摘要
采用RBF神经网络进行温度传感器故障检测,利用TE(Tennessee-Eastman)控制系统中的温度传感器的输出信息建立动态神经网络温度传感器输出模型,并利用该模型进行在线的故障检测,仿真结果表明该模型有很强的抗干扰性,同时还有较好的收敛性和稳定性.
This paper presents a method of the temperature sensor fault diagnosis based on RBF neural network.By using temperature sensor output information in the text TE(Tennessee-Eastman) control system,a dynamic neural network model of the temperature sensor output is created.This model can be used on-line fault diagnosis.The simulation results show that the model has a strong anti-interference and good convergence and stability.
出处
《吉首大学学报(自然科学版)》
CAS
2010年第2期79-82,共4页
Journal of Jishou University(Natural Sciences Edition)
基金
湖南省科技计划项目(06JJ2024
2008GK2022)