融合图标签传播和判别特征增强的工业机器人关键部件半监督故障诊断方法

doi:10.3901/JME.2022.17.116

机械工程学报 ›› 2022, Vol. 58 ›› Issue (17): 116-124.doi: 10.3901/JME.2022.17.116

扫码分享

融合图标签传播和判别特征增强的工业机器人关键部件半监督故障诊断方法

韩特¹, 李彦夫¹, 雷亚国², 李乃鹏², 李响²

1. 清华大学工业工程系北京 100084;
2. 西安交通大学现代设计及转子轴承系统教育部重点实验室西安 710049

收稿日期:2021-12-07 修回日期:2022-05-12 发布日期:2022-11-07
作者简介:韩特,男,1993年出生,博士,助理研究员。主要研究方向为工业装备智能故障诊断与健康管理、工业大数据分析。E-mail:hant@mail.tsinghua.edu.cn;雷亚国,男,1979 年出生,博士,教授,博士研究生导师。主要研究方向为大数据智能故障诊断与寿命预测、机械系统建模与动态信号处理、机械设备健康监测与智能维护。E-mail:yaguolei@mail.xjtu.edu.cn

Semi-supervised Fault Diagnosis Method via Graph Label Propagation and Discriminative Feature Enhancement for Critical Components of Industrial Robot

HAN Te¹, LI Yanfu¹, LEI Yaguo², LI Naipeng², LI Xiang²

1. Department of Industrial Engineering, Tsinghua University, Beijing 100084;
2. Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi'an Jiaotong University, Xi'an 710049

Received:2021-12-07 Revised:2022-05-12 Published:2022-11-07
Contact: 国家重点研发计划项目(2018YFB1306100)。

摘要/Abstract

摘要： RV减速器作为工业机器人关键部件之一，其机械故障将造成整机定位精度下降。围绕RV减速器开展健康状态监测与智能故障诊断具有重要意义。基于故障标记数据充足的假设，数据驱动的智能诊断方法可以有效建立监测信号与健康状态的非线性映射关系。然而，在工程实际中收集大量故障标记样本需要昂贵的标记代价和人力成本。针对上述问题，提出了一种融合图标签传播和判别特征增强的RV减速器半监督故障诊断方法。首先，利用标签传播算法赋予无标记样本伪标签。然后，通过信息熵定量评估伪标签置信度，降低误标记对模型半监督学习的干扰。同时，在深度特征嵌入空间下优化少量标记样本度量损失，构造更具判别力的特征图，提升伪标签质量。最后，采用实际工业机器人RV减速器故障数据进行方法验证。结果表明，所提半监督故障诊断方法可以对无标记样本精准地传播标签，仅利用少量标记样本获取更优的故障识别精度。

关键词: RV减速器, 工业机器人, 半监督故障诊断

Abstract: RV reducer is the critical component of industrial robot. Its mechanical faults will reduce the machine performance. The monitoring and intelligent fault diagnosis is of great significance. Traditional fault diagnosis methods assume that sufficient labeled data are available, while labeling the fault data is labor-consuming in practice. To solve this problem, a novel semi-supervised fault diagnosis method via graph label propagation and discriminative feature enhancement is proposed for RV reducer. First, the pseudo labels are produced by label propagation algorithm for unlabeled data. By using entropy, the pseudo labels are associated with a weight reflecting its certainty, so as to reduce the effect of pseudo label noise. Then, by optimizing the metric learning loss in deep embedding space for few labeled samples, the discriminative ability of feature graph is enhanced. The effectiveness of proposed method is demonstrated in the fault dataset of actual industrial robot RV reducer. The results show that the proposed semi-supervised method can produce accuracy pseudo labels, and achieve superior fault identification rate with few labeled samples.

Key words: RV reducer, industrial robot, semi-supervised fault diagnosis

中图分类号:

TH17

韩特, 李彦夫, 雷亚国, 李乃鹏, 李响. 融合图标签传播和判别特征增强的工业机器人关键部件半监督故障诊断方法[J]. 机械工程学报, 2022, 58(17): 116-124.

HAN Te, LI Yanfu, LEI Yaguo, LI Naipeng, LI Xiang. Semi-supervised Fault Diagnosis Method via Graph Label Propagation and Discriminative Feature Enhancement for Critical Components of Industrial Robot[J]. Journal of Mechanical Engineering, 2022, 58(17): 116-124.

