留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

改进的深度置信网络在电主轴故障诊断中的应用

李滨 曾辉

李滨, 曾辉. 改进的深度置信网络在电主轴故障诊断中的应用[J]. 机械科学与技术, 2021, 40(7): 1051-1057. doi: 10.13433/j.cnki.1003-8728.20200172
引用本文: 李滨, 曾辉. 改进的深度置信网络在电主轴故障诊断中的应用[J]. 机械科学与技术, 2021, 40(7): 1051-1057. doi: 10.13433/j.cnki.1003-8728.20200172
LI Bin, ZENG Hui. Application of Improved Deep Belief Network in Electric Spindle Fault Diagnosis[J]. Mechanical Science and Technology for Aerospace Engineering, 2021, 40(7): 1051-1057. doi: 10.13433/j.cnki.1003-8728.20200172
Citation: LI Bin, ZENG Hui. Application of Improved Deep Belief Network in Electric Spindle Fault Diagnosis[J]. Mechanical Science and Technology for Aerospace Engineering, 2021, 40(7): 1051-1057. doi: 10.13433/j.cnki.1003-8728.20200172

改进的深度置信网络在电主轴故障诊断中的应用

doi: 10.13433/j.cnki.1003-8728.20200172
基金项目: 

航空发动机中介机匣铣车复合高效加工技术开发 6000001072

详细信息
    作者简介:

    李滨(1975-), 副教授, 硕士生导师, 研究方向为机电一体化技术应用、先进制造技术与装备, 630104635@qq.com

  • 中图分类号: TH133.33

Application of Improved Deep Belief Network in Electric Spindle Fault Diagnosis

  • 摘要: 针对加工中心电主轴中滚动轴承等零部件容易出现故障或者失效等问题, 即提出一种改进的DBN(深度置信网络)电主轴故障诊断方法。该方法对电主轴中滚动轴承运行故障状态下的振动信号进行特征提取, 然后通过DBN映射出信号与故障特征的复杂关系来进行故障诊断。其中为提高训练DBN的效率以及解决在反向传播过程中梯度消失的问题, 提出一种新型激活函数。研究结果表明, 采用新型激活函数的DBN不仅降低了时间成本, 同时也具有较高的故障识别的能力。
  • 图  1  深度置信网络结构图

    图  2  Tanh和IM-Tanh的原函数图像

    图  3  Tanh和IM-Tanh的导数图像

    图  4  电主轴故障诊断流程图

    图  5  故障诊断正确率随位置参数的变化图

    图  6  故障诊断正确率随斜率参数的变化图

    图  7  轴承故障类型诊断正确率随迭代次数的变化

    表  1  轴承故障数据集类型描述

    故障类型 故障深度/Inch 数据集A1 数据集A2 数据集A3 数据集A0 故障类别
    正常 0 50 50 50 150 1
    内1 0.007 50 50 50 150 2
    内2 0.014 50 50 50 150 3
    内3 0.021 50 50 50 150 4
    外1 0.007 50 50 50 150 5
    外2 0.014 50 50 50 150 6
    外3 0.021 50 50 50 150 7
    滚1 0.007 50 50 50 150 8
    滚2 0.014 50 50 50 150 9
    滚3 0.021 50 50 50 150 10
    下载: 导出CSV

    表  2  不同激活函数的故障识别正确率

    激活函数 Sigmoid Tanh IM-Tanh Relu
    正确率/% 91.2 89.5 99.7 86.6
    迭代数 830 850 630 920
    时间t/s 41.254 4 35.583 1 30.877 6 33.176 5
    下载: 导出CSV
  • [1] 庞红. 加工中心电主轴故障诊断系统研究[D]. 昆明: 昆明理工大学, 2018

    PANG H. Research on fault diagnosis system of electrical spindle in machining center[D]. Kunming: Kunming University of Science and Technology, 2018 (in Chinese)
    [2] 雷亚国, 贾封, 周昕, 等. 基于深度学习理论的机械装备大数据健康监测方法[J]. 机械工程学报, 2015, 51(21): 49-56 https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB201521007.htm

    LEI Y G, JIA F, ZHOU X, et al. A deep learning-based method for machinery health monitoring with big data[J]. Journal of Mechanical Engineering, 2015, 51(21): 49-56 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB201521007.htm
    [3] 刘帅师, 程曦, 郭文燕, 等. 深度学习方法研究新进展[J]. 智能系统学报, 2016, 11(5): 567-577 https://www.cnki.com.cn/Article/CJFDTOTAL-ZNXT201605001.htm

