|本期目录/Table of Contents|

[1]张腾飞,马福民.粗糙-神经网络逆模补偿的发电机励磁复合控制[J].电机与控制学报,2009,(01):104-111.
 ZHANG Teng-fei,MA Fu-min.Generator excitation compound control with rough neural network inverse system compensation[J].,2009,(01):104-111.
点击复制

粗糙-神经网络逆模补偿的发电机励磁复合控制(PDF)
分享到:

《电机与控制学报》[ISSN:1007-449X/CN:23-1 408/TM]

卷:
期数:
2009年01
页码:
104-111
栏目:
出版日期:
2009-01-30

文章信息/Info

Title:
Generator excitation compound control with rough neural network inverse system compensation
作者:
张腾飞; 马福民
南京邮电大学自动化学院; 南京财经大学信息工程学院
Author(s):
ZHANG Teng-fei; MA Fu-min
关键词:
发电机 励磁控制 前馈补偿 复合控制 粗糙集 神经网络
Keywords:
generators excitation control feed forward compensation compound control rough set neural network
分类号:
TM712
DOI:
-
文献标志码:
A
摘要:
利用粗糙集数据智能分析与决策规则自动提取的优点以及神经网络良好的泛化能力,提出了粗糙-神经网络逆模型的具体实现方法;在证明五阶同步发电机模型可逆的基础上,研究了船舶同步发电机的粗糙-神经网络逆模型,提出了基于粗糙-神经网络逆模型前馈补偿的船舶发电机励磁复合控制方法,并对复合控制的稳定性和可靠性进行了分析。在某船舶电力仿真系统中进行了多工况仿真研究并进行了对比分析。仿真结果表明,粗糙-神经网络逆模型前馈补偿的复合控制可以提高船舶电力系统电压控制的稳态精确度、改善系统的动态性能。
Abstract:
The integration of rough set with neural network comprehensively can utilize the merits of rough set,such as data intelligent analysis and automatic extraction of decision-making rules,and the ability of arbitrarily approximating nonlinear functions in neural network.The concept of rough neural network inverse model was first put forward and the realization method was introduced.After proving the reversibility of the fifth-order generator model,the rough neural network inverse model for ship synchronous generator was researched.And then a ship generator excitation compound control method with rough neural network inverse system feed forward compensation was presented,and the stability and reliability of compound system was analyzed.The simulation of the compound control system was performed in a certain ship power simulation system under multi operation condition.The simulation results demonstrate that the proposed control method is effective for improving ship power system dynamic performance and stability.

参考文献/References:

-

相似文献/References:

备注/Memo

备注/Memo:
江苏省教育厅高校自然科学基金基础研究项目(08KJB520007);; 南京邮电大学引进人才科研基金项目(NY207148)
更新日期/Last Update: 2009-07-08