基于1D⁃RSCNN的嵌入式轴承故障实时检测

doi:10.13229/j.cnki.jdxbgxb20211207

摘要/Abstract

摘要：

针对传统故障诊断模型参数多，训练、检测时间长，抗噪性差，不适用于在线实时诊断的问题，提出了基于残差连接和一维可分离卷积（1D-RSCNN）的滚动轴承故障诊断方法，构建了由Jetson Nano和信号采集电路组成的嵌入式系统。利用一维可分离卷积和全局平均池化对模型尺寸进行压缩，改善传统卷积的运算效率；通过宽卷积核，残差网络中引入Dropout提高对噪声的容忍度。试验结果表明，该方法诊断准确率高达99.92%，与其他模型相比，诊断精度高，实时性好，抗干扰能力强，适用于电机轴承故障的实时检测。

关键词: 电机故障, 嵌入式, 一维可分离卷积, 残差连接, Jetson Nano

Abstract:

Aiming at the problems of traditional fault diagnosis model with many parameters， long training， long detection time， poor noise resistance and not suitable for online real-time diagnosis， the paper puts forward the rolling bearing fault diagnosis method based on residual connection and one-dimensional separable convolution（1D-RSCNN）， and constructs an embedded system consisting of Jetson Nano and signal acquisition circuit. The model dimensions are compressed with 1D separable convolution and global average pooling to improve the computational efficiency of traditional convolution， and wide convolution cores， Dropout is introduced into the residual network to improve the tolerance of noise through. The test results show that the diagnostic accuracy of this method is as high as 99.92%. Compared with other models， the diagnosis accuracy is high， the real-time is good， the anti-jamming ability is strong， and it is suitable for the real-time detection of motor bearing fault.

Key words: motor faults, embedded systems, 1D separable convolution, residual connections, Jetson Nano

中图分类号:

TP277

王秀芳,孙双,丁春阳. 基于1D⁃RSCNN的嵌入式轴承故障实时检测[J]. 吉林大学学报(工学版), 2022, 52(2): 310-317.

Xiu-fang WANG,Shuang SUN,Chun-yang DING. Real⁃time detection of embedded bearing faults based on 1D⁃RSCNN[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(2): 310-317.