    LIU S S, CHENG X, GUO W Y, et al. Progress report on new research in deep learning[J]. CAAI Transactions on Intelligent Systems, 2016, 11(5): 567-577 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZNXT201605001.htm
    [4] 段艳杰, 吕宜生, 张杰, 等. 深度学习在控制领域的研究现状与展望[J]. 自动化学报, 2016, 42(5): 643-654 https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201605002.htm

    DUAN Y J, LV Y S, ZHANG J, et al. Deep learning for control: the state of the art and prospects[J]. Acta Automatica Sinica, 2016, 42(5): 643-654 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201605002.htm
    [5] 尹宝才, 王文通, 王立春. 深度学习研究综述[J]. 北京工业大学学报, 2015, 41(1): 48-59 https://www.cnki.com.cn/Article/CJFDTOTAL-BJGD201501011.htm

    YIN B C, WANG W T, WANG L C. Review of deep learning[J]. Journal of Beijing University of Technology, 2015, 41(1): 48-59 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-BJGD201501011.htm
    [6] 任浩, 屈剑锋, 柴毅, 等. 深度学习在故障诊断领域中的研究现状与挑战[J]. 控制与决策, 2017, 32(8): 1345-1358 https://www.cnki.com.cn/Article/CJFDTOTAL-KZYC201708001.htm

    REN H, QU J F, CHAI Y, et al. Deep learning for fault diagnosis: the state of the art and challenge[J]. Control and Decision, 2017, 32(8): 1345-1358 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-KZYC201708001.htm
    [7] TAMILSELVAN P, WANG P F. Failure diagnosis using deep belief learning based health state classification[J]. Reliability Engineering & System Safety, 2013, 115: 124-135 http://www.sciencedirect.com/science/article/pii/S0951832013000574
    [8] TRAN V T, ALTHOBIANI F, BALL A. An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks[J]. Expert Systems with Applications, 2014, 41(9): 4113-4122 doi: 10.1016/j.eswa.2013.12.026
    [9] GAN M, WANG C, ZHU C A. Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings[J]. Mechanical Systems and Signal Processing, 2016, 72-73: 92-104 doi: 10.1016/j.ymssp.2015.11.014
    [10] SHAO H D, JIANG H K, LIN Y, et al. A novel method for intelligent fault diagnosis of rolling bearings using ensemble deep auto-encoders[J]. Mechanical Systems and Signal Processing, 2018, 102: 278-297 doi: 10.1016/j.ymssp.2017.09.026
    [11] 张士强. 基于深度学习的故障诊断技术研究[D]. 哈尔滨: 哈尔滨工业大学, 2018

    ZHANG S Q. Research on fault diagnosis technology based on deep learning[D]. Harbin: Harbin Institute of Technology, 2018 (in Chinese)
    [12] 赵光权, 葛强强, 刘小勇, 等. 基于DBN的故障特征提取及诊断方法研究[J]. 仪器仪表学报, 2016, 37(9): 1946-1953 doi: 10.3969/j.issn.0254-3087.2016.09.004

    ZHAO G Q, GE Q Q, LIU X Y, et al. Fault feature extraction and diagnosis method based on deep belief network[J]. Chinese Journal of Scientific Instrument, 2016, 37(9): 1946-1953 (in Chinese) doi: 10.3969/j.issn.0254-3087.2016.09.004
    [13] 周兆永, 何东健, 张海辉, 等. 基于深度信念网络的苹果霉心病病害程度无损检测[J]. 食品科学, 2017, 38(14): 297-303 doi: 10.7506/spkx1002-6630-201714046

    ZHOU Z Y, HE D J, ZHANG H H, et al. Non-destructive detection of moldy core in apple fruit based on deep belief network[J]. Food Science, 2017, 38(14): 297-303 (in Chinese) doi: 10.7506/spkx1002-6630-201714046
    [14] 贾继德, 贾翔宇, 梅检民, 等. 基于小波与深度置信网络的柴油机失火故障诊断[J]. 汽车工程, 2018, 40(7): 838-843 https://www.cnki.com.cn/Article/CJFDTOTAL-QCGC201807014.htm

