-SVM is established.The proposed model is trained and tested by a large number of measured data.The results show that the proposed model is feasible and effective.

关 键 词：堆石料 粒子群算法 支持向量机 参数反演分析 

分 类 号：TV641.4[水利工程—水利水电工程]