图/表 15

图1

图2

图3

图4

图5

图6

图7

图8

表1

图9

表2

图10

图11

表3

图12

参考文献 25

1	Lee C Y, Cheng Y H. Motor fault detection using wavelet transform and improved PSO-BP neural network[J]. Processes, 2020, 8(10): 1322.
2	Pandarakone S E, Mizuno Y, Nakamura H. Evaluating the progression and orientation of scratches on outer-raceway bearing using a pattern recognition method[J]. IEEE Transactions on Industrial Electronics, 2019, 66(2): 1307-1314.
3	Cao H, Fan F, Zhou K, et al. Wheel-bearing fault diagnosis of trains using empirical wavelet transform [J]. Measurement, 2016, 82: 439-449.
4	Nikolaou N G, Antoniadis I A. Rolling element bearing fault diagnosis using wavelet packets[J]. NDT & E International, 2009, 35(3): 197-205.
5	武哲, 杨绍普, 刘永强. 基于多元经验模态分解的旋转机械早期故障诊断方法[J]. 仪器仪表学报, 2016, 37(2): 241-248.
	Wu Zhe, Yang Shao-pu, Liu Yong-qiang. Early fault diagnosis method of rotating machinery based on multiple empirical mode decomposition[J]. Journal of Instrumentation, 2016, 37(2): 241-248.
6	Dragomiretskiy K, Zosso D. Variational mode decomposition [J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
7	姚德臣, 杨建伟, 程晓卿, 等. 基于多尺度本征模态排列熵和SA-SVM的轴承故障诊断研究[J]. 机械工程学报, 2018, 54(9): 168-176.
	Yao De-chen, Yang Jian-wei, Cheng Xiao-qing, et al. Railway rolling bearing fault diagnosis based on muti-scale IMF permutation entropy and SA-SVM classifier[J]. Journal of Mechanical Engineering, 2018, 54(9): 168-176.
8	Krishnakumari A, Elayaperumal A, Saravanan M. et al. Fault diagnostics of spur gear using decision tree and fuzzy classifier[J]. Int J Adv Manuf Technol,2017, 89: 3487-3494.
9	Chen S Z, Yang R, Zhong M Y. Graph-based semi-supervised random forest for rotating machinery gearbox fault diagnosis[J]. Control Engineering Practice, 2021, 117: 104952.
10	Yang Y, Yu D, Cheng J. A roller hearing fault diagnosis method baesd on EMD energy entropy and ANN[J]. Journal of Sound and Vibration, 2006, 294(1): 269-277
11	Li H W, Zhao X P, Wu J X, et al. Motor fault diagnosis based on short-time fourier transform and convolutional neural network[J]. Chinese Journal of Mechanical Engineering, 2017, 30(6): 1357-1368.
12	Li G Q, Deng C, Wu J, et al. Sensor data-driven bearing fault diagnosis based on deep convolutional neural networks and s-transform[J]. Sensors, 2019, 19(12): 2750-2764.
13	Ding X X, He Q B. Energy-fluctuated multiscale feature learning with deep convnet for intelligent spindle bearing fault diagnosis[J]. IEEE Transactions on InStrumentation and Measurement, 2017, 66(8): 1926-1935.
14	Xia M, Li T, Xu L, et al. Fault diagnosis for rotating machinery using multiple sensors and convolutional neural networks[J]. IEEE/ASME Transactions on Mechatronics, 2018, 23(1): 101-110.
15	吴晨芳, 杨世锡, 黄海舟, 等. 一种基于改进的LeNet-5模型滚动轴承故障诊断方法研究[J]. 振动与冲击, 2021, 40(12): 55-61.
	Wu Chen-fang, Yang Shi-xi, Huang Hai-zhou, et al. Research on a fault diagnosis method of rolling bearing based on improved lenet-5 model[J]. Vibration and Shock, 2021,40(12): 55-61.
16	曲建岭, 余路, 袁涛, 等. 基于一维卷积神经网络的滚动轴承自适应故障诊断算法[J]. 仪器仪表学报, 2018, 39(7): 134-143.
	Qu Jian-ling, Yu Lu, Yuan Tao, et al. Adaptive fault diagnosis algorithm of rolling bearing based on one-dimensional convolutional neural network[J]. Journal of Instrumentation, 2018, 39(7): 134-143.
17	宫文峰, 陈辉, 张美玲, 等. 基于深度学习的电机轴承微小故障智能诊断方法[J]. 仪器仪表学报, 2020, 41(1): 195-205.
	Gong Wen-feng, Chen Hui, Zhang Mei-ling, et al. Intelligent fault diagnosis method of motor bearing based on deep learning[J]. Journal of Instrumentation, 2020, 41(1): 195-205.
18	Li X Y, Li J L, Zhao C Y, et al. Gear pitting fault diagnosis with mixed operating conditions based on adaptive 1D separable convolution with residual connection[J]. Mechanical Systems and Signal Processing, 2020, 142: 106740.
19	邓飞跃, 吕浩洋, 顾晓辉, 等. 基于轻量化神经网络Shuffle-SENet的高速动车组轴箱轴承故障诊断方法[J]. 吉林大学学报: 工学版. DOI: 10.13229/j.cnki.jdxbgxb20210644. doi: 10.13229/j.cnki.jdxbgxb20210644
	Deng Fei-yue, Hao-yang Lyu, Gu Xiao-hui, et al. High-speed locomotive set axle box bearing troubleshooting method based on lightweight neural network Shuffle-SENet[J]. Journal of Jilin University(Engineering and Technology Edition). DOI: 10.13229/j.cnki.jdxbgxb20210644. doi: 10.13229/j.cnki.jdxbgxb20210644
20	Lu S, Qian G, He Q, et al. In situ motor fault diagnosis using enhanced convolutional neural network in an embedded system[J]. IEEE Sensors Journal, 2020, 20(15): 8287-8296.
21	He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 2016: 770-778.
22	赵敬娇, 赵志宏, 杨绍普. 基于残差连接和1D-CNN的滚动轴承故障诊断研究[J]. 振动与冲击, 2021, 40(10): 1-6.
	Zhao Jing-jiao, Zhao Zhi-hong, Yang Shao-pu. Research on fault diagnosis of rolling bearing based on residual connection and 1D-CNN[J]. Vibration and Shock, 2021, 40(10): 1-6.
23	董绍江, 裴雪武, 吴文亮, 等. 改进抗干扰CNN的变负载滚动轴承损伤程度识别[J]. 振动,测试与诊断, 2021, 41(4): 715-722, 831.
	Dong Shao-jiang, Pei Xue-wu, Wu Wen-liang, et al. Identification of damage degree of variable load rolling bearing based on improved anti-interference CNN[J]. Vibration, Test and Diagnosis, 2021, 41(4): 715-722, 831.
24	Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]∥International Conference on International Conference on Machine Learning, Miami, 2015: 448-456.
25	Lin M, Chen Q, Yan S C. Network in network[C]∥International Conference on Learning Representations, Vancouver, Canada, 2014: 1-10.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

