基于支持向量机的可靠性增长费用建模与分析

支持向量机是一种采用结构风险最小化原则代替传统经验风险最小化原则的新型统计学习方法，具有完备的理论基础。首先应用支持向量机原理建立了基于支持向量机的多参数武器装备可靠性增长费用预测模型，然后对我军某型现役装备使用阶段可靠性增长费用数据进行了预测与分析。结果表明，与一般的回归分析相比，基于支持向量机的回归模型具有很好的预测精度。

Cost Modeling and Analyzing of Reliability Growth Based on a Support Vector Machine

This paper first presents a noval support vector regression(SVR) algorithm based on structural risk minimization inductive principle instead of empirical risk minimization principle.The algorithm realizes to solve non-linear regression problems mainly though inducting insensitive loss function and kernel function.Then develop an reliability growth cost estimation model using the SVR.The results as shown in tables indicates that the model can bring accurate learning precision and good prediction generalization ability.