一种模糊神经网络改进算法及其在振动强度识别中的应用  

An Improved Algorithm of Fuzzy Neural Networks and Its Application to Vibration Intensity Identification

作　　者：王太勇[1] 商同[1] 吴振勇[1] 任成祖[1] 

机构地区：[1]天津大学机械工程学院,天津300072

出　　处：《振动工程学报》2001年第4期451-454,共4页Journal of Vibration Engineering

基　　金：国家自然科学基金资助项目 (编号 :5 9875 0 6 7)

摘　　要：对传统模糊自适应 Ham ming网络算法进行了改进 :通过引入新的模糊算法对传统算法中的类别选择函数进行改进 ,以提高网络的正确识别率 ;为了实现模式识别中网络的有序输出 ,对输出层获胜神经元的选取方法也进行了相应的改进。改进后的算法用于空调压缩机壳体振动强度的识别 ,利用模糊自适应 Hamm ing神经网络综合考虑各测点振动、噪声信号所包含的信息 ,对壳体振动强度区域实现自动划分。通过改进前、后两种算法在不同警戒参数下的试验结果发现 ,采用改进后的算法大大提高了网络的正确识别率 。We put forward an improved algorithm of fuzzy adaptive Hamming neural networks, which overcomes the shortcomings of traditional one's shortcomings that are random order recognition and lower discrimination capability by introducing a new category choice function and modifying the method of choosing winner neuron in output layer with the characteristics of vibration and noise signal taken into account, fuzzy adaptive Hamming networks with improved algorithm is employed for identifying shell's vibration intensity, and contrast tests are carried out under different vigilance parameters. The results show that the method can improve the networks discrimination power greatly, and can also realize the sequential recognition process.

关 键 词：模糊神经网络 类别选择函数 模式识别 振动强度 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.4[自动化与计算机技术—控制科学与工程]