| 引用本文: | 孙勇,李志民,张东升,于继来.基于改进算法的模糊神经网络电力系统稳定器[J].电力自动化设备,2009,(6): |
| .Power system stabilizer based on fuzzy neural network with improved learning algorithm[J].Electric Power Automation Equipment,2009,(6): |
|
|
| 摘要: |
| 基于模糊神经网络的电力系统稳定器具有适应电力系统非线性,且不依赖电力系统数学模型的特点,针对模糊神经网络隶属度函数的中心参数选取问题,提出了一种基于极大熵原理优化模糊神经网络的设计方法.该方法利用一个最优化的目标函数导出中心向量和宽度的学习算法,改善了网络的回归能力和泛化能力.针对电力系统发生的低频振荡问题,提出了一种基于熵优化模糊神经网络电力系统稳定器的设计方案.该方案避免了控制器对系统精确数学模型的依赖,利用神经网络的学习能力,在线自动生成训练样本,实现了电力系统的实时控制.仿真结果表明,提出的电力系统稳定器控制方案可以显著地提高被控机组的稳定性及电力系统的动态性能. |
| 关键词: 模糊神经网络 隶属度函数 中心参数选取 极大熵原理 低频振荡 熵优化 电力系统稳定 多机电力系统 |
| DOI： |
| 分类号:TM712 |
| 基金项目:国家自然科学基金? |
|
| Power system stabilizer based on fuzzy neural network with improved learning algorithm |
|
SUN Yong1 LI Zhimin1 ZHANG Dongsheng2 YU Jilai1
|
| Abstract: |
| The power system stabilizer based on FNN(Fuzzy Neural Network) adapts well to the nonlinearity of power system and does not rely on the precise mathematical model. A FNN design method based on maximum entropy principle is proposed to optimize the center parameters of its membership functions,which uses an optimized objective function to deduce the learning algorithms of center vector and width,improving its regression and generalization ability. For the lower - frequency oscillation of power system,a power ... |
| Key words: fuzzy neural network membership function center parameter selection maximum entropy principle lower - frequency oscillation entropy optimization power system stability multi - machine power system |
