摘要
支持向量机是建立在统计学理论之上的强有力的机器学习技术。本文提出了基于支持向量机模型预测钢淬透性的方法,并分析了核函数的选择对支持向量机建模的影响。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。
Support vector machine (SVM) is a powerful machine learning technique based on statistical learning theory (SLT). In this paper, an SVM-based approach applied to predict steel quenching degree is presented, and the effects of selecting kernel function on SVM modeling are also analyzed. 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.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2006年第11期1410-1413,共4页
Chinese Journal of Scientific Instrument
基金
国家科技部(2003EG113016)资助项目。
关键词
支持向量机
人工神经网络
淬透性
预测
泛化能力
support vector machine artificial neural network quenching degree prediction generalization