神经网络用于产品品质鉴定的新方法

A New Method to Evaluate the Quality of Products by Neural Network Approach

针对用人工神经网络进行产品品质鉴定时特征指标过多的问题 ,提出利用 Cp 准则选出重要的特征指标作为输入节点 ,从而极大地简化人工神经网络 ,提高产品鉴定的效果 .

In order to deal with the problem that the number of characteristic variables of a product is too large when the quality of the product is evaluated by neural network, we put forward a new method of selecting the important variables by C p criterion and using them as the input nodes of neural network. This method can simplify the network and improve the result of evaluation.