变结构神经网络模型的BP算法及其应用研究

神经网络模型是一种非常有效的数据处理工具,但是存在结构确定困难的缺点.针对神经网络算法的这种缺点,提出了变结构神经网络模型.此模型增加了神经网络隐节点的决策变量,并对此决策变量进行松弛.在采用BP梯度算法确定神经网络结构的同时,确定网络参数.由于电缆的状态监测是时序数据,将此模型应用于电缆的状态监测过程中,能体现出较好的适应性.

BP Calculation of Variable Structure Neural Network Model and Its Application

Neural network model is an effective data processing method,but it has a shortcoming of difficult structure confirmation.This paper aims at this primary disadvantage of the neural network calculation,giving a variable structure neural network model,which model increases decision-making variable in allusion to the hidden nodes of neutral network,fixing network parameter while using BP gradient algorithm to fix the structure of neural network by means of slacking this decision-making variable.In applying this model to cable state detection which is time series data,in processing continuous changing data,this model has good adaptability.