|
|||||
|
|
| PSO-GM模型在拱坝变形预报中的应用 | |
| 引用本文： | 王宝强,崔伟杰,温毓繁,张栋梁,张林海.PSO-GM模型在拱坝变形预报中的应用[J].三峡大学学报(自然科学版),2014,36(5):23-27. |
| 作者姓名： | 王宝强 崔伟杰 温毓繁 张栋梁 张林海 |
| 作者单位： | 1. 河海大学水文水资源与水利工程科学国家重点实验室,南京 210098;河海大学水资源高效利用与工程安全国家工程研究中心,南京 210098;河海大学水利水电学院,南京 210098 2. 雅砻江流域水电开发有限公司,成都,610000 3. 河海大学水利水电学院,南京,210098 4. 辽宁省东水西调工程建设局,辽宁铁岭,112000 |
| 基金项目： | 国家自然科学基金资助项目，新世纪优秀人才支持计划资助，高等学校博士学科点专项科研基金，中央高校基本科研业务费项目 |
| 摘 要： | 用PSO-GM模型来预测了拱坝变形情况.该模型通过粒子群算法优化灰色模型中背景值的权重系数r和指数灰元N,既保留了灰色模型要求样本数据少、短期预测精度高、可检验等优点,又弱化了线性GM(1,1)模型对累加生成的数据序列须成一定指数规律变化的要求,从而更具普遍性.通过工程实例计算验证可知,PSO-GM模型无论拟合精度还是预测精度都较一般线性灰色GM(1,1)模型好,可以为坝体位移监测提供参考. |
| 关 键 词： | PSO-GM模型 优化 拱坝变形 拟合 预测 |
Application of PSO-GM Model to Prediction of Arch Dam Deformation |
|
| Wang Baoqiang,Cui Weijie,Wen Yufan,Zhang Dongliang,Zhang Linhai.Application of PSO-GM Model to Prediction of Arch Dam Deformation[J].Journal of China Three Gorges University(Natural Sciences),2014,36(5):23-27. | |
| Authors: | Wang Baoqiang Cui Weijie Wen Yufan Zhang Dongliang Zhang Linhai |
| Institution: | Wang Baoqiang Cui Weijie Wen Yufan Zhang Dongliang Zhang Linhai (1. State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering, Hohai Univ. , Nanjing 210098, China; 2. National Engineering Research Center of Water Resources Efficient Utilization and Engi- neering Safety, Hohai Univ. , Nanjing 210098, China; 3. College of Water Conservancy Hydropower En- gineering, Hohai Univ. , Nanjing 210098, China; 4. Yalong River Hydropower Development Co. , Ltd. , Chengdu 610000, China; 5. Liaoning Province East-to-West Water Diversion Building and Construction Au- thority, Tieling 112000,China) |
| Abstract: | The deformation of arch dam is predicted by PSO-GM model. In order to weaken the exponential dependence requisition of data sequence generated by accumulation, the particle swarm optimization（PSO） is applied to optimize the parameters which are called the weight coefficient r and the index of grey-element N in GM model. The new model not only has high prediction precision with small and short-term sample, but also has more adaptability. The experimental results indicate that the PSO-GM model in the aspect of fitting preci- sion and prediction precision is better than the GM（1,1） model, so as to provide a reference for dam dispalce- ment monitoring. |
| Keywords: | PSO-GM model optimization deformation of arch dam fitting prediction |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |