计算机科学 ›› 2019, Vol. 46 ›› Issue (11): 323-327.doi: 10.11896/jsjkx.180901719
王岩, 罗倩, 邓辉
WANG Yan, LUO Qian, DENG Hui
摘要： 滚动轴承是旋转机械结构中常用的零件,如果发生故障,会造成极大的危害。随着大数据时代的到来,现代智能诊断方法已被广泛应用到轴承故障诊断中。针对目前智能诊断方法存在的问题,将统计模型引入轴承故障诊断中,提出了基于变分贝叶斯的轴承故障诊断方法。该方法对轴承振动信号进行局部特征尺度分解,得到若干个内禀尺度分量,并分别提取时域特征组成特征集,使用特征集训练产生基于变分贝叶斯的混合多维高斯分布模型,通过计算不同轴承故障的概率实现故障诊断。实验结果表明,所提方法的诊断正确率达到99.6%,与基于支持向量机的轴承诊断方法相比,在所组成的特征集上诊断正确率最高提升了39.6%。文中提出的方法能够全面且有效地诊断滚动轴承故障,对高维复杂的故障数据也有很好的诊断效果。
中图分类号:
| [1]ZHANG R,TAO H,WU L,et al.Transfer Learning with Neural Networks for Bearing Fault Diagnosis in Changing Working Conditions[J].IEEE Access,2017,5:14347-14357. [2]SUN S S,HE G H,CUI J.Fault diagnosis method of rollingbearing based on dual-tree rational-dilation complex wavelet packet transform and SVM[J].Computer Science,2015(S2):131-134.(in Chinese) 孙珊珊,何光辉,崔建.基于有理双树复小波和svm的滚动轴承故诊断方法[J].计算机科学,2015(S2):131-134. [3]FU Q,JING B,HE P,et al.Fault feature selection and diagnosis of rolling bearings based on EEMD and optimized Elman_AdaBoost algorithm[J].IEEE Sensors Journal,2018,18(12):5024-5034. [4]GHAHRAMANI Z.Probabilistic machine learning and artificial intelligence[J].Nature,2015,521(7553):452-459. [5]KONG H H,SHI H B.A Comparative Study of Generative and Discriminative Classification Methods [J].Sci-Tech Information Development & Economy,2010,20(8):78-81.(in Chinese) 孔环环,石洪波.产生式与判别式分类方法比较研究[J].图书情报导刊,2010,20(8):78-81. [6]QIU L,GAO S,CAO C G.Improved Estimation of Distribution Algorithms Based on Normal Distribution[J].Computer Science,2015,42(8):32-35.(in Chinese) 邱玲,高尚,曹存根.改进的正态分布的分布估计算法[J].计算机科学,2015,42(8):32-35. [7]WU Z T,CHENG J S,LI B Q,et al.The method of generalized local characteristic-scale decomposition and its application[J].Journal of Vibration Engineering,2016,29(2):331-339.(in Chinese) 吴占涛,程军圣,李宝庆,等.广义局部特征尺度分解方法及其应用[J].振动工程学报,2016,29(2):331-339. [8]LUO S,CHENG J.VPMCD based novelty detection method on and its application to fault identification for local characteristic-scale decomposition[J].Cluster Computing,2017,20(4):2955-2965. [9]CHAMBERS J M.Graphical Methods for Data Analysis[M].Chapman and Hall/CRC,2017. [10]PAOLELLA M S.New graphical methods and test statistics for testing composite normality[J].Econometrics,2015,3(3):532-560. [11]MA Y,ZHAO S,HUANG B.Multiple-Model State Estimation Based on Variational Bayesian Inference[J].IEEE Transactions on Automatic Control,2018,64(4):1679-1685. [12]CHEN Y,GUO Q,SUN H,et al.A Distributionally Robust Optimization Model for Unit Commitment Based on Kullback-Leibler Divergence[J].IEEE Transactions on Power Systems,2018,33(5):5147-5160. [13]LIM K L,WANG H.MAP approximation to the variationalBayes Gaussian mixture model and application[J].Soft Computing,2017(3):1-13. [14]WU G.Fast and scalable variational Bayes estimation of spatial econometric models for Gaussian data[J].Spatial Statistics,2018,24:32-53. [15]WU W,NAGARAJAN S,CHEN Z.Bayesian Machine Learning:EEG/MEG signal processing measurements[J].IEEE Signal Processing Magazine,2016,33(1):14-36. [16]KANGIN D,MARKARIAN G.Multi-Bernoulli filter for group object tracking and its Gaussian-Wishart implementation[C]∥International Joint Conference on Neural Networks.IEEE,2017:3161-3168. [17]KAMIL A,VINCENT E.Variational Bayesian Inference forSource Separation and Robust Feature Extraction[J].IEEE/ACM Transactions on Audio Speech & Language Processing,2016,24(10):1746-1758. [18]STURROCK K,ROCHA J.A Multidimensional Scaling Stress Evaluation Table:[J].Field Methods,2016,12(1):49-60. [19]LI J R,YUE J H.Fault diagnosis algorithm for the axle box bearing of walking unit in EMU based on HHT and resonance demodulation method[J].Journal of Beijing Jiaotong University,2017,41(4):85-90.(in Chinese) 李佳睿,岳建海.基于HHT及共振解调方法的动车组走行部轴箱轴承故障诊断算法[J].北京交通大学学报,2017,41(4):85-90. |
