基于改进鲁棒自联想神经网络的传感器故障诊断新方法

Application of A Novel Robust Autoassociative Neural Network in Sensor Failure Diagnosis

本文首次提出一种传感器故障检测和信号恢复的改进鲁棒自联想神经网络新方法。文中阐述了改进鲁棒自联想神经网络的结构和算法，总结和归纳了传感器的六类故障模式.仿真了这些传感器故障模式的信号表现形式，并采取改进鲁棒自联想神经网络检测和恢复此六类传感器故障。本方法具有易于实时实现，结构简单的优点，计算机实验表明本方法是行之有效的。

A novel Robust Auto Associative Network(RAAN)method is given for sensor failure diagnosis. The structure and algorithm of RAAN are presented. Six klnds of sensor failure modes are summed up. The method is easy to be realized on-line and has simple structure. The simulation results show that the novel RAAN can successfully detect sensor failure and recover the signals of failed-sensors for many reasons.