论文部分内容阅读
故障诊断准确性直接影响光纤传感器网络的应用价值,为了改善光纤传感器网络故障的诊断性能,本文提出了一种Volterra级数和神经网络的光纤传感器网络故障诊断方法。首先采用Volterra级数提取光纤传感器故障的信号特征,然后采用神经网络中的相关向量机对光纤传感器特征进行学习,建立光纤传感器故障诊断识别器,最后通过具体光纤传感器网络对其性能进行仿真测试。结果表明,本文方法能够分析光纤传感器网络的故障特征,较好完成了光纤传感器网络的故障诊断,而且结果要优于其他光纤传感器故障诊断方法。
The accuracy of fault diagnosis directly affects the application value of optical fiber sensor networks. In order to improve the diagnostic performance of optical fiber sensor networks, this paper presents a fault diagnosis method of optical fiber sensor networks based on Volterra series and neural network. Firstly, the signal characteristics of fiber sensor fault were extracted by Volterra series. Then the correlation vector machine in neural network was used to study the characteristics of fiber sensor, and the fault diagnosis identifier of fiber sensor was established. Finally, the performance of the fiber sensor was tested by simulation. The results show that the proposed method can analyze the fault characteristics of optical fiber sensor networks and accomplish the fault diagnosis of optical fiber sensor networks well, and the results are superior to other methods of fault diagnosis of optical fiber sensors.