基于多核非负矩阵分解的机械故障诊断 -- 西北工业大学学报,2015,33(2):251-258
论文:2015,Vol:33,Issue(2):251-258
引用本文:
杨永生, 张优云, 朱永生. 基于多核非负矩阵分解的机械故障诊断[J]. 西北工业大学学报
Yang Yongsheng, Zhang Youyun, Zhu Yongsheng. The Fault Diagnosis Technology of Mechanical Equipment Based on Multi-Kernel Non-negative Matrix Factorization(MKNMF)[J]. Northwestern polytechnical university

基于多核非负矩阵分解的机械故障诊断
杨永生1,2, 张优云1, 朱永生1
1. 西安交通大学机械工程学院, 陕西西安 710049;
2. 陕西省行政学院计算机系, 陕西西安 710068
摘要:
在机械设备故障诊断研究领域中,系统采集的原始监测数据经过处理得到的结果往往是数据量很大,维数很高的图像数据,因此,从高维图像中获取敏感特征是当前故障诊断领域中面临的一项关键技术。本文提出了基于多核非负矩阵分解的机械设备故障诊断方法,该方法克服了传统故障诊断需对机械设备信号进行特征提取而造成信息丢失,通过应用多核非负矩阵分解方法进行降维,然后结合多核支持向量机实现对降维后的数据直接进行识别。实验证明该方法可降低原始数据特征的维数,提高分类运算的效率以及故障诊断的识别率。
关键词:    多核非负矩阵分解    支持向量机    故障诊断    数据降维   
The Fault Diagnosis Technology of Mechanical Equipment Based on Multi-Kernel Non-negative Matrix Factorization(MKNMF)
Yang Yongsheng1,2, Zhang Youyun1, Zhu Yongsheng1
1. College of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049 China;
2. Department of Computer Engineering, Shaanxi Academy of Governance, Xi'an 710068 China
Abstract:
In the fault diagnosis field of mechanical equipment, the result of analyzing the collected monitoring data from the equipment is often the high dimensionality of images which contain mass data; so the method of extracting sensitive feature from the high-dimensional information or image is a key technology. We present a new method for fault diagnosis of mechanical equipment based on Multi-Kernel Non-negative Matrix Factorization (MKNMF), which overcomes the defect that the traditional fault diagnosis of mechanical equipment requires signal feature extraction this defect causes loss of information; we reduce dimensions for high dimension information through applying Multi-Kernel Non-negative Matrix Factorization method and then distinguish the dimensionality reduction data with Multi-Kernel Support Vector Machine (MKSVM). The experiments and their analysis show preliminarily that this method can reduce the dimensions of the original monitored data and improve the recognition rate of machine fault diagnosis.
Key words:    computational efficiency    data acquisition    equipment    factorization    failure analysis    feature extraction    flowcharting    genetic algorithms    matrix algebra    optimization    pixels    schematic diagrams    support vector machines    data dimensionality reduction    fault diagnosis    MKNMF(Multi-Kernel Non-negative Matrix Factorization)    MKSVM (Multi-Kernel Support Vector Machine)   
收稿日期: 2014-09-14     修回日期:
DOI:
基金项目: 国家科技重大专项(2012ZX04005-011)资助
通讯作者:     Email:
作者简介: 杨永生(1963-),陕西省行政学院教授、博士研究生,主要从事故障诊断与模式识别研究。
相关功能
PDF(1323KB) Free
打印本文
把本文推荐给朋友
作者相关文章
杨永生  在本刊中的所有文章
张优云  在本刊中的所有文章
朱永生  在本刊中的所有文章

参考文献:
[1] Giger M L, Karssemeijer N, Schnabel J A. Breast Image Analysis for Risk Assessment[J]. Detection, Diagnosis, and Treatment of Cancer Annual Review of Biomedical Engineering, 2013, 15:327-357
[2] Peng Z K, Meng G, Chu F L. Improved Wavelet Reassigned Scalograms and Application for Modal Parameter Estimation[J]. Shock and Vibration, 2011, 18:299-316
[3] Wang D. Support Vector Data Description for Fusion of Multiple Health Indicators for Enhancing Gearbox Fault Diagnosis and Prognosis[J]. Measurement Science and Technology, 2011, 22(2):025-102
[4] 朱丽,龙兵,刘震.基于ARMA的雷达发射机故障预测及其实现[J].计算机测量与控制, 2010, 18(11):2460-2461 Zhu Li, Long Bin, Liu Zhen. ARMA-Based Fault Prediction for Radar Transmitter and Its Realization Method[J].Computer Measurement & Control, 2010, 18(11):2460-2461(in Chinese)
[5] Liu Y H, Liu Y C, Chen Y Z. High-Speed Inline Defect Detection for TFT-LCD Array Process Using a Novel Support Vector Data Description. Expert Systems with Applications, 2011, 38(5):6222-6231
[6] 罗颂荣,程军圣,杨宇.基于本征时间尺度分解和变量预测模型模式识别的机械故障诊断[J].计算机测量与控制, 2013, 32(13):43-48 Luo Songrong, Cheng Junsheng, Yang Yu. Machine Fault Diagnosis Method Using ITD and Variable Predictive Model-Based Class Discrimination[J]. Journal of Vibration and Shock, 2013, 32(13):43-48(in Chinese)
[7] 卢进军.基于非负矩阵分解的相关反馈图像检索算法[J].上海交通大学学报,2005,39(4):578-581 Lu Jinjun. Non-Negative Matrix Factorization Based Relevance Feedback Algorithm in Image Retrieval[J]. Journal of Shanghai Jiaotong University, 2005, 39(4):578-581(in Chinese)
[8] 汪洪桥,蔡艳宁.多尺度核方法的自适应序列学习及应用[J].模式识别与人工智能, 2011(01):72-81 Wang Hongqiao, Cai Yanning. Adaptive Sequence Learning and Applications for Multi-Scale Kernel Method[J]. Pattern Recognition and Artificial Intelligence, 2011(01):72-81(in Chinese)
[9] 亓晓振,王庆.一种基于稀疏编码的多核学习图像分类方法[J].电子学报,2012, 40(4):773-779 Qi Xiaozhen, Wang Qing. An Image Classification Approach Based on Sparse Coding and Multiple Kernel Learning[J]. Acta Electronica Sinica, 2012, 40(4):773-779(in Chinese)
[10] 李谦,景丽萍,于剑.基于多核学习的投影非负矩阵分解算法[J].计算机科学,2014, 41(2):64-67 Li Qian, Jing Liping, Yu Jian. Multi-Kernel Projective Nonnegative Matrix Factorization Algorithm[J]. Computer Science, 2009,32(8):2014, 41(2):64-67(in Chinese)
[11] 张周锁,李凌均,何正嘉.基于支持向量机的机械故障诊断方法研究[J].西安交通大学学报, 2002, 36(2):1303-1306 Zhang Zhousuo, Li Lingjun, He Zhengjia. Research on Diagnosis Method of Machinery Fault Based on Support Vector Machine[J]. Journal of Xi'an Jiaotong University, 2002, 36(2):1303-1306(in Chinese)
相关文献:
1.陈绍炜, 柳光峰, 冶帅.基于核极限学习机的模拟电路故障诊断研究[J]. 西北工业大学学报, 2015,33(2): 290-294
2.窦丹丹, 姜洪开, 何毅娜.基于信息熵和SVM多分类的飞机液压系统故障诊断[J]. 西北工业大学学报, 2012,30(4): 529-534