摘要
根据金属原子特征,提出了基于支持向量机(support vector machine,SVM)金属发射率预测模型。通过分析原子的原子量、原子半径、第一电离势和电负性等特征,选择合适的惩罚参数和多项式核函数,利用一定的训练样本,建立了基于SVM的金属发射率预测模型。通过实例验证了该方法的有效性。
For the characteristics of metal atoms, metal emissivity forecasting model based on support vector machine （SVM） is put forward. The characteristics of atom, such as atomic weight, radius, first ionization potentials, electronegativities are analyzed. The penalty and polynomial kernel function are chosen. Making use of definite training sample, metal emissivity forecasting model based on SVM is established. Model is validated by the case involving two testing samples. The result shows the validity of the method.
出处
《红外技术》
CSCD
北大核心
2008年第11期674-676,共3页
Infrared Technology
