|
|
|
Fault detection method based on computational intelligence
technology fusion |
| DENG Wu1,2,3, CHEN Rong1, SONG Yingjie 1 |
1.Department of Informational Science and Technology, Dalian Maritime University, Dalian 116026, China;
2. Department of Software, Dalian Jiaotong University, Dalian 116028, China; 3. Key Laboratory of Intelligent
Manufacture of Hunan Province, Xiangtan University, Xiangtan 411105, China |
|
|
|
Abstract A computational intelligence technology fusion method of fault detection was proposed in order to improve the detection precision and decrease the misinformation detection of complex system. The various approaches such as rough set, genetic algorithm and neural network were integrated to synthesize their merits for fault detection. According to the uncertainty and imperfection of the original sample data, the rough set was used to pretreat for the normalization of data, the discretization of continuous data and the attribute reduction in order to obtain the minimum fault feature subset. The genetic algorithm with the ability of strong global search was used to train the weights of back propagation neural network. The minimum reduced subset was inputted into the trained network to construct the fault detection model that can classify the pretreated fault feature vectors under certain states to realize the fault detection. The motor bearing experiment results show that the method can optimize the structure of neural network and improve the rate and precision of fault detection.
|
|
Published: 01 July 2010
|
|
|
基于计算智能技术融合的故障识别方法
为了提高复杂系统故障识别的精度和降低误报率,利用粗糙集理论、遗传算法、神经网络等计算智能方法的优势,提出一种基于计算智能技术融合的故障识别方法.针对原始样本数据的不确定性和不完备性,利用粗糙集对原始样本数据进行数据归一化、离散化、属性约简等预处理,求得能够覆盖原始数据特征的具有最大完备度的最小规则集.利用具有全局搜索能力的遗传算法直接训练反向传播神经网络的权值,将规则集作为网络输入,形成优化网络模型.采用该模型对预处理的各种状态故障特征向量进行分类决策,实现故障识别.通过电机轴承故障识别实验表明,该方法能够优化网络结构,提高故障识别速度和准确率.
|
|
| ［1］ 张萍,王桂增,周东华.动态系统的故障诊断方法［J］.控制理论与应用,2000,17(2): 153159.
ZHANG Ping, WANG Guizeng, ZHOU Donghua.Fault diagnosis methods for dynamic systems ［J］. Control Theory and Applications, 2000, 17(2): 153159.
［2］ 林勇,周晓军,杨先勇,等.基于双谱识别和人工免疫网络的智能故障检测［J］.浙江大学学报：工学版,2009,43(10): 17771782.
LIN Yong, ZHOU Xiaojun, YANG Xianyong, et al. Intelligent fault diagnosis methods based on bispectrum recognition and artificial immune network ［J］. Journal of Zhejiang University: Engineering Science, 2009, 43(10): 17771782.
［3］ 姜苍华,周东华.基于计算智能方法的动态系统故障诊断技术［J］.控制工程,2003,10(5): 385390.
JIANG Canghua, ZHOU Donghua. Fault diagnosis techniques based on computational intelligence for dynamic systems ［J］.Control Engineering of China, 2003, 10(5): 385390.
［4］ 代建华,陈卫东,潘云鹤.基于粗糙集的综合推理模型［J］. 浙江大学学报：工学版,2006,40(9): 15261530.
DAI Jianhua, CHEN Weidong, PAN Yunhe. Synthesis reasoning model based on rough set theory ［J］. Journal of Zhejiang University: Engineering Science, 2006, 40(9): 15261530.
［5］ WU J D, WANG Y H, CHIANG P H, et al. A study of fault diagnosis in a scooter using adaptive order tracking technique and neural network ［J］. Expert Systems with Applications, 2009, 36(1): 4956.
［6］ WU J D, LIU C H. Investigation of engine fault diagnosis using discrete wavelet transform and neural network ［J］. Expert Systems with Applications, 2008, 35(3): 12001213.
［7］ PIRMORADI F N, SASSANI F, SILVA C D. Fault detection and diagnosis in a spacecraft attitude determination system ［J］. Acta Astronautica, 2009, 65(5): 710729.
［8］ PAWLAK Z. Rough sets ［J］. International Journal of Computer and Information Science, 1982, 11(5): 341356.
［9］ 张文修,吴伟业,梁吉业,等.粗糙集理论与方法［M］.北京：科学出版社,2001: 940.
［10］ 谭天乐,宋执环,李平.基于粗糙集的故障诊断方法［J］.浙江大学学报：工学版,2003,37(1): 4751.
TAN Tianle, SONG Zhihuan, LI Ping. Approach for fault detection and diagnosis based on rough set ［J］.Journal of Zhejiang University: Engineering Science, 2003, 37(1): 4751.
［11］ GENG Z, ZHU Q. Rough setbased heuristic hybrid recognizer and its application in fault diagnosis ［J］. Expert Systems with Applications, 2009, 36(2): 27112718.
［12］ TAN Y H, HE Y G, CUI C, et al. A novel method for analog fault diagnosis based on neural networks and genetic algorithm ［J］. IEEE Transactions on Neural Networks, 2008, 57(11): 26312639.
［13］ 廖瑛,张绍勇,尹大伟,等.基于粗糙集遗传神经网络的柴油机故障诊断［J］.控制工程,2009,16(6): 709713.
LIAO Ying, ZHANG Shaoyong, YIN Dawei, et al. Faults diagnosis of diesels based on rough set genetic neural networks ［J］. Control Engineering of China, 2009, 16(6): 709713.
［14］ 姚鑫骅,徐月同,傅建中,等.基于粗糙集理论的数控机床智能故障诊断研究［J］.浙江大学学报：工学版,2008,42(10): 17191785.
YAO Xinhua, XU Yuetong, FU Jianzhong, et al. Intelligent fault diagnosis of CNC machine tools based on rough set theory ［J］. Journal of Zhejiang University: Engineering Science, 2008, 42(10): 17191785.
［15］ RYSZARD N. Evaluation of vibroacoustic diagnostic symptoms by means of the rough sets theory ［J］. Computers in Industry, 1992, 20 (2): 141152.
［16］ 金微,陈慧萍.基于分层聚类的kmeans算法［J］.河海大学常州分校学报,2007,21(1): 710.
JIN Wei, CHEN Huiping. A hybrid hierarchical kmeans clustering algorithm ［J］. Journal of Hohai University Changzhou,2007,21(1): 710.
［17］ MASAHIRO I. Attribute reduction in variable precision rough set model ［J］.International Journal of Uncertainty, Fuzziness and Knowledgebased Systems, 2006, 14(4): 461479.
［18］ 王翔飞,须文波.属性约简的一种新计算方法［J］.微电子学与计算机,2007,24(4): 99101.
WANG Xiangfei, XU Wenbo. A new method for attributes reduction ［J］. Microelectronics and Computer, 2007, 24(4): 99101. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
