基于复合小波网络的传感器故障在线检测仿真研究  

The Study Of Fault Detection Online For Sensor Based On Multiple Wavelet Network

作　　者：陈东雷[1] 王清元[2] 李喆 

机构地区：[1]江苏省扬州大学 [2]云南农业大学

出　　处：《传感器世界》2006年第12期16-20,共5页Sensor World

摘　　要：针对人工神经网络存在的问题,提出将小波分析与神经网络融合构成的小波网络用于传感器的故障诊断中。为进一步提高小波网络的性能,在小波网络的基础之上将其结构进行改进提出复合小波网络。为避免由于传感器输入信号突变所引发的传感器故障误诊断,将检测方法加以改进。仿真实验表明,复合小波网络具有更快的收敛速度和更好的预测性能,更适用于传感器的在线故障检测;同时,改进的检测方法既提高了检测的快速性,又提高了可靠性。Aiming at the problem of the artificial network, the wavelet network which is integrated by the artificial network is raised to be used in the fault detection of transducer . In order to improve the capability of the wavelet network, the multiple wavelet network is advanced based on improving the structure of wavelet network .For avoiding the fault diagnosis owing the break of sensor＇s inputs , detection＇s means is improved . The result of experiments indicates that the multiple wavelet network has the quicker convergence speed and the higher prediction performance and is fitter for fault detection . And the improved fault detection using the multiple wavelet network enhances both speed-ability and security.

关 键 词：神经网络 复合小波网络 传感器 故障检测 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置]