一种基于RBF神经网络的传感器故障诊断方法

An Integrated Fault Detection and Diagnosis Approach to Sensor Faults Based on RBF Neural Network

摘要: 针对传感器故障，提出了一种基于RBF神经网络的集成故障诊断方法，用RBF神经网络建立传感器故障模型，对系统的状态和故障参数进行在线估计，然后将故障参数与修正的Bayes分类算法（MB算法）相结合，进行传感器故障在线检测、分离和估计。对连续搅拌釜式反应器（CSTR）的仿真结果表明，该集成故障诊断方法能够对多重传感器进行故障进行快速准确的分离和估计，并对传感器故障具有容错性。

Abstract: An integrated fault detection and diagnosis approach to sensor faults based on radial basis function (RBF) neural networks is presented in this paper. An RBF neural network is used to estimate the state and fault parameters of the constructed model for sensor faults. The estimated fault parameters are processed by the improved Bayes algorithm to realize online sensor fault detection, isolation, and estimation. The simulation for continuous stirred tank reactor (CSTR) shows the presented approach can isolate and estimate the multiple sensor faults quickly and accurately and the integrated system has tolerant ability to sensor faults.