中南大学学报（自然科学版）2017，Vol.48Issue(10)：2622-2627,6.DOI:10.11817/j.issn.1672-7207.2017.10.009
基于Adaboost加权支持向量机的热轧板带弯曲性能质量预警
Research on quality warning of strip bending performance based on Adaboost-weighted support vector machine
摘要
Abstract
Due to the data imbalance between normal and abnormal samples, the quality warning is not sensitive and the detection rate is low in the quality monitoring of strip bending performance. To solve this problem, different imbalance solutions to the abnormal detection from data level and algorithm level were studied. The quality warning method based on the Adaboost-weighted support vector machine method was proposed. The results show that the average value of fault detection rate is improved to 88.58%, and the average value of false alarm rate is reduced to 0.63%. The proposed method produces satisfying results in fault detection, which provides support for quality warning in hot rolling strip process.关键词
带钢弯曲性能/质量预警/Adaboost加权支持向量机Key words
strip bending performance/quality early warning/Adaboost-weighted support vector machine分类
矿业与冶金引用本文复制引用
周鹏,何飞,梁冰,徐科..基于Adaboost加权支持向量机的热轧板带弯曲性能质量预警[J].中南大学学报（自然科学版）,2017,48(10):2622-2627,6.基金项目
国家自然科学基金资助项目(51204018) （51204018）
"十二五"国家科技支撑计划项目(2015BAF30B01) （2015BAF30B01）
中央高校基本科研业务费专项资金资助项目(TW201711,FRF-TP-16-018A1)(Project (51204018) supported by the National Natural Science Foundation of China （TW201711,FRF-TP-16-018A1）
Project (2015BAF30B01) supported by the National Science and Technology Pillar Program during the 12th "Five-year" Plan of China （2015BAF30B01）
Project (TW201711, FRF-TP-16-018A1) supported by the Fundamental Research Funds for the Central Universities) （TW201711, FRF-TP-16-018A1）
