基于一类SVM的综合导航系统信息故障检测方法

为了提高舰艇综合导航系统的可靠性,并考虑到系统准确建模和大量故障数据获取的困难性,提出了一种基于一类支持向量机的信息故障检测方法。该方法主要包括两个过程:第一个过程是根据实测数据,并利用一类支持向量机的分类原理和主元分析法对导航信息进行离线建模;第二个过程是结合主元分析法将该模型应用到实时的信息故障检测中。该方法不依赖于系统模型而且只需要正常的小样本数据对模型进行训练,具有简便易于实现的优点。仿真试验表明,该方法对导航系统的硬故障和软故障都具有较好的检测能力和较短的检测延迟时间,而且该方法对径向基核函数参数的变化具有较低的敏感性,避免了复杂的调参过程。

Information fault detection for integrated navigation systems using one-class support vector machine

Aiming to improve the reliability of the integrated navigation system and consider the difficulty in acquiring the accurate system model and large amount of fault data, an information fault detection method based on one-class support vector machine (SVM) is presented. The method mainly included two processes: 1) the measured data are used to build the model for navigation system by using one-class SVM and Principal Component Analysis; 2) the model is applied in the real-time information failure detection by combining with Principal Component Analysis. The new method does not rely on the system model and only requires the normal and small sample to train the model, which is simple and convenient for fault detection. The results of the experiment based on the measured data show that the proposed method has good detection performance and short detection delay time for both step fault and gradual fault, and is not sensitive to the changes of the radial basis function kernel parameter, which avoids the complicated parameter tuning.