|
|||||
|
|
| 基于差分进化小波神经网络的多维非线性系统辨识 | |
| 引用本文： | 李目,何怡刚,谭文.基于差分进化小波神经网络的多维非线性系统辨识[J].电子测量与仪器学报,2010,24(7):599-604. |
| 作者姓名： | 李目 何怡刚 谭文 |
| 作者单位： | 1. 湖南科技大学信息与电气工程学院,湘潭,411201;湖南大学电气与信息工程学院,长沙,410082 2. 湖南大学电气与信息工程学院,长沙,410082 3. 湖南科技大学信息与电气工程学院,湘潭,411201 |
| 基金项目： | 国家自然科学基金，高校博士点基金项目，教育部新世纪优秀人才支持计划，湖南省自然科学基金项目 |
| 摘 要： | 提出一种基于差分进化小波神经网络(DE-WNN)的多维非线性系统辨识方法。利用差分进化算法同时优化小波神经网络的结构和参数,简化网络结构,提高小波神经网络的学习精度和收敛速度。将该方法应用于多维非线性系统的辨识,并与RBF神经网络和遗传小波神经网络的辨识结果进行了比较,实验结果表明,差分进化算法优化的小波神经网络隐层节点为6,迭代次数为30,网络训练时间为0.58s,辨识均方误差达到1.02×10?4,所提出的方法具有更高的辨识精度和收敛速度,能够更好的辨识出多维非线性系统。 |
| 关 键 词： | 差分进化算法 小波神经网络 多维非线性系统 辨识 |
Identification of multi-dimensional nonlinear systems based on differential evolution wavelet neural network |
|
| Li Mu,He Yigang,Tan Wen.Identification of multi-dimensional nonlinear systems based on differential evolution wavelet neural network[J].Journal of Electronic Measurement and Instrument,2010,24(7):599-604. | |
| Authors: | Li Mu He Yigang Tan Wen |
| Affiliation: | Li Mu1,2 He Yigang2 Tan Wen1(1.School of Information and Electrical Engineering,Hunan University of Science and Technology,Xiangtan 411201,China,2.College of Electrical and Information Engineering,Hunan University,Changsha 410082,China) |
| Abstract: | A new method based on differential evolution wavelet neural network(DE-WNN) was presented for identification of multi-dimensional nonlinear systems.The structures and parameters of wavelet neural network were optimized by DE-WNN algorithm at the same time.The algorithm could get a best network structure and improve learning accuracy and convergence rate.The proposed method was applied to identify the multi-dimensional nonlinear systems,and the results were compared with those of RBF neural network and genet... |
| Keywords: | differential evolution algorithm wavelet neural network multi-dimensional nonlinear systems identification |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |