摘要
提出了一种控制系统传感器故障诊断的结构形式 ,针对多传感器系统的特点 ,将相关传感器的输出数据综合 ,应用神经网络的非线性拟合能力扩展相关信息 ,信息融合诊断策略根据这些信息确定出故障传感器 ,同时对故障信号进行恢复 .仿真实验表明该结构形式对于传感器的三种常见故障均能进行识别和恢复 ,效果令人满意 .
This paper proposes a structural form of sensor failure diagnoses. To the charac teristic of multi-sensor system, synthesizing the output data of relational sen sors, using the nonlinear approach ability of neural network expand relational i nformation. According to the information, the fusion diagnoses strategy can ensu re the fault sensor and resume the fault signal. Simulation tests show that the structural form can identify and resume three kinds of normal failure. The effec t is satisfactory.
出处
《传感技术学报》
CAS
CSCD
2000年第4期272-276,共5页
Chinese Journal of Sensors and Actuators
关键词
传感器
故障诊断
径向基函数网络
神经网络
sensor failure diagnoses\ \ radial basis transfer function\ \ information fusio`
