基于神经网络预测模型输入参数配置方法的实现

基于数据挖掘中的关联概念,提出了一种针对神经网络预测模型训练参数的选择方法,有效地提高了神经网络模型在毛纺工艺中对纱线断头率的预测精度;该方法通过生产中的训练参数记录进行关联规则的提取,可快速的排除产生负面影响的训练参数,迅速选择可以提高预测精度的训练参数,从而达到提高神经网络模型预测性能的目的;实验证明,利用关联算法进行参数配置,可以有效提高神经网络输入模型的预测精度.

Realization of Parameter Disposes Based on ANN Model

A method to dispose ANN(Artificial Neural Network) training parameters is proposed based on the association algorithm which belongs to datamining.It improves the precision of prediction to the yarn breaking rate in ANN model effectively.Through carrying on Association rules drawing to the record that tests the parameter in production,this method can rapidly get rid of the training parameters exerting a negative influence,and choose those improving prediction.Thus the goal of improving the ANN performance can be achieved.It has been proved by experiments that parameter disposes based on association algorithm can improve the prediction precision of ANN model.