在人工神经网络建模过程中，采用主成分分析的方法对网络的输入数据进行预处理，显著提高了网络的学习速度。

In the process of modeling ANN, in order to accelerate the back-propagation learning process, the inputs of the ANN are processed in advance by principal component analysis.

youdao

以江阴兴澄钢铁公司的实际数据进行实验，结果表明，支持向量机方法有着良好的泛化能力，优于人工神经网络建模方法。

With real data collected from Jiangyin Xingcheng Steel Work CO. LTD, experiments show that SVM-based method is effective and superior to ANN-based method on generalization performance.

youdao

为了提高轧制力模型预报值的精度，提出了一种基于人工神经网络的轧制力建模新方法。

For improving the precision of prediction of rolling model, a new method using artificial neural networks of rolling force modeling is put forward.

youdao