| 基于粗糙集与人工神经网络的变压器故障诊断 |
| |
| 引用本文： | 宫会丽,宋学艳,丁香乾.基于粗糙集与人工神经网络的变压器故障诊断[J].中国海洋大学学报(自然科学版),2005,35(6):1045-1048. |
| |
| 作者姓名： | 宫会丽 宋学艳 丁香乾 |
| |
| 作者单位： | 1. 中国海洋大学信息工程中心,山东,青岛,266071
2. 颐中烟草(集团)有限公司信息中心,山东,青岛,266001 |
| |
| 摘 要： | 根据电力变压器故障诊断问题,提出了基于粗糙集与人工神经网络的变压器故障诊断模型,分析了该模型的实现步骤.采用Kohonen网络对连续属性值进行离散化,应用粗糙集理论对特征参数进行属性约简,并把约简结果生成规则作为BP网络的输入.仿真结果表明,把经过粗糙集理论预处理过的数据送入BP网络训练,提高了学习速度和故障诊断正确率,减少了训练时间.
|
| 关 键 词： | 变压器故障诊断 BP神经网络 粗糙集 约简 |
| 文章编号： | 1672-5174(2005)06-1045-04 |
| 收稿时间： | 2005-04-04 |
| 修稿时间： | 2005-06-18 |
Research on Transformer Fault Diagnosis with Rough Sets Theory and BP Neural Networks |
| |
| GONG Hui-Li,SONG Xue-Yan,DING Xiang-Qian.Research on Transformer Fault Diagnosis with Rough Sets Theory and BP Neural Networks[J].Periodical of Ocean University of China,2005,35(6):1045-1048. |
| |
| Authors: | GONG Hui-Li SONG Xue-Yan DING Xiang-Qian |
| |
| Institution: | 1. Center of Information Engineering, Ocean University of China, Qingdao 266071, China; 2. Information Centre, Etsong Tobacco Group, Qingdao 266071, China |
| |
| Abstract: | In this article, aiming at transformer fault diagnosis, a diagnosis model based on rough set theory and BP neural networks is brought forward and the realization steps of the model are analyzed. After the continuous attributes are discretized with a Kohonen neural network, rough sets theory is used to simplify the attribute parameters. The reduction results are transformed into rules, which are used as input of the BP neural network. The simulations show that the learning speed and diagnosis correctness are greatly improved after the training data is processed by rough sets, and the computation time is decreased by using rough set theory. |
| |
| Keywords: | transformer fault diagnosis BP neural network rough sets reduction |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
