| 摘要: |
| 针对遗传算法和BP网络在寻优过程中的不足,将改进的遗传算法(IGA)与遗传编程(GP)相结合,建立了有广泛搜索能力和很强局部精化能力的IGA-GP自动编程算法,将该算法应用于BP神经网络的优化,克服了BP网络寻优过程中收敛速度慢、易陷入局部最优的不足,解决了新训练样本加入对网络稳定的影响。在此基础上,建立了黄河流域需水预测模型;拟合结果表明,该模型具有较高的预测精度。 |
| 关键词: 黄河流域 需水预测 遗传算法 遗传编程 神经网络 |
| DOI： |
| 分类号: |
| 基金项目:国家973重点基础研究发展规划项目(G1999043608) |
|
| Application of IGA-GP & BP neural network method to water-requirement prediction in Yellow River Basin |
|
|
| Abstract: |
| Due to the shortcomings of genetic algorithms (GA) and BP neural network,this paper applies an automatic programming algorithm combined improving genetic algorithms (IGA) with genetic programming (GP),which owns the virtues of much stronger searching capability in comprehensive and local aspects.The application of IGA-GP method in the optimization of IGA-GP method is used BP neural network can solve its shortcomings of slow convergence speed as well as being prone to lose in local optimal solution in the course of searching optimal solution and solve the problem of new training samples affecting BP neural network's stability.And then a model of water-requirement prediction in Yellow River Basin has been obtained.Results of fitting show the model has better predicting precision. |
| Key words: Yellow River Basin water-requirement prediction genetic algorithms genetic programming neural network |
