摘要
神经网络是智能故障诊断中运用最为广泛的诊断方法之一,能应对复杂数字电路和模拟电路故障诊断;基于VC++的神经网络诊断系统具有运算速度快、输入输出界面丰富、易于实现在线故障诊断等特点,而Matlab提供强大的神经网络工具箱,在网络训练方面有优势;利用参数文件将二者优势结合起来,可实现功能完善的数模混合电路智能故障诊断系统;诊断实例表明,使用该方法实现数模混合电路故障诊断系统,具有高建模速度和高诊断精度的特点。
Artificial Neural Networks （ANN） was used widely in intelligent fault diagnosis system and can deal with complex logical circuit and analog circuit. An ANN fault diagnosis system based on VC＋＋ runs fast, has abundant user interlace and can realize online fault diagnosis. Matlab supplies powerful ANN toolbox and has advantage in training networks. A perfect intelligent fault diagnosis system for mixed-signal circuits will be built by combining VC＋＋ and Matlab with parameter files. The example showed that mixed-signal circuits fault diagnosis systems with this method can be built rapidly and diagnose faults accurately.
出处
《计算机测量与控制》
CSCD
2008年第10期1376-1379,共4页
Computer Measurement &Control
关键词
神经网络
散模混合电路
故障诊断
artificial neural networks （ANN）
mixed-signal circuits
fault diagnosis
