摘要
飞机后续备件配置直接关系到装备的战备完好率和寿命周期费用,对备件的正确分类是进行备件配置决策的前提。支持向量机是采用结构风险最小化原则代替传统统计学中的基于大样本的经验风险最小化原则的新型机器学习方法,具有出色的学习分类能力和推广能力。研究了新型支持向量机算法-最小二乘支持向量机,设计了基于多元分类的最小二乘支持向量机,在此基础上,建立了飞机备件多元分类模型,并对某机型的备件进行了分类。结果表明,基于最小二乘支持向量机的飞机备件多元分类方法是有效、可行的。
Effective schemes of aircraft spare parts can improve availability of equipment and also lower life cycle cost. But the spare parts should be classified scientifically before an effective scheme could be given. Support vector machines have excellent learning, classification ability and generalization ability, which use structural risk minimization instead of traditional empirical risk minimization based on large sample. In this paper, a multi - class support vector classifier was built based on least squares support vector machines. And then, we built an aircraft spare parts multi - class classifier and tested the model by classifying new aircraft spare parts. The results show that the aircraft spare parts multi - class classifier is efficient and feasible.
出处
《电光与控制》
北大核心
2006年第2期73-74,78,共3页
Electronics Optics & Control
关键词
机器学习
支持向量机
飞机备件
machine learning
support vector machines
aircraft spare parts
