一种基于SVR的传感器系统故障诊断方法

Sensor Fault Diagnosis System Base on Support Vector Regression

简要介绍了回归型支持向量机(Support Vector Regression,SVR),并在此基础上构建了一个传感器故障诊断系统,对SVR采用离线训练,在线应用的方法,用训练好的SVR来模拟柴油机温度控制的传感器系统的动态特性。仿真结果表明:SVR能有效地模拟传感器系统的动态特性,能跟踪传感器的输出信号,并及时对传感器故障进行准确的诊断。

This article briefly introduce Support Vector Regression, and design a sensor fault diagnosis system base on SVR. SVR is trained out of line, and used online. After being trained, SVR is used to simulate dynamic characteristic of diesel engine temperature-controlling system. The simulation result shows that, SVR can simulate the system more accurately, track the output signal of sensor, and diagnose the sensor system.