| [1] | 齐秀秀, 王佳昊, 李文雄, 周帆. 基于概率元学习的矩阵补全预测融合算法 Fusion Algorithm for Matrix Completion Prediction Based on Probabilistic Meta-learning 计算机科学, 2022, 49(7): 18-24. https://doi.org/10.11896/jsjkx.210600126 |
| [2] | 邹承明, 陈德. 高维大数据分析的无监督异常检测方法 Unsupervised Anomaly Detection Method for High-dimensional Big Data Analysis 计算机科学, 2021, 48(2): 121-127. https://doi.org/10.11896/jsjkx.191100141 |
| [3] | 王卫东, 徐金慧, 张志峰, 杨习贝. 基于密度峰值聚类的高斯混合模型算法 Gaussian Mixture Models Algorithm Based on Density Peaks Clustering 计算机科学, 2021, 48(10): 191-196. https://doi.org/10.11896/jsjkx.200800191 |
| [4] | 吴健, 孙保明. 无线传感器网络中基于字典优化的压缩感知定位方法 Dictionary Refinement-based Localization Method Using Compressive Sensing inWireless Sensor Networks 计算机科学, 2019, 46(4): 118-122. https://doi.org/10.11896/j.issn.1002-137X.2019.04.019 |
| [5] | 王卫红, 陈骁, 吴炜, 高星宇. 高分影像复杂背景下的城市水体自动提取方法 Method of Automatically Extracting Urban Water Bodies from High-resolution Images with Complex Background 计算机科学, 2019, 46(11): 277-283. https://doi.org/10.11896/jsjkx.181001985 |
| [6] | 柴五一, 杨丰, 袁绍锋, 黄靖. 用于图像分割的多分类高斯混合模型和基于邻域信息的高斯混合模型 Multi-class Gaussian Mixture Model and Neighborhood Information BasedGaussian Mixture Model for Image Segmentation 计算机科学, 2018, 45(11): 272-277. https://doi.org/10.11896／j.issn.1002-137X.2018.11.043 |
| [7] | 成英超,王瑞胡,胡章平. 一种基于高斯混合模型的协同过滤算法 Novel Approach on Collaborative Filtering Based on Gaussian Mixture Model 计算机科学, 2017, 44(Z6): 451-454. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.101 |
| [8] | 张宜浩,刘智,朱常鹏. 融合距离度量和高斯混合模型的中文词义归纳模型 Chinese Word Sense Induction Model by Integrating Distance Metric and Gaussian Mixture Model 计算机科学, 2017, 44(8): 265-269. https://doi.org/10.11896/j.issn.1002-137X.2017.08.045 |
| [9] | 周红玉,杨扬,张愫. 基于迭代的非刚性点阵配准算法 Non-rigid Point Set Registration Algorithm Based on Iteration 计算机科学, 2016, 43(Z6): 226-231. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.055 |
| [10] | 范文超,李晓宇,魏 凯,陈兴林. 基于改进的高斯混合模型的运动目标检测 Moving Target Detection Based on Improved Gaussian Mixture Model 计算机科学, 2015, 42(5): 286-288. https://doi.org/10.11896/j.issn.1002-137X.2015.05.058 |
| [11] | 韩光,孙宁,李晓飞,赵春霞. 基于混合PSO的高斯混合模型地形分类 Gaussian Mixture Model Terrain Classification Based on Hybrid PSO 计算机科学, 2014, 41(8): 289-292. https://doi.org/10.11896/j.issn.1002-137X.2014.08.061 |
| [12] | 向金海,廖红虹,樊恒,代江华,孙伟平,余胜生. 基于局部强度比率特征的前景检测 Robust Foreground Detection Using Local Intensity Ratio 计算机科学, 2014, 41(3): 293-296. |
| [13] | 胡庆辉,丁立新,陆玉靖,何进荣. 一种快速、鲁棒的有限高斯混合模型聚类算法 Rapid Robust Clustering Algorithm for Gaussian Finite Mixture Model 计算机科学, 2013, 40(8): 191-195. |
| [14] | 尚岩峰，汪辉，汪宁. 基于高斯混合分布和区域竞争主动轮廓的医学目标分割 Medical Object Extraction by Gaussian Mixture Model and Region Competition Active Contour Model 计算机科学, 2012, 39(9): 257-261. |
| [15] | 管 涛. 统计聚类模型研究综述 Overview of Statistical Clustering Models 计算机科学, 2012, 39(7): 18-24. |
|
||
首页