基于支持向量回归机的传感器故障诊断方法研究

Sensor Fault Diagnosis System Based on Support Vector Regression

以支持向量回归机(Support Vector Regression,SVR)为基础,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,能有效跟踪传感器的输出信号,并在传感器发生故障后能及时地对传感器系统进行故障诊断。

A sensor fault diagnosis system based on Support Vector Regression was designed. SVR was trained out of line, and used online. After being trained, SVR was 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.