两种改进BP算法神经网络滤波的比较  

Comparison of two improved BP algorithms used in ANN filter

作　　者：朱洪波[1] 许兆凤[1] 马燕枫[1] 盛兆俊[1] 

机构地区：[1]华北电力大学电力系,河北保定071003

出　　处：《电力自动化设备》2003年第6期35-36,40,共3页Electric Power Automation Equipment

摘　　要：对两种改进BP(Back-Propagation)算法神经网络的滤波进行了比较,通过反复的训练得出两种改进算法在权值调整和误差收敛过程中所遇到的共同点和差别,并得出初始权值、激励函数和神经元个数等因素的选取对神经网络学习的影响。Two improved BP(Back-Propagation)algorithms are compared,which are used in ANN(Artificial Neural Network)filter.By repeating training,their common ground and the difference in the process of weight adjusting and error constringency are drawn,and the effect of neuron num-ber,exciting function and initial weight on the training of ANN is summarized.

关 键 词：BP算法 神经网络 滤波 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]