摘要
支持向量机是一种针对小样本、非线性对象的故障诊断与预测方法;为了适应装备对排除故障快速性和在线性的要求,提出了利用在线稀疏最小二乘支持向量机回归算法的基本原理,建立针对于电子装备的在线预测模型;通过Matlab技术仿真实现了对某型无人机陀螺仪电源伏值状态趋势的在线预测和故障预报,并通过对比验证了该预测模型在确保准确性的前提下有效提高了预测的快速性和实时性;最终证明基于在线稀疏最小二乘支持向量机的在线预测模型在解决该问题上具有良好的应用价值。
Support vector machine （SVM） is one fault detection identification and prognostic method for the object which has the charac- teristics of small sample and nonlinearity. In order to insure it is suitable for mass training and online training, utilizing the basic principles of the OS--LSM （online sparse least square support vector machine） algorithm, an online prediction model based on OS--LSSVM is estab- lished. Through emulating of a UAV gyroscope voltage, online prediction and fault prediction on the trend of device status are implemented. The results show that it is meaningful to use the OS--LSSVM based model for online monitoring and fault prediction.
出处
《计算机测量与控制》
CSCD
北大核心
2012年第11期2903-2905,2908,共4页
Computer Measurement &Control
基金
军内科研项目(装司[2010]530号)
关键词
故障诊断
状态监控
在线预测
OS-LSSVM
fault detection identification
condition monitoring
online prediction
OS--LSSVM
