| 基于遗传退火算法进化神经网络的水位预测 |
| |
| 引用本文： | 丁红,董文永,李湘晖,李培冀.基于遗传退火算法进化神经网络的水位预测[J].柳州师专学报,2014(2):129-132. |
| |
| 作者姓名： | 丁红 董文永 李湘晖 李培冀 |
| |
| 作者单位： | [1]武汉理工大学信息工程学院,湖北武汉430070 [2]柳州师范高等专科学校数学与计算机科学系,广西柳州545005 [3]武汉大学计算机学院,湖北武汉430072 [4]柳州市防洪排涝工程管理处,广西柳州545002 |
| |
| 基金项目： | 国家自然科学基金资助项目（11161029）、国家自然科学基金资助项目（61170305）、国家自然科学基金资助项目（60873114）、广西教育厅项目（201204LX501）共同资助. |
| |
| 摘 要： | 为获得更准确的预测结果及更优良的预测性能,本文提出了一个新模型.该模型将遗传算法和退火相结合并进化BP神经网络,称为GASANN模型.通过预测中国广西柳江年水位数据,将新模型的性能与加权移动平均(WMA)、逐步回归(SR)以及自回归移动平均(ARIMA)进行比较,结果显示新模型性能优于其他模型.因此,该非线性模型可作为获取准确水位预测及改善水位预测性能的可选模型之一.
|
| 关 键 词： | 遗传算法 退火算法 BP神经网络 水位预测 |
Neural Network Based on Genetic Algorithm and Anneal Algorithm for Water Level Prediction |
| |
| Ding Hong,Wenyong Dong,Li Xianghui,Li Peiji.Neural Network Based on Genetic Algorithm and Anneal Algorithm for Water Level Prediction[J].Journal of Liuzhou Teachers College,2014(2):129-132. |
| |
| Authors: | Ding Hong Wenyong Dong Li Xianghui Li Peiji |
| |
| Institution: | 1. School of Information Engineering, Wuhan University of Technology, Wuhan, Hubei, 430070 China ; 2. Department of Mathematics and Computer science, Liuzhou Teachers College, Liuzhou, Guangxi, 545004 China; 3. Computer School, Wuhan University, Wuhan, Hubei, 430070 China; 4. Liuzhou City Flood Control and Drainage Project Management Office, Liuzhou, Guangxi, 545002 China) |
| |
| Abstract: | In order to obtain more accurate forecasting result of runoff, a novel model has been proposed in this paper, which was a BP neural network based on genetic algorithm and anneal algorithm （GASANN）. During the forecasting the yearly water level of Liujiang River in Guangxi, the method has been compared with three individual forecasting models, such as weighted moving average （WMA） , stepwise regression （SR） and auto regression integrated moving average （ARIMA）. It was noticed that the presented method was superior to the other models presented in this study in terms of the same evaluation measurements. Therefore the nonlinear ensemble model pro- posed can be used as an alternative forecasting tool for water level. |
| |
| Keywords: | Genetic algorithm Anneal algorithm BP neural network Water level forecasting |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
