一种在线检测与预测传感器故障的方法研究

分析了人工神经网络和模糊逻辑，并结合二者各自的优势，针对传感器故障检测的特点，提出一种对传感器故障在线检测与预测的方法。该方法采用在线学习训练网络，并给出传感器的预测信号，对传感器是否发生故障做出检测，仿真实验证明，该方法对传感器的故障能在线做出准确的检测，同时隔离故障传感器并为系统和设备提供临时的预测信号。

Aanalysis of an approach of on-line detection and prediction of sensor fault

Artificial neural network and , fuzzy logic are discussed, For the trait of sensor fault detecan approach of on - line detection and prediction of sensor fault based on the respective advantages of artificial neural network and fuzzy logic is proposed , which is employed on -line refreshing network, gives predictive signals and then, detects sensor fault. Judging by simulation experiments, the approach can accurately on -line detect sensor fault, separate the fault sensors in the meantime, and it can provide system and equipment with temporary predictive signals .