基于模糊神经网络的微波器件建模

Microwave Device Modeling Based on the Fuzzy Neural Network

通过模糊数据曲线来确定模糊规则,从而只需要根据系统的输入输出数据来建立网络最佳结构,并对BP算法进行了改进以加快网络模型的训练速度。在此基础上,用建立的模糊神经网络对微波无源器件共面波导的电容参数来进行提取。实验证明,模糊数据曲线确定的网络结构是接近最佳的,在训练速度和精度方面,效果优于神经网络建模算法。

A simple but effective method to determinate the model by the fuzzy-data curve was presented, by this the best architecture was only related to the input-output data of the system, and model based on BP algorithm was improved to speed up the network model. Furry neural network model of capacitance parameters for CPW（coplanar waveguide） was built. Under the same condition, the precision and speed of fuzzy neural network algorithm was better than that of neural network.