A New Type of DSCNN-GRU Structure for Bearing Fault Diagnosis of Reducer
-
摘要: 结合深度学习理论,将一维卷积神经网络运用于振动信号故障诊断,相较于传统方法,提取特征简单且高效。为进一步优化一维卷积结构,弥补其在信号所有位置的寻找模式,联系周期内的故障特征,提出一种新型DSCNN-GRU网络。该模型融合了深度可分离卷积的轻量快捷,降低了一维卷积结构参数;加入门控机制,可记忆分析故障点的信号特征,联系周期内的信号关系,更好地捕捉信号故障特征,提升对时间序列的敏感性。提出一种跟踪梯度优化Adam算法,解决模型随时间窗振荡问题。通过采集的减速机滚动轴承数据研究表明,该算法平均故障识别率可达94%以上,分类效果明显,泛化能力强。Abstract: Being based on the theory of deep learning, one-dimensional Convolutional Neural Networks is applied to fault diagnosis of bearing vibration signals. Compared with traditional methods, extraction feature is simple and efficient. In order to further optimize the one-dimensional convolution structure, smooth over its search mode at all positions of the signal, and connect the fault characteristics in the period, a new DSCNN-GRU network model is proposed. The model combines the lightweight and fast of Depthwise Separable Convolution, and reduces the structural parameters of one-dimensional convolution. By adding gating mechanism, the signal characteristics of fault points can be memorized and analyzed, and the signal relationship in the period can be linked to better capture the signal fault characteristics and enhance the sensitivity of temporal series. An Adam algorithm for tracking gradient optimization is proposed to solve the problem of model with time windows oscillation. The data collected from the reducer rolling bearing shows that the average fault recognition rate of the algorithm can reach more than 94%, the classification effect is obvious, and the generalization ability is stronger.
-
表 1 训练数据集数目描述
数据集 滚动体 内圈 外圈 正常 1 2 3 4 5 6 7 8 9 0 0.18mm 0.36mm 0.54mm 0.18mm 0.36mm 0.54mm 0.18mm 0.36mm 0.54mm 0 训练集 840 840 840 840 840 840 840 840 840 840 验证集 240 240 240 240 240 240 240 240 240 240 测试集 120 120 120 120 120 120 120 120 120 120 注:表中数据是在4种电机功率(0, 0.75 kW, 1.5 kW, 2.25 kW)下采集的数据,每一个功率包含D1~D4数据集。 表 2 DSCNN-GRU结构参数
层数 层结构 输入张量 卷积核大小/维度 特征图张量 步长 填充 1 卷积层1 N×4 096×1 81×1×16 N×512×16 8 零补 2 池化层1 N×512×16 2×1×16 N×256×16 2 3 卷积层2 N×256×16 49×16×16 N×128×16 2 零补 4 池化层2 N×128×16 2×1×16 N×64×16 2 5 分离卷积1 N×64×16 9×1×32 N×64×32 1 零补 6 池化层3 N×64×32 2×1×32 N×32×32 2 7 分离卷积2 N×32×32 7×1×32 N×32×32 1 零补 8 池化层4 N×32×32 2×1×32 N×16×32 2 9 分离卷积3 N×16×32 5×1×64 N×16×64 1 零补 10 池化层5 N×16×64 2×1×64 N×8×64 2 11 分离卷积4 N×8×64 3×1×64 N×8×64 1 零补 12 池化层6 N×8×64 2×1×64 N×4×64 2 13 GRU层 N×4×64 ×1 N×64 14 全连接层 N×64 ×1 024 N×1 024 15 输出层 N×1 024 ×10 N×10 表 3 回转窑运作工况说明与诊断分析
工
况回转窑物料投加情况 故障
分析高热值
废液中热值
废液低热值
废液固
废1 ○ × ○ × 正常 2 × ○ ○ ○ 外圈异常 3 ○ ○ × ○ 正常 4 ○ ○ × × 正常 注:○代表物料投加;×表示未启用投加。 -
[1] 徐卓飞, 张海燕, 王丹, 等.基于EMD与KPCA的滚动轴承故障特征提取及诊断方法研究[J].机械科学与技术, 2014, 33(10):1518-1524 doi: 10.13433/j.cnki.1003-8728.2014.1016Xu Z F, Zhang H Y, Wang D, et al. Study on feature extraction and diagnosis method of rolling bearing faults based on EMD and KPCA[J]. Mechanical Science and Technology for Aerospace Engineering, 2014, 33(10):1518-1524(in Chinese) doi: 10.13433/j.cnki.1003-8728.2014.1016 [2] 李永波.滚动轴承故障特征提取与早期诊断方法研究[D].哈尔滨: 哈尔滨工业大学, 2017 http://cdmd.cnki.com.cn/Article/CDMD-10213-1017862518.htmLi Y B. Investigation of fault feature extraction and early fault diagnosis for rolling bearings[D]. Harbin: Harbin Institute of Technology, 2017(in Chinese) http://cdmd.cnki.com.cn/Article/CDMD-10213-1017862518.htm [3] Ou L, Yu D J, Yang H J. A new rolling bearing fault diagnosis method based on GFT impulse component extraction[J]. Mechanical Systems and Signal Processing, 2016, 81:162-182 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=a4ac9c6f2344756adad5cf50bf1db109 [4] 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 http://d.old.wanfangdata.com.cn/Periodical/kzyjc201708001Ren 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) http://d.old.wanfangdata.com.cn/Periodical/kzyjc201708001 [5] Chen X Y, Zhou J Z, Xiao J, et al. Fault diagnosis based on dependent feature vector and probability neural network for rolling element bearings[J]. Applied Mathematics and Computation, 2014, 247:835-847 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=2570e0efb15a3ec7a32d03733cd327b2 [6] 王宏超, 陈进, 霍柏琦, 等.