基于RBF神经网络的传感器故障检测方法  

Sensor Fault Detection Method Based on RBF Neural Network

作　　者：刘甜甜[1] 那文波[1] 何宁[1] 李明[1] 

机构地区：[1]中国计量大学机电工程学院,杭州310018

出　　处：《煤矿机械》2017年第5期143-145,共3页Coal Mine Machinery

摘　　要：针对液位控制系统在运行过程中容易发生传感器故障,提出一种利用RBF神经网络模型的方法预测液位系统的液位输出对传感器进行故障检测,通过比较神经网络模型的预测输出和控制系统实际输出的残差信号大小,并得到故障指示量,可以判断传感器有无故障发生。仿真结果表明,这种故障检测方法能达到比较可靠的检测效果。For liquid level control system are prone to sensor fault in the process of running,put a method that apply a RBF neural network model is used to predict the output of the liquid level system approach to fault detection of the sensor, as long as compare with the sizeof the residual signal that output of the neural network model and the actual output of the system, and get the fault indicator, can judge whether the sensor failure. The simulation results show that the fault detection method can achieve more reliabledetecfion effect.

关 键 词：RBF神经网络 液位系统 传感器故障 故障检测 

分 类 号：TP206[自动化与计算机技术—检测技术与自动化装置]