文档介绍：Quality data carefully organized in 2021
哈尔滨理工大学硕士毕业论文
基于神经网络的模拟电路故障诊断专家系统研究
基于神经网络的模拟电路故障诊断
专家系统研究
基 misalignment mapping characteristic to approaches the failure diagnosis model. In view of the limitation of traditional fault diagnosis method, this paper proposed the concrete fault diagnosis method, studied the neural network diagnosis method which the
unit Levenberg-Marquardt algorithm and the momentum law, used the concrete example to neural network training simulation. The diagnosis result indicated that the method which the paper proposed is fast and effective and this research will provide the new theory basis and the diagnosis method for the complex analogous circuit failure diagnosis even integrated circuit.
In addition, the tradition failure diagnosis expert system exists insufficient which cannot carry on self-study, auto-adapted, difficult to gain the knowledge, and match conflict when it inference, and so on. This article uses the wavelet analysis and neural network technology as part of the construction of expert system. Use wavelet analysis extract analog circuit fault characteristic, the expert system knowledge gaining part is replaced by neural network's training, and use the connection power and the threshold value of Back Propagation (BP) neural network which had been well trained replaces the expert system knowledge library. The expert system inference part completes through the operation of the weight data and the input data. In view of a low pass filter electric circuit, we researched and developed an expert system based on BP neural network for analog circuit. The system uses MATALB GUI programming to realize the following function, firstly, the algorithm realization of feature extraction and algorithm selection, user can choose the different diagnosis algorithm according to the user's needs to realize to the fault feature extraction; secondly, set parameter of BP neural network, user can set hid level integer, study rat