摘要
达到提出应用主成分分析法对样本进行预处理，减少网络的输入因子数，消除输入因子间的相关性并简化网络结构，达到提高网络学习速率的目的，得到的人工神经网络模型能达到所要求的精度。
A method is proposed in order to accelerate the convergence of artifcial neural network(ANN) modeling of chemical process,in which the principal components analysis is applied in the data processing in training sets.The result shows that the correlation of input variables could be eliminate and the structure of network could be simplified by this method.Moreover,the precision of obtained ANN model could attain to the desired accuracy.
出处
《计算机与应用化学》
CAS
CSCD
1999年第3期219-221,230,共4页
Computers and Applied Chemistry
基金
广东省自然科学基金
关键词
主成分分析法
人工神经网络
制浆
化工过程
Principal components analysis,Artificial neural network(ANN),Kraft pulping,Pulp hardness
