摘要
支持向量机是一种基于统计学习理论的机器学习算法,采用结构风险最小化原则代替经验风险最小化原则,较好地解决了小样本学习问题;采用核函数思想,使非线性空间的问题转换到线性空间,降低了算法的复杂度;具有良好的泛化能力。针对机载设备故障诊断及预测等工程实际应用中遇到的典型故障样本缺乏、先验知识不足等采用神经网络等其它方法无法解决的问题,提出利用支持向量机应用在机载设备故障诊断及预报中。
SVM （Support Vector Machine）, which is based on Statistical Learning Theory, can solve small sample learning problems better by using Structural Risk Minimization than Empirical Risk Minimization, can change the problem in non-linearity space to that in the linearity space by using the kernel function idea in order to reduce the algorithm complexity. Moreover, SVM has better training generalization. In the practical application include fault diagnosis and forecast for airborne equipment, the problems of little typical sample on fault and transcendental knowledge are not easy to be solved via neural network technology etc. This paper proposes the SVM to be used in Fault Diagnosis and Forecast for Airborne Equipment.
出处
《科技信息》
2008年第2期72-73,共2页
Science & Technology Information
关键词
支持向量机
机载设备
故障诊断及预测
统计学习理论
Support vector machine
Airborne equipment
Fault diagnosis and forecast
Statistical learning theory
