| 基于遗传算法优化神经网络权值的大坝结构损伤识别 |
| |
| 引用本文： | 李小荣,郭永刚.基于遗传算法优化神经网络权值的大坝结构损伤识别[J].震灾防御技术,2008,3(2):189-196. |
| |
| 作者姓名： | 李小荣 郭永刚 |
| |
| 作者单位： | 1. 北京工业大学建筑工程学院,北京,100022
2. 中国水利水电科学研究院,北京,100044 |
| |
| 摘 要： | 针对传统 BP 神经网络存在着容易陷入局部极小点、训练时间太长等缺点,本文采用基于浮点编码的遗传算法,对 BP 神经网络的初值空间进行了遗传优化。用基于浮点编码的遗传算法来优化 BP 神经网络的权值,可得到最佳初始权值矩阵,并按误差前向反馈算法,沿负梯度搜索进行网络学习。文中以混凝土重力坝结构作为算例,用结构的模态频率变化作为网络的输入向量,结构的损伤位置作为输出向量,对网络进行了训练。仿真结果表明：遗传 BP 神经网络的收敛和诊断能力优于传统 BP 神经网络,可有效地运用到大坝结构的健康诊断与损伤识别中。
|
| 关 键 词： | 遗传算法 BP神经网络 损伤 大坝 |
| 收稿时间： | 3/4/2008 12:00:00 AM |
Dam Damage Identifacation on the Base of Optimic Neural Network Weight by Genetic Algorithm |
| |
| Li Xiaorong and Guo Yonggang.Dam Damage Identifacation on the Base of Optimic Neural Network Weight by Genetic Algorithm[J].Technology for Earthquake Disaster Prevention,2008,3(2):189-196. |
| |
| Authors: | Li Xiaorong and Guo Yonggang |
| |
| Institution: | Beijing University of Technology, Beijing 100022, China;China Institute of Water Resources and Hydropower Research, Beijing 100044, China |
| |
| Abstract: | In order to solve the problem in traditional BP neural network, such as the problem of local minimal point, over long time training, a genetic algorithm based floating-point coding optimizes initial value space of the BP neural network is studied in this paper. A genetic algorithm based on floating-point coding optimizes initial value space of the BP neural network and optimal initial value matrix is obtained. The method of network learning is by the error forward back coupling algorithm in negative gradient. As example, an structure of concrete gravity dam with frequency as imput vector and the position of the structure damage as output vector is studied.The result show that GA-BP network＇s convergence speed and diagnose capability is better than the traditional BP neural network. The method of this paper can be used in the field of diagnosis and damage identification of dam properly. |
| |
| Keywords: | Genetic algorithm BP neural network Damage Dam |
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《震灾防御技术》浏览原始摘要信息 |
| 点击此处可从《震灾防御技术》下载免费的PDF全文 |
|
