基于神经网络的电力电能自适应测量方法  

The self-adjusted measuring method of power energy based on neural networks

作　　者：徐秀平[1] 李柱峰[1] 

机构地区：[1]五邑大学,广东江门529020

出　　处：《电测与仪表》2003年第8期8-11,共4页Electrical Measurement & Instrumentation

摘　　要：详细介绍了基于神经网络的电力电能自适应测量方法,给出系统原理图及电力电能测量误差自动校正方法;首次提出了LEA判别法,从而实现了梯度牛顿法的有效结合神经网络学习方法;采用DSP技术实现了电能实时快速测量,给出了实验结果。In this article, the self-adjusted measuring method of power energy based on neural networks have been thoroughly given,and we have also given the system principle diagram,the automation error calibration method of power energy measuring.At the first time,the LEA decision method has been given so that Grads methods and Newton methods can be effectively combined in neural networks learning. DSP technology has been used to realize timing,fast energy measuring, we have also given the experiment result.

关 键 词：神经网络 电能测量 LEA判别法 自适应 DSP 

分 类 号：TM933.4[电气工程—电力电子与电力传动] TP183[自动化与计算机技术—控制理论与控制工程]