| 频响函数作为神经网络输入参数的应用研究 |
| |
| 引用本文： | 方剑青,矫桂琼. 频响函数作为神经网络输入参数的应用研究[J]. 中国机械工程, 2006, 0(Z2) |
| |
| 作者姓名： | 方剑青 矫桂琼 |
| |
| 作者单位： | 西北工业大学，西北工业大学 西安，710072，西安，710072 |
| |
| 摘 要： | 给出一个BP神经网络,应用频响函数作为神经网络的输入参数,用来识别结构的状态信息,由于频响函数数据量大,直接作为神经网络输入参量容易造成网络训练收敛慢或不收敛。将频响函数在(0,1)范围进行归一化处理,通过用BP网络试验,新方法收敛速度提高了25倍,表明这是一种简单有效的方法。
|
| 关 键 词： | 频响函数 神经网络 故障诊断 输入参数 |
Application Study on Using Frequency Response Function as Neural Network''''s Input Parameters |
| |
| Fang Jianqing Jiao Guiqiong Northwestern Polytechnic University,Xi'an. Application Study on Using Frequency Response Function as Neural Network''''s Input Parameters[J]. China Mechanical Engineering, 2006, 0(Z2) |
| |
| Authors: | Fang Jianqing Jiao Guiqiong Northwestern Polytechnic University Xi'an |
| |
| Affiliation: | Fang Jianqing Jiao Guiqiong Northwestern Polytechnic University,Xi'an,710072 |
| |
| Abstract: | This paper presented a Back-Propagation network method(BP network),using struc- tural frequency response function as the network input parameters.This method was proposed to i- dentify a structure's state information.Except many advantages such as simpleness,this method had also many shortages.For example,the networks training will be difficult because of its large data.In general,input parameters should be normalized between 1 to 1.The frequency response function data was normalized between 0 and 1.An example was given in details,in which a BP network was used.Two kinds of network are compared,the new method gives an answer much faster then tradi- tional ways for 25 times.And the results show that this method is more simple,and effective. |
| |
| Keywords: | frequency response function neural network fault diagnosis input parameter |
| 本文献已被 CNKI 等数据库收录！ |
|
