摘要
针对BP网络学习收敛速度慢和易陷入局部最小点的不足,提出利用一种自适应学习速率动量梯度下降反向传播算法对BP神经网络进行训练。该算法使BP神经网络学习速率和稳定性得到提高。将这种改进的BP网络算法应用于配电网诊断实例,用这种改进的网络算法进行分类,采用VB语言作为开发工具调用神经网络工具箱建立了一个简化的故障诊断系统,验证了该算法的有效性、正确性。
A reverse transmission calculation of self adaptive learning rate with momentum gradient reduction is described in the paper against the problems of slow convergence and easy trapping into smallest spot. The calculation has made the BP net upgrade the rate and stability of learning .In the paper, an improved BP networks are used in the fault diagnosis of distribution network.And an improved BP networks are trained as a classifier of the distribution network＇s fault. It sets up a simple system of fault diagnosis about distribution network by the Visual B and Matlab,which has made an effective fault diagnosis of distribution network.
出处
《继电器》
CSCD
北大核心
2007年第12期27-31,40,共6页
Relay
关键词
配电网
故障诊断
BP神经网络
VB
distribution network
fault diagnosis
BP neural network
Visual B
