基于支持向量机的产品设计推理模型研究  

Research on product design reasoning model based on support vector machine

作　　者：燕鸣[1] 闫德光 Yan Ming;Yan Deguang

机构地区：[1]山西大学商务学院信息中心,山西太原030031 [2]山东能源集团龙口矿业集团有限公司梁家煤矿运输工区,山东龙口265700

出　　处：《数码设计》2018年第9期112-113,共2页Peak Data Science

摘　　要：为提高产品设计的智能化程度,面向产品设计中主体参数设计过程,以支持向量机作为推理算法,提出基于支持向量机的产品参数预测模型。分析了支持向量机方法,并建立相应的算法流程,通过数据归一化方法对数据集进行归一化,去除量纲对训练结果的影响,并通过遗传算法对算法进行优化,优选参数,最后收集企业数据,划分训练集和测试集,训练出模型后用测试集进行验证,结果表明算法正确率在90%以上,计算时间在0.8s以内,能够满足应用需求,同时也验证了该算法能够提高产品设计的效率,从而降低设计成本。In order to improve the intelligentized degree of product design,a product parameter prediction model based on support vector machine is proposed in this paper,which is oriented to the process of subject parameter design in product design and takes support vector machine as reasoning algorithm.The support vector machine method is analyzed,and the corresponding algorithm flow is established.The data set is normalized by the data normalization method,the influence of dimension on the training result is removed,and the genetic algorithm is used to optimize and select the parameters of the algorithm.Finally,the enterprise data are collected,the training set and test set are divided,and the model is trained and verified by test set.The results show that the accuracy of the algorithm is More than 90%,the calculation time is less than 3s.At the same time,it is proved that the algorithm can improve the efficiency of product design and reduce the design cost.

关 键 词：支持向量机 产品设计 模型推理 

分 类 号：TH122[机械工程—机械设计及理论]