摘要
研究了BP神经网络的结构模型和学习训练的过程并将其应用到遥测装备的故障诊断中。基于神经网络方法建立了遥测装备故障诊断的神经网络模型,以遥测下变频器故障为例进行了仿真研究,建立了遥测下变频器故障现象和故障原因的样本数据,利用MATLAB编写的神经网络程序对样本数据进行训练,得到了训练的仿真数据及误差曲线,并通过测试样本数据验证了神经网络故障诊断的正确性。
The structure of the BP neural network model was built. And, the process of learning and training is studied and applied into the telemetry equipment fault diagnosis. Telemetry equipment fault diagnosis model of neural network is built. Then the simulation research has been carried out with the telemetry downconverter, The sample data of telemetry downconverter fault phenomenon and the cause is built, the training simulation data and error curve is got, with training these sample data by neural network program which is written by MATLAB, and the correctness of neural network fault diagnosis is verified by testing sample data.
作者
朱会
ZHU Hui(91550 unit of PLA,Dalian 116023,China)
出处
《软件》
2018年第4期214-217,共4页
Software
关键词
遥测装备
故障诊断
神经网络
Telemetry equipment
Fault diagnosis
BP neural network