    JIA J D, JIA X Y, MEI J M, et al. Misfire fault diagnosis of diesel engine based on wavelet and deep belief network[J]. Automotive Engineering, 2018, 40(7): 838-843 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-QCGC201807014.htm
    [15] 鲁春燕, 李炜. 基于深度置信网络的炼化空压机故障诊断方法[J]. 化工学报, 2019, 70(2): 757-763 https://www.cnki.com.cn/Article/CJFDTOTAL-HGSZ201902040.htm

    LU C Y, LI W. Fault diagnosis method of petrochemical air compressor based on deep belief network[J]. CIESC Journal, 2019, 70(2): 757-763 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-HGSZ201902040.htm
    [16] 时培明, 梁凯, 赵娜, 等. 基于深度学习特征提取和粒子群支持向量机状态识别的齿轮智能故障诊断[J]. 中国机械工程, 2017, 28(9): 1056-1061, 1068 doi: 10.3969/j.issn.1004-132X.2017.09.009

    SHI P M, LIANG K, ZHAO N, et al. Intelligent fault diagnosis for gears based on deep learning feature extraction and particle swarm optimization SVM state identification[J]. China Mechanical Engineering, 2017, 28(9): 1056-1061, 1068 (in Chinese) doi: 10.3969/j.issn.1004-132X.2017.09.009
    [17] 李飞, 高晓光, 万开方, 等. 基于权值动量的RBM加速学习算法研究[J]. 自动化学报, 2017, 43(7): 1142-1159 https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201707004.htm

    LI F, GAO X G, WAN K F, et al. Research on RBM accelerating learning algorithm with weight momentum[J]. Acta Automatica Sinica, 2017, 43(7): 1142-1159 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201707004.htm
    [18] 刘小文, 郭大波, 李聪. 卷积神经网络中激活函数的一种改进[J]. 测试技术学报, 2019, 33(2): 121-125 doi: 10.3969/j.issn.1671-7449.2019.02.006

    LIU X W, GUO D B, LI C. An improvement of the activation function in convolutional neural networks[J]. Journal of Test and Measurement Technology, 2019, 33(2): 121-125 (in Chinese) doi: 10.3969/j.issn.1671-7449.2019.02.006
    [19] 王红霞, 周家奇, 辜承昊, 等. 用于图像分类的卷积神经网络中激活函数的设计[J]. 浙江大学学报, 2019, 53(7): 1363-1373 https://www.cnki.com.cn/Article/CJFDTOTAL-ZDZC201907016.htm

    WANG H X, ZHOU J Q, GU C H, et al. Design of activation function in CNN for image classification[J]. Journal of Zhejiang University, 2019, 53(7): 1363-1373 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZDZC201907016.htm
    [20] 邢剑锋. 基于改进的深度信念网络的行星减速器智能故障诊断方法研究[D]. 重庆: 重庆大学, 2017

    XING J F. Study on intelligent fault diagnosis of planetary reducer based on improved depth belief network[D]. Chongqing: Chongqing University, 2017 (in Chinese)
    [21] 李旋, 周清锋, 何朝津, 等. 经验模式分解与小波变换在模拟信号中的对比分析[J]. 地质学刊, 2009, 33(1): 79-83 https://www.cnki.com.cn/Article/CJFDTOTAL-JSDZ200901023.htm

    LI X, ZHOU Q F, HE C J, et al. Comparison analysis of empirical mode decomposition and wavelet decomposition in analog signals[J]. Journal of Geology, 2009, 33(1): 79-83 (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JSDZ200901023.htm
    [22] BORG G G, HARRIS J H. Application of plasma columns to radiofrequency antennas[J]. Applied Physics Letters, 1999, 74(22): 3272-3274 doi: 10.1063/1.123317
    [23] 赵志宏, 杨绍普, 申永军. 一种改进的EMD降噪方法[J]. 振动与冲击, 2009, 28(12): 35-37, 62 doi: 10.3969/j.issn.1000-3835.2009.12.010

    ZHAO Z H, YANG S P, SHEN Y J. Improved EMD based de-noising method[J]. Journal of Vibration and Shock, 2009, 28(12): 35-37, 62 (in Chinese) doi: 10.3969/j.issn.1000-3835.2009.12.010
    [24] LOPARO K A. Bearing data center, case western reserve university[EB/OL]. http://www.eecs.case.edu/laboratory/bearing
  • 加载中
图(7) / 表(2)
计量
  • 文章访问数:  220
  • HTML全文浏览量:  48
  • PDF下载量:  27
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-12-10
  • 刊出日期:  2021-07-01

目录

    /

    返回文章
    返回