摘要
提出了基于SVM的滴丸生产工艺参数优化方法,较好地预测了滴丸含水量,给出了各工艺参数取值范围,在实际生产中取得了良好效果。理论分析和仿真研究表明,该方法学习速度快、跟踪性能好、泛化能力强、对样本的依赖程度低,比基于BP神经网络的建模具有更好的推广能力。
This paper introduces a kind of optimizing method of Pipule Manufacturing Process parameters based on the Libsvm, by which the changes of Pipule's containing water are preferably forecasted and the proper process parameters are founded.Theoretical and simulation analysis indicates that this method features high learning speed,good approximation,well generalization ability,and little dependence on the sample set.It has the better performance than the model based on the BP neural network.
出处
《计算机工程与应用》
CSCD
北大核心
2007年第36期205-207,共3页
Computer Engineering and Applications
关键词
支持向量机
工艺参数
建模与优化
support vector machine(SVM)
process parameters
modeling and optimization