| 基于RBF网络的模拟移动床PH传感器故障诊断 |
| |
| 引用本文： | 高山,潘丰. 基于RBF网络的模拟移动床PH传感器故障诊断[J]. 微计算机信息, 2005, 0(21) |
| |
| 作者姓名： | 高山 潘丰 |
| |
| 作者单位： | 无锡江南大学控制科学与工程研究中心 214122江苏(高山)，无锡江南大学控制科学与工程研究中心 214122江苏(潘丰) |
| |
| 基金项目： | 科技部攻关项目“工业过程控制技术开发与应用”(编号:2001BA204B01) |
| |
| 摘 要： | 为了提高模拟移动床控制系统PH传感器的可靠性,提出了一种基于两级RBF神经网络的故障诊断方法。该方法首先利用径向基(RBF)神经网络对传感器的输出序列建立预测模型,通过计算预测输出和实际输出的残差来检测故障的发生,然后对包含故障的残差信号利用小波变换进行特征提取,最后利用RBF诊断网络实现故障诊断。通过把这种方法应用到实际诊断测试中,可达到较准确的诊断结果。
|
| 关 键 词： | 径向基神经网络 故障诊断 时序预测 小波 特征提取 |
SMB PH fault diagnosis based on RBF neural networks |
| |
| Gao,Shan Pan,Feng. SMB PH fault diagnosis based on RBF neural networks[J]. Control & Automation, 2005, 0(21) |
| |
| Authors: | Gao Shan Pan Feng |
| |
| Abstract: | In order to enhance the reliability of PH sensor in Simulation Movable Bed (SMB) control system, a fault diagnostic method based on two-step Radial Ba sic Function (RBF) neural network is proposed. Firstly RBF neural network is used to built predictor model with a serial of value of sensor, and the residual be tween output of predictor model and actual value is computed to determine whethe r sensor is working normal or not. Then wavelet transform is used to extract the sensor feature from fault residual signal, and finally RBF diagnostic neural ne twork is used to diagnose faults. The application to the PH sensor test in SMB proves effective. |
| |
| Keywords: | RBF neural network fault diagnosis time series predict wavelet feat ure extraction |
| 本文献已被 CNKI 等数据库收录！ |