强抗噪时频分析方法及其在滚动轴承故障诊断中的应用[J].机械工程学报, 2015, 51(1):90-96 http://d.old.wanfangdata.com.cn/Periodical/jxgcxb201501012Wang H C, Chen J, Huo B Q, et al. Noise-resistant time-frequency analysis method and its application in fault diagnosis of rolling bearing[J]. Journal of Mechanical Engineering, 2015, 51(1):90-96(in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jxgcxb201501012 [7] Meng L J, Xiang J W, Wang Y X, et al. A hybrid fault diagnosis method using morphological filter-translation invariant wavelet and improved ensemble empirical mode decomposition[J]. Mechanical Systems and Signal Processing, 2015, 50-51:101-115 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=5855267047e81dcd55d46295e988aa5e [8] Purushotham V, Narayanan S, Prasad S A N. Multi-fault diagnosis of rolling bearing elements using wavelet analysis and hidden Markov model based fault recognition[J]. NDT & E International, 2005, 38(8):654-664 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=0eb4551a57c2e3e2b7f5f8a7ab42b626 [9] Unal M, Onat M, Demetgul M, et al. Fault diagnosis of rolling bearings using a genetic algorithm optimized neural network[J]. Measurement, 2014, 58:187-196 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=50d7a73138becaa487e7fafa88b8871d [10] 张伟.基于卷积神经网络的轴承故障诊断算法研究[D].哈尔滨: 哈尔滨工业大学, 2017 http://cdmd.cnki.com.cn/Article/CDMD-10213-1017864225.htmZhang W. Study on bearing fault diagnosis algorithm based on convolutional neural network[D]. Harbin: Harbin Institute of Technology, 2017(in Chinese) http://cdmd.cnki.com.cn/Article/CDMD-10213-1017864225.htm [11] Shao H D, Jiang H K, Zhang X, et al. Rolling bearing fault diagnosis using an optimization deep belief network[J]. Measurement Science and Technology, 2015, 26(11):28-37 http://d.old.wanfangdata.com.cn/Periodical/jxgcxb201807010 [12] 汤芳, 刘义伦, 龙慧.稀疏自编码深度神经网络及其在滚动轴承故障诊断中的应用[J].机械科学与技术, 2018, 37(3):352-357 doi: 10.13433/j.cnki.1003-8728.2018.0304Tang F, Liu Y L, Long H. Application of deep neural network with sparse auto-encoder in rolling bearing fault diagnosis[J]. Mechanical Science and Technology for Aerospace Engineering, 2018, 37(3):352-357(in Chinese) doi: 10.13433/j.cnki.1003-8728.2018.0304 [13] Ince T, Kiranyaz S, Eren L, et al. Real-time motor fault detection by 1-D convolutional neural networks[J]. IEEE Transactions on Industrial Electronics, 2016, 63(11):7067-7075 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=a8027015c0ef7dd4ead3dd28bb3ae1f7 [14] 赵光权, 刘小勇, 姜泽东, 等.基于深度学习的轴承健康因子无监督构建方法[J].仪器仪表学报, 2018, 39(6):82-88 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201806011Zhao G Q, Liu X Y, Jiang Z D, et al. Unsupervised health indicator of bearing based on deep learning[J]. Chinese Journal of Scientific Instrument, 2018, 39(6):82-88(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yqyb201806011 [15] Zhang X L, Wang B J, Chen X F. Intelligent fault diagnosis of roller bearings with multivariable ensemble-based incremental support vector machine[J]. Knowledge-Based Systems, 2015, 89:56-85 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dc311da09aad7ba70b8f190cbc971127 [16] Shen Z J, Chen X F, Zhang X L, et al. A novel intelligent gear fault diagnosis model based on EMD and multi-class TSVM[J]. Measurement, 2012, 45(1):30-40 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=766386a9394ba6cb8a7711e64f144db3 [17] Cerrada M, Zurita G, Cabrera D, et al. Fault diagnosis in spur gears based on genetic algorithm and random forest[J]. Mechanical Systems and Signal Processing, 2016, 70-71:87-103 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=6ecd0dd120a2d60814f0fadf569ae9e5 [18] Van der Maaten L, Hinton G. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9:2579-2605 http://connection.ebscohost.com/c/articles/36099312/visualizing-data-using-t-sne