| 自适应遗传算法优化管网状态估计神经网络模型 |
| |
| 引用本文： | 陈磊,张土乔,吕谋,何小香. 自适应遗传算法优化管网状态估计神经网络模型[J]. 水利水电技术, 2004, 35(10): 61-63 |
| |
| 作者姓名： | 陈磊 张土乔 吕谋 何小香 |
| |
| 作者单位： | 浙江大学,市政工程研究所,浙江,杭州,310027;青岛建工学院,环境工程系,山东,青岛,266000;杭州电子科技大学,外国语学院,浙江,杭州,310000 |
| |
| 基金项目： | 国家自然科学基金资助项目(50078048). |
| |
| 摘 要： | 针对遗传算法收敛速度慢、传统BP算法易收敛于局部最优以及网络结构难以确定等问题，引进自适应遗传算法优化网络的权阈值以搜寻网络最优拓扑结构，并利用自适应遗传算法优化该网络的权阈值，建立基于改进BP网络的宏观管网状态模型．实例分析表明，改进模型具有较高的预测精度。
|
| 关 键 词： | BP网络 自适应遗传算法 管网状态估计 |
| 文章编号： | 1000-0860(2004)10-0061-03 |
| 修稿时间： | 2004-06-07 |
Self-adaptive GA for optimization of neural network model of pipe network for state estimation |
| |
| CHEN Lei. Self-adaptive GA for optimization of neural network model of pipe network for state estimation[J]. Water Resources and Hydropower Engineering, 2004, 35(10): 61-63 |
| |
| Authors: | CHEN Lei |
| |
| Abstract: | Simple GA has the shortcoming of slow convergence, while BP neural network is prone to the local optimum and its structure is usually difficult to be determined. In this paper, a real-coded self-adaptive GA was introduced to optimize the weight and threshold so that a binary-coded self-adaptive GA can find the best topological structure, and then a real-coded self-adaptive GA was presented to optimize the weight and threshold of BP network which has the best structure. A macroscopic state model of pipe network was developed based on improved BP neural network. Case study shows that the improved model has higher prediction accuracy. |
| |
| Keywords: | BP neural network self-adaptive genetic algorithm state estimation of pipe network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
