改进灰狼算法优化SVM的大坝变形预测  

Dam deformation prediction based on IGWO-SVM

作　　者：朱军桃 程胜[1,2] 邢尹 ZHUJun-tao;CHENG Sheng;XING Yin(College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China;Guangxi Key Laboratory of Spatial Information and Geomatics, Guilin University of Technology, Guilin 541006, China)

机构地区：[1]桂林理工大学测绘地理信息学院,广西桂林541006 [2]桂林理工大学广西空间信息与测绘重点实验室,广西桂林541006

出　　处：《桂林理工大学学报》2019年第3期669-673,共5页Journal of Guilin University of Technology

基　　金：国家自然科学基金项目(41071294);广西高校科学技术研究重点项目(ZD2014062)

摘　　要：为进一步提高大坝变形的预测精度,提出了一种改进的灰狼算法优化支持向量机预测模型。通过引入非线性收敛因子和采用动态加权策略,提升了灰狼算法优化支持向量机惩罚因子和核函数参数的能力,并以最优参数建立支持向量机大坝变形预测模型。选取实例数据,与布谷鸟算法、差分进化算法、粒子群算法和基本灰狼算法优化的支持向量机预测模型进行比较。实验结果表明,改进的灰狼算法对支持向量机参数的优化是有效的,基于此建立的模型预测效果良好,达到了提高大坝变形预测精度的目的。Precise prediction of dam deformation plays an important role in safety evaluation. In order to further improve accuracy of dam deformation prediction, an improved support vector machine is proposed. By introducing nonlinear convergence factor and adopting dynamic weighting strategy, grey wolf optimization is improved to search penalty factor and kernel function parameter of support vector machine, and the model is established with optimized parameters. The experimental results show that the improved grey wolf optimization is effective for parameters optimization of support vector machine, and it can improve the accuracy of dam deformation prediction.

关 键 词：变形监测 灰狼优化算法 支持向量机 

分 类 号：TV698.1[水利工程—水利水电工程]