| 在多参数检测时神经网络的结构优化方法 |
| |
| 引用本文： | 乔新勇,周云峰. 在多参数检测时神经网络的结构优化方法[J]. 计算机工程与应用, 2009, 45(8): 236-237. DOI: 10.3778/j.issn.1002-8331.2009.08.071 |
| |
| 作者姓名： | 乔新勇 周云峰 |
| |
| 作者单位： | 1.装甲兵工程学院 机械工程系，北京 100072 2.北京昆仑海岸传感技术中心，北京 100084 |
| |
| 摘 要： | 运用多特征参数进行设备状态监测是一种具有较高精确度的技术手段，但是当检测参数数量较大时运算量是一个不容忽视的问题。针对采用人工神经网络进行设备状态检测时的结构优化问题进行研究，提出由特征压缩层和检测层组成串联网络的方法建立神经网络检测模型。仿真结果表明，该组合网络减小了运算量，改善了网络收敛性能。
|
| 关 键 词： | 人工神经网络 结构优化 状态监测 特征压缩 |
| 收稿时间： | 2008-01-23 |
| 修稿时间： | 2008-3-31 |
Method for optimizing structure of neural network in states measuring based on multi-parameters |
| |
| QIAO Xin-yong,ZHOU Yun-feng. Method for optimizing structure of neural network in states measuring based on multi-parameters[J]. Computer Engineering and Applications, 2009, 45(8): 236-237. DOI: 10.3778/j.issn.1002-8331.2009.08.071 |
| |
| Authors: | QIAO Xin-yong ZHOU Yun-feng |
| |
| Affiliation: | 1.Department of Mechanical Engineering，The Academy of Armored Forces Engineering，Beijing 100072，China 2.Beijing ColliHigh Center of Sensor Technology，Beijing 100084，China |
| |
| Abstract: | It is an effective method to measure the states of a device using multi-parameters,but the calculations are consider-able when the number of the measured parameters is large,so such a problem should not be neglected.This paper studies the structure optimization of artificial neural network when measuring the state of a device,puts forward a combined neural network model including the functions of compressing characteristic and diagnosing faults.The result after simulating shows that such kind of combined ne... |
| |
| Keywords: | artificial neural network structure optimization state measure characteristic compression |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