故障类型	样本长度	训练样本	测试样本	标签
滚珠故障（RU）	1024	700	100	0
外圈故障（BORF）	1024	700	100	1
内圈故障（BIRF）	1024	700	100	2
正常（Healthy）	1024	700	100	3

层结构	数目×尺寸×步长	输出维度	参数量
输入层	-	1024×1	0
卷积层	16×32×8	128×16	528
残差块1	16×1×1	128×16	320
	32×3×1	128×32	592
	32×3×1	128×32	592
残差块2	32×1×1	128×32	1152
	64×3×1	128×64	2208
	64×3×1	128×64	2208
全局平均池化	-	64×1	0
Softmax层	4	4×1	260

算法	准确率/%	模型参数	训练时间/s	测试时间/s
1D-RSCNN	99.92	7 860	675	0.85
1D CNN	99.68	86 920	868	1.30
ResNets	99.81	41 990	782	1.06
文献［20］	100.00	206 148	916	2.54

[1]	郭继昌,吴洁,郭春乐,朱明辉. 基于残差连接卷积神经网络的图像超分辨率重构[J]. 吉林大学学报(工学版), 2019, 49(5): 1726-1734.
[2]	宋大凤, 李广含, 张琳, 潘冰, 曾小华, 彭宇君, 王庆年. 模糊逻辑在混合动力汽车电机故障检测中的应用[J]. 吉林大学学报(工学版), 2016, 46(2): 354-359.
[3]	马喜强,刘维亚,郑喜凤,程鹏. 非平稳多任务下的动态功耗管理随机策略[J]. 吉林大学学报(工学版), 2014, 44(3): 776-781.
[4]	陈大伟, 刘海龙, 李金屏. 复杂静态背景下多移动目标实时检测系统的FPGA实现[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 287-290.
[5]	金玉善, 郭凯, 杨书范, 黄永平. 嵌入式系统测量中的指数平滑滤波新算法[J]. 吉林大学学报(工学版), 2012, 42(增刊1): 314-316.
[6]	周宝余, 臧雪柏, 赵浩宇, 包环宇. 基于QT的无线多路视频监控系统[J]. 吉林大学学报(工学版), 2011, 41(增刊1): 204-207.
[7]	曲良东, 刘衍珩, 魏达. 基于VPN的车载网关异构无线网络切换系统[J]. 吉林大学学报(工学版), 2010, 40(05): 1292-1297.
[8]	李秀红，黄天戍，孙忠富，肖春华 . 基于GPRS/SMS的嵌入式环境监测系统[J]. 吉林大学学报(工学版), 2007, 37(06): 1409-1414.
[9]	张海涛，艾云峰 . 基于Petri网的分布式实时嵌入式系统的调度分析[J]. 吉林大学学报(工学版), 2007, 37(03): 616-0620.
[10]	刘久富,杨忠,孙德敏,李志宇. 基于模型的飞行控制软件测试用例的生成[J]. 吉林大学学报(工学版), 2006, 36(04): 543-547.
[11]	辛华峰，于枫，谭健，王文丽. 嵌入式USB主/从机应用模块[J]. 吉林大学学报(工学版), 2005, 35(02): 166-0169.
[12]	赵宏伟, 陈鹏, 刘大有, 王庆年. 混合动力汽车多能源动力总成嵌入式系统[J]. 吉林大学学报(工学版), 2003, (3): 35-37.