| 修正初始权值的BP网络在CSTR故障诊断中的应用 |
| |
| 引用本文： | 江艳君,李柠,黄道.修正初始权值的BP网络在CSTR故障诊断中的应用[J].华东理工大学学报(自然科学版),2004,30(2):207-210. |
| |
| 作者姓名： | 江艳君 李柠 黄道 |
| |
| 作者单位： | 华东理工大学自动化工程中心,上海,200237;华东理工大学自动化工程中心,上海,200237;华东理工大学自动化工程中心,上海,200237 |
| |
| 基金项目： | 国家863资助项目(2002AA412120) |
| |
| 摘 要： | 将BP算法和使用复合法修正初始权值的BP算法运用到CSTR模型中进行故障诊断。采用复合法对初始权值进行修改，避免了BP算法中初始权值的随机性带来的收敛缓慢甚至瘫痪现象，并结合CSTR模型的故障诊断进行了仿真运算，与BP网络的比较表明了改进算法在运算效率上的优势。
|
| 关 键 词： | 神经网络 初始权值 BP算法 复合法 |
| 文章编号： | 1006-3080(2004)02-0207-04 |
| 修稿时间： | 2003年4月10日 |
Application of BP Network with Changing Initial Weights to CSTR Fault Diagnosis |
| |
| JIANG Yan-jun,LI Ning,HUANG Dao.Application of BP Network with Changing Initial Weights to CSTR Fault Diagnosis[J].Journal of East China University of Science and Technology,2004,30(2):207-210. |
| |
| Authors: | JIANG Yan-jun LI Ning HUANG Dao |
| |
| Institution: | JIANG Yan-jun,LI Ning,HUANG Dao~* |
| |
| Abstract: | Neural networks have been widely used in kinds of research fields. In this paper, faults of CSTR will be detected and diagnosed using an improved BP algorithm. Due to remarkable influence of initial weights on networks' training speed, great attention is paid to selection of initial weights. A compositional method is used to modify initial weights in order to avoid the low convergence and system paralysis caused by the randomicity of initial weights. The fault diagnosis of CSTR model is simulated to indicate higher performance of the improved algorithm compared with BP networks. |
| |
| Keywords: | neural networks initial weight BP algorithm compositional method |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
