基于知识的模糊神经网络的旋转机械故障诊断

李如强; 陈进; 伍星

基于知识的模糊神经网络的旋转机械故障诊断

上海交通大学振动、冲击、噪声国家重点实验室,上海 200030

基金项目: 国家“十五”科技攻关计划重点资助项目(2001BA204B05_KHKZ0009)

详细信息

作者简介:
李如强(1973- ),男,山东人,讲师,博士(联系人.E-mail:rqli163@163.com).

中图分类号: TP206.3
计量
- 文章访问数: 2826
- HTML全文浏览量: 185
- PDF下载量: 697
- 被引次数: 0
出版历程
- 收稿日期: 2004-10-11
- 修回日期: 2005-08-23
- 刊出日期: 2006-01-15

Fault Diagnosis of Rotating Machinery Using Knowledge-Based Fuzzy Neural Network

The State Key Laboratory of Vibration, Shock & Noise, Shanghai Jiaotong University, Shanghai, 200030, P. R. China

摘要

摘要: 提出了一种基于知识的模糊神经网络并用于故障诊断．首先基于粗糙集对样本数据进行初步规则获取，并计算规则的依赖度和条件覆盖度，然后根据规则数目进行模糊神经网络结构部分设计，规则的依赖度和条件覆盖度用于设定网络初始权重，而用遗产算法对神经网络输出参数进行优化．这样的模糊神经网络称为基于知识的模糊神经网络．使用该网络对旋转机械常见故障进行诊断，结果表明，和一般模糊神经网络相比，该网络具有训练时间短而诊断率高的特点．
- 旋转机械 /
- 故障诊断 /
- 粗糙集 /
- 模糊集 /
- 遗传算法 /
- 基于知识的模糊神经网络
Abstract: A novel knowledge_based fuzzy neural network(KBFNN)for fault diagnosis is presented. Crude rules were extracted and the corresponding dependent factors and antecedent coverage factors were calculated firstly from the diagnostic sample based on rough sets theory.Then the number of rules was used to construct partially the structure of a fuzzy neural network and those factors were implemented as initial weights,with fuzzy output parameters being optimized by genetic algorithm. Such fuzzy neural network was called KBFNN.This KBFNN was utilized to identify typical faults of rotating machinery.Diagnostic results show that it has those merits of shorter training time and higher right diagnostic level compared to general fuzzy neural networks.
- rotating machinery /
- fault diagnosis /
- rough sets theory /
- fuzzy sets theory /
- generic algorithm /
- knowledge_based fuzzy neural network

HTML全文

参考文献(12)

[1]	Renwick J T.Vibration analysis-a proven technique as a predictive maintenance tool[J].IEEE Transactions on Industry Application,1985,21：324—332. doi: 10.1109/TIA.1985.349652
[2]	Toshio T,Tornoya N,Peng C.Failure detection and diagnosis of rotating machinery by orthogonal expansion of density function of vibration signal[A].In:Proceedings. EcoDesign'99: First International Symposium On Environmentally Conscious Design and Inverse Manufacturing[C].Tokyo,Japan:1999,86—891.
[3]	姚洪兴，赵林度，盛昭瀚.基于模糊神经网络的故障诊断方法的应用[J].气轮机技术，2000，42(5)：257—262.
[4]	Pawlak Z.Rough sets[J].International Journal of Information and Computer Science,1982，11(5)：341—348. doi: 10.1007/BF01001956
[5]	OU Jian,SUN Cai-xin,BI Wei-min,et al.A steam turbine-generator vibration fault diagnosis method based on rough set[A].In:Proceedings of IEEE International Conference on Power System Technology[C].Kunming,China：2002,1532—1534.
[6]	LI Xiao-lei,WU Xiao-bing.The application of rough set theory in vehicle transmission system fault diagnosis[A].In:Proceedings of IEEE International Conference on Vehicle Electronics[C].Changchung,China:1999,240—242.
[7]	CAO Long-han,CAO Chang-xiu,GUO Zhen,et al.The research of fault diagnosis for fuel injection system of diesel engine with ANN based on rough sets theory[A].In:Proceeding of the 4th World Congress on Intelligent Control and Automation[C].Shanghai,China:2002,410—414.
[8]	王小平，曹立明.遗传算法——理论、应用与软件实现[M].西安:西安交通大学出版社，2002，1—38.
[9]	Walczak B, Massart D L. Rough sets theory[J].Chemometrics and Intelligent Laboratory Systems,1999,47:1—16. doi: 10.1016/S0169-7439(98)00200-7
[10]	李如强，陈进，伍星.基于模糊C均值聚类和粗糙集理论的旋转机械故障诊断[J].信息与控制，2004，24(1):4—5.
[11]	Mitra S,Mitra P,Pal S K.Evolutionary modular design of rough knowledge-based network using fuzzy attributes[J].Neurocomputing,2001,36:45—66. doi: 10.1016/S0925-2312(00)00335-0
[12]	Sawyer J.Sawyer's Turbomachinery Maintenance Handbooks[M].Turbomachinery International Publications,1980.