| 基于SOM神经网络的航舵故障分类方法 |
| |
| 引用本文： | 周 晶,余家祥,司 南,田庆战. 基于SOM神经网络的航舵故障分类方法[J]. 太赫兹科学与电子信息学报, 2012, 10(3): 339-342 |
| |
| 作者姓名： | 周 晶 余家祥 司 南 田庆战 |
| |
| 作者单位： | 海军大连舰艇学院训练部,辽宁大连,116018 |
| |
| 摘 要： | 为解决航舵故障诊断的复杂非线性模式分类问题,提出一种基于自组织特征映射(SOM)神经网络的航舵故障诊断方法,构造一个2层SOM神经网络,训练后多个权值向量位于输入向量聚类中心,实现快速有效的自适应分类.仿真结果表明:SOM网络经过100次训练即可实现聚类,对有限故障测试样本分类准确率可达90％,对航舵故障诊断具有一定的参考价值.
|
| 关 键 词： | 自组织特征映射 人工神经网络 故障诊断 航舵 |
| 收稿时间： | 2011-06-26 |
| 修稿时间： | 2011-08-24 |
Fault classification method for nautical steer based on SOM neural networks |
| |
| ZHOU Jing,YU Jia-xiang,SI Nan and TIAN Qing-zhan. Fault classification method for nautical steer based on SOM neural networks[J]. Journal of Terahertz Science and Electronic Information Technology, 2012, 10(3): 339-342 |
| |
| Authors: | ZHOU Jing YU Jia-xiang SI Nan TIAN Qing-zhan |
| |
| Affiliation: | (Department of Training,Dalian Naval Academy,Dalian Liaoning 116018,China) |
| |
| Abstract: | It is difficult to collect inductive fault patterns of the steer system for diagnosis.In order to solve such a complicated nonlinear pattern classification problem,a kind of fault diagnosis method for steer system is proposed based on the Self-Organizing feature Map(SOM) neural network structure.A twolayer SOM neural network is built.Many weight vectors are in the clustering center of input vector after training.The adaptive classification is realized fast and effectively.The simulation results show that the SOM network can realize clustering after 100 times of training with the accuracy rate up to 90% for the classification of finite fault test samples. |
| |
| Keywords: | Self-Organizing feature Map artificial neural networks fault diagnosis nautical steer |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《太赫兹科学与电子信息学报》浏览原始摘要信息 |
|
点击此处可从《太赫兹科学与电子信息学报》下载免费的PDF全文 |
