SVR在传感器故障诊断中的仿真研究

Simulation Research on SVR in Sensor Fault Diagnosis

利用回归型支持向量机(Support vector regression, SVR),设计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。使用训练好的SVR模拟系统的动态特性,并将输出结果和实际系统输出相比较,从而生成故障残差。仿真结果表明,SVR能够高精度的模拟系统的动态特性,进而生成较高精度的故障残差,有效地保证了传感器故障诊断的准确性。

A sensor fault diagnosis system is designed by using SVR. SVR is trained out of line, and used online. After being trained, SVR is used to simulate system dynamic characteristic. The simulation result is compared with actual output, and then fault error is drawn. The simulation result shows that, SVR can simulate the system more accurately, thus the fault error is very precise. This assures the validity of this fault diagnosis system.