| 循环自构形算法及其在设备故障诊断中的应用 |
| |
| 引用本文： | 饶泓,扶名福,陈炼,谢明祥.循环自构形算法及其在设备故障诊断中的应用[J].计算机工程与应用,2007,43(24):220-222. |
| |
| 作者姓名： | 饶泓 扶名福 陈炼 谢明祥 |
| |
| 作者单位： | 南昌大学,计算中心,南昌,330031;南昌大学,机电工程学院,南昌,330031 |
| |
| 摘 要： | 基于随机度和分治思想，提出并实现了前向反馈神经网络中的循环自构形算法，该算法能有效解决自构形算法的收敛不一致问题，将网络收敛到一致的最精简的结构。通过MATLAB实验表明，循环自构形算法可将网络隐层节点数从15和20一致精简到6。将该算法应用于风机的故障诊断中，实践表明该方法具有更有效的故障知识表达性能，能更好地解决故障诊断问题。
|
| 关 键 词： | 循环自构形 神经网络 故障诊断 风机 |
| 文章编号： | 1002-8331（2007）24-0220-03 |
| 修稿时间： | 2006-12 |
Circular self-configuring algorithm and application in equipment fault diagnosis |
| |
| RAO Hong,FU Ming-fu,CHEN Lian,XIE Ming-xiang.Circular self-configuring algorithm and application in equipment fault diagnosis[J].Computer Engineering and Applications,2007,43(24):220-222. |
| |
| Authors: | RAO Hong FU Ming-fu CHEN Lian XIE Ming-xiang |
| |
| Affiliation: | 1.Computer Center，Nanchang University，Nanchang 330031，China 2.Mechanical and Electrical School，Nanchang University，Nanchang 330031，China |
| |
| Abstract: | Based on the randomness and divide algorithm,the circular self-configuring algorithm of BP neural network is introduced in this paper.The algorithm is realized in the experiment.It shows this algorithm can converge uniformly and reduce the neural network to most simplify.The experiment of application in the centrifugal fan fault diagnosis underlines the theoretical resuits. |
| |
| Keywords: | circular self-configuring Neural Network fault diagnosis centrifugal fan |
| 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》下载全文 |
