| 基于小波模糊神经网络的DTC系统参数的辨识 |
| |
| 引用本文： | 曹承志,鲁木平,王楠,王欣.基于小波模糊神经网络的DTC系统参数的辨识[J].电工技术学报,2004,19(6):18-22. |
| |
| 作者姓名： | 曹承志 鲁木平 王楠 王欣 |
| |
| 作者单位： | 沈阳工业大学信息科学与工程学院,沈阳,110023;东北大学理学院,沈阳,110004 |
| |
| 基金项目： | 辽宁省自然科学基金，辽宁省教育厅资助项目 |
| |
| 摘 要： | 模糊神经网络由于具有良好的自学习和自适应能力,在非线性系统辨识中有着广泛的应用,又由于小波变换或分解所表现的良好的时频局部化特性,以及多尺度的功能,提出了基于小波模糊神经网络的直接转矩控制系统(DTC)参数辨识方法.利用递推正交最小二乘法(ROLS),采用改进的Givens旋转变换技术避免了大型矩阵的QR分解运算.通过计算机仿真证实了该法良好的辨识效果.
|
| 关 键 词： | 小波模糊神经网络 ROLS 非线性 DTC |
| 修稿时间： | 2003年7月21日 |
Parameters Identification on DTC System Based on Wavelet Fuzzy Neural Networks |
| |
| Cao Chengzhi,Lu Muping,Wang nan,Wang Xin.Parameters Identification on DTC System Based on Wavelet Fuzzy Neural Networks[J].Transactions of China Electrotechnical Society,2004,19(6):18-22. |
| |
| Authors: | Cao Chengzhi Lu Muping Wang nan Wang Xin |
| |
| Affiliation: | 1. Shenyang University of Technology Shenyang 110023 China 2. Northeastern University Shenyang 110004 China |
| |
| Abstract: | Fuzzy neural networks show good ability of self-adaption and self-learning, and is widely applied in non-linear system identification. Wavelet transformation or analysis shows the time frenqency location characteristic and multi-scale ability. Wavelet fuzzy neural networks based on parameters identification on direct torque control(DTC) system is proposed because of these advantages. The recursive orthogonal least squares(ROLS) algorithm is considered. The use of modified Givens rotations avoids orthogonal decomposition of complex matrices. And at last the computer simulation results show that the identification method has the better effect to improve the low speed performances of the DTC system. |
| |
| Keywords: | ROLS DTC |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
