基于数据挖掘的铁水硅质量分数SVM预测方法

SVM forecasting of hot metal silicon quality score using data mining

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.

The advantages of the data mining technology in processing large data and eliminating redundant information were fully considered. Thus, a support vector machines （SVM） forecasting system based on data mining preprocess of ant colony optimizing algorithm was proposed to search the historical daily silicon content with the same furnace status as the forecasting day and to compose data sequence with highly similar furnace status features. Taking the new data sequence as the training data of SVM, the data amount was decreased and the processing speed was improved. This approach achieves greater forecasting accuracy comparing with the method of single SVM.