一种用于磨粒识别的基于改进PSO算法的支持向量机模型
发布时间:2018-01-13 13:10
本文关键词:一种用于磨粒识别的基于改进PSO算法的支持向量机模型 出处:《润滑与密封》2016年02期 论文类型:期刊论文
更多相关文章: 油液检测 磨粒识别 粒子群优化算法 支持向量机
【摘要】:为提高磨粒智能识别的准确率,以传统支持向量机和粒子群优化(PSO)算法为基础,提出一种基于改进PSO算法的支持向量机(SVM)识别模型。该识别模型的惩罚参数和核函数参数可同时得到最佳优化,从而可建立模型参数最优的自适应SVM识别模型。采用该识别模型对油液中的磨粒进行智能识别,结果表明该模型识别准确率高达98%,明显优于BP神经网络模型。
[Abstract]:In order to improve the accuracy of intelligent wear particle recognition, it is based on the traditional support vector machine and particle swarm optimization (PSO) algorithm. A support vector machine (SVM) recognition model based on improved PSO algorithm is proposed. The penalty parameters and kernel function parameters of the recognition model can be optimized at the same time. Thus an adaptive SVM recognition model with optimal model parameters can be established. The recognition model is used to identify the wear particles in oil. The results show that the recognition accuracy of the model is as high as 98%. It is obviously superior to BP neural network model.
【作者单位】: 军械工程学院七系;武汉军械士官学校四系;军械工程学院军械技术研究所;
【基金】:国家自然科学基金项目(51205405;51305454)
【分类号】:TH117;TP18
【正文快照】: j縥縥縥縥,
本文编号:1418976
本文链接:https://www.wllwen.com/kejilunwen/jixiegongcheng/1418976.html