The BP Neural Network Fault Diagnosis of Bearings Based on Wavelet and Information Granulation
-
摘要: 通过对圆锥滚子轴承轴向故障振动信号的预处理,得到响应的特征,从而利用BP神经网络进行故障诊断。首先利用一种新的小波消噪算法对监测信号进行预处理,该算法是基于最佳正交小波基的选择,使熵在小波收缩过程中的作用最小;文章重点在于利用模糊信息粒化对消噪后信号进行模糊粒化,从而更好的特征提取;最后将特征向量作为输入,运用BP神经网络进行故障诊断。通过实验故障信号验证了,消噪后的信号能更好地进行特征提取;同时,模糊粒化后能更准确的进行故障诊断。Abstract: Through using the tapered roller-bearing axial fault vibration signal,we get the response characteristics and take advantage of BP neural network for fault diagnosis.Firstly,a new wavelet-denoising algorithm is used to pre-monitor signals,which is based on the best selection of orthogonal wavelet bases,aiming at the minimum entropy effect in the process of Wavelet Shrinkage.Then use the fuzzy information granulation to granulate the noised signal;followed signal of fuzzy granular layer wavelet packet decomposition and reconstruction,by no fault and fault feature vectors.Finally,take the feature vectors as input and use BP neural network for fault diagnosis.Fault signal is verified by experiments and the signal after denoising is better for feature extraction;meanwhile,the signal after fuzzy granulation can be used for more accurate fault diagnosis.
-
Key words:
- wavelet-denoising /
- information granulation /
- BP neural network /
- bearing /
- fault diagnosis
-
[1] 李永龙, 绍忍平, 曹精明.基于小波包与支持向量机结合的齿轮故障分类研究[J]. 西北工业大学学报, 2010, 28(4) [2] 毕果, 陈进.组合切片分析在滚动轴承故障诊断中的应用研究[J]. 机械科学与技术, 2009, 28(2):182~185 [3] 曾小军, 黄宜坚.基于 AR 模型和支持向量机的故障诊断方法[J]. 机械科学与技术, 2010, 29(7):972~980 [4] 谭真臻, 陈果, 孙丽萍.基于 Hilbert 谱图特征的转子故障智能诊断[J]. 机械科学与技术, 2010, 29(9):1177~1181 [5] 张周锁, 闫晓旭, 成玮.粒计算及其在机械故障智能诊断中的应用[J]. 西安交通大学学报, 2009, 43(9):37~41 [6] 吴涛等.滚动轴承振动诊断的 SOM 神经网络方法[J]. 机械设计与制造, 2010, (1):198~200 [7] Goumas S K,Zervakis M E.Classification of washing machinesvibration signals using discrete wavelet analysis for feature extrac-tion[J]. IEEE Transactions on Instrumentation and Meas-urement, 2002, 51(3):497~508 [8] 李建平, 杨万年译.小波十讲[M]. 北京:国防工出版社, 2004 [9] 胡广书.现代信号处理教程[M]. 北京:清华大学出版社, 2004 [10] Donoho D L.De-noising by soft-thresholding[J]. IEEE Trans-actions on Information Theory, 1995, 41(3):613~627 [11] 史峰等.Matlab 神经网络30 个案例分析[M]. 北京:北京航空航天大学出版社, 2010 [12] Zadel L A.Towards a theory of fuzzy information granulation andits centrality in human reasoning and fuzzy logic[J]. Fuzzy Setsand System, 1997, 90(2):111~127 [13] 张铃, 张钹.模糊商空间理论(模糊粒度计算方法)[J]. 软件学报, 2003, 14(4):770~776 [14] Yao Y Y.Relational interpretations of neighorhood operators andrough set approximation operators[J]. Information Science,1998, 111(1/4):239~259 [15] Pawlak Z.Granularity of knowledge,indiscernibility and roughsets[A]. Proceedings of IEEE World Congress on Computa-tional Intelligence[C],Piscataway, NJ, USA:IEEE, 1998 [16] Zheng Z, Hu H, Shi Z Z.Tolerance granular space and its appli-cations[A]. IEEE International Conference on GranularComputing[C],Piscataway, NJ, USA:IEEE, 2005 [17] 王国胤, 张清华, 胡军.粒计算研究综述[J]. 智能系统学报,2007, 2(6):8~26 [18] 谢克明, 逯新红, 陈泽华.粒计算的基本问题和研究[J]. 计算机工程与应用, 2007, 43(6) [19] Bargiela A,Pedrycz W.Granular Computing:An Introduc-tion[M]. Kluwer Academic Publishers, Dodrecht, 2003 [20] 飞思科技产品研发中心编著.神经网络理论与 Matlab7 实现[M]. 北京:电子工业出版社, 2005
点击查看大图
计量
- 文章访问数: 274
- HTML全文浏览量: 36
- PDF下载量: 11
- 被引次数: 0