论文部分内容阅读
提出了一种基于蚁群聚类算法数据挖掘预处理的支持向量机(SVM)预测方法.利用其在处理大数据量、消除冗余信息等方面的独特优势,寻找与预测炉况同等的多个历史铁水硅质量分数,由此组成具有高度相似炉况特征的数据序列,将此数据序列作为SVM的训练数据.这种处理方法可减少数据量,提高预测的速度和精度.将该系统应用于铁水硅质量分数预测中,与单纯的SVM方法相比,具有较高的预测精度.
This paper proposes a support vector machine (SVM) prediction method based on ant colony clustering algorithm for data mining preprocessing.Using its unique advantages in dealing with large amount of data and eliminating redundant information, it looks for the same amount of forecasting furnace A history of molten iron silicon mass fraction, which constitutes a highly similar furnace characteristics of the data sequence, the data sequence as SVM training data.This approach can reduce the amount of data to improve the prediction speed and accuracy.This system is applied In the prediction of mass fraction of molten iron, the proposed method has higher prediction accuracy than pure SVM method.