多元分类LS-SVM设计与装备保障性评估

Equipment Supportability Assessment Study and the Design of Multi-class Least Squares Support Vector Machines

科学、有效地进行保障性评估是提高装备综合保障能力和加快装备形成战斗力的研究重点之一;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,并设计了基于多元分类的最小二乘支持向量机;建立了装备保障性评估的最小二乘支持向量机决策模型,确定了保障性评估指标体系和支持矢量学习决策模式;对某新型装备的保障性进行了评估.结果表明,基于最小二乘支持向量机的保障性评估是有效的、可行的.

Assessing equipment supportability scientifically and efficiently is one of core research fields in increasing equipments integrated supportability and promoting battle effectiveness. Support vector machines have excellent learning, classification ability and generalization ability which use structural risk minimization instead of empirical risk minimization. The paper studies new support vector machines-least squares support vector machines, and present a new multi-class support vector machines algorithm. And then, designs equipment supportability assessment mode. Because those deciding supportability assessment parameters is difficult, the paper also presents multi-parameter assessment system and supportability grade decide making index. Furthermore, new equipment supportability is assessed by the supportability assessment mode. The results show that the equipment supportability assessment mode is efficient and feasible.