参考文献

[1] XU W，HAN L，WANG X，et al. Intelligent modularized reconfigurable mechanisms for robots：Development and experiment[J]. Chinese Journal of Mechanical Engineering，2020，33：74.
[2] 彭鹏，柯梁亮，汪久根. 噪声干扰下的RV减速器故障诊断[J]. 机械工程学报，2020，56(1)：30-36. PENG Peng，KE Liangliang，WANG Jiugen. Fault diagnosis of RV reducer with noise interference[J]. Journal of Mechanical Engineering，2020，56(1)：30-36.
[3] 雷亚国，贾峰，孔德同，等. 大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报，2018，54(5)：94-104. LEI Yaguo，JIA Feng，KONG Detong，et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J]. Journal of Mechanical Engineering，2018，54(5)：94-104.
[4] 周兴康，余建波. 基于深度一维残差卷积自编码网络的齿轮箱故障诊断[J]. 机械工程学报，2020，56(7)：96-108. ZHOU Xingkang，YU Jianbo. Gearbox fault diagnosis based on one-dimension residual convolutional auto-encoder[J]. Journal of Mechanical Engineering，2020，56(7)：96-108.
[5] LEI Y，YANG B，JIANG X，et al. Applications of machine learning to machine fault diagnosis：A review and roadmap[J]. Mechanical Systems and Signal Processing，2020，138：106587.
[6] XU K，LI Y，LIU C，et al. Advanced data collection and analysis in data-driven manufacturing process[J]. Chinese Journal of Mechanical Engineering，2020，33：43.
[7] CHAPELLE O，SCHOLKOPF B，ZIEN A. Semi-supervised learning [M].Cambridge: MIT Press,2006.
[8] 周志华. 基于分歧的半监督学习[J]. 自动化学报， 2013，39(11)：1871-1878. ZHOU Zhihua. Disagreement-based semi-supervised learning[J]. Acta Automarica Sinica，2013，39(11)：1871-1878.
[9] YAROWSKY D. Unsupervised word sense disambiguation rivaling supervised methods[C]// The 33rd Annual Meeting on Association for Computational Linguistics in Stroudsburg，PA，USA，1995：189-196.
[10] MIYATO T，MAEDA S，KOYAMA M，et al. Virtual adversarial training：A regularization method for supervised and semi-supervised learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence，2018，41(8)：1979-1993.
[11] ZHANG Z，ZHAO M，CHOW T W S. Graph based constrained semi-supervised learning framework via label propagation over adaptive neighborhood[J]. IEEE Transactions on Knowledge and Data Engineering，2013，27(9)：2362-2376.
[12] ISCEN A，TOLIAS G，AVRITHIS Y，et al. Label propagation for deep semi-supervised learning[C]// The IEEE/CVF Conference on Computer Vision and Pattern Recognition in Long Beach，California，June 16-20，2019：5070-5079.
[13] WU X，ZHANG Y，CHENG C，et al. A hybrid classification autoencoder for semi-supervised fault diagnosis in rotating machinery[J]. Mechanical Systems and Signal Processing，2021，149：107327.
[14] YU K，LIN T R，MA H，et al. A multi-stage semi-supervised learning approach for intelligent fault diagnosis of rolling bearing using data augmentation and metric learning[J]. Mechanical Systems and Signal Processing，2021，146：107043.
[15] LIAO Y，HUANG R，LI J，et al. Deep semisupervised domain generalization network for rotary machinery fault diagnosis under variable speed[J]. IEEE Transactions on Instrumentation and Measurement，2020，69(10)：8064-8075.
[16] 吕枫，王义，阮胡林，等. 深度嵌入关系空间下齿轮箱标记样本扩充及其半监督故障诊断方法[J]. 仪器仪表学报，2021，42(2)：55-65. LÜ Feng，WANG Yi，RUAN Hulin，et al. Labeled sample augmentation based on deep embedding relation space for semi-supervised fault diagnosis of gearbox[J]. Chinese Journal of Scientific Instrument，2021，42(2)：55-65.
[17] ZHU X，GHAHRAMANI Z. Learning from labeled and unlabeled data with label propagation[R]. Technical Report CMU-CALD-02–107，Carnegie Mellon University，2002.
[18] ZHOU D，BOUSQUET O，LAL T N，et al. Learning with local and global consistency[C]// Advances in neural information processing systems in British Columbia，Canada，2004：321-328.
[19] SCHROFF F，KALENICHENKO D，PHILBIN J. FaceNet：A unified embedding for face recognition and clustering[C]// The IEEE Conference on Computer Vision and Pattern Recognition in Boston，MA，USA，June 7-12，2015：815-823.
[20] YANG B，LEI Y，JIA F，et al. A polynomial kernel induced distance metric to improve deep transfer learning for fault diagnosis of machines[J]. IEEE Transactions on Industrial Electronics，2020，67(11)：9747-9757.

融合图标签传播和判别特征增强的工业机器人关键部件半监督故障诊断方法

Semi-supervised Fault Diagnosis Method via Graph Label Propagation and Discriminative Feature Enhancement for Critical Components of Industrial Robot

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	许立新. 考虑位置度误差的RV减速器多组滚针轴承动态载荷特性研究[J]. 机械工程学报, 2022, 58(17): 144-155.
[2]	王文玺, 黄云, 刘占芳, 邹莱, 吕冲. 大曲率表面机器人高速磨削中的陀螺力矩分析[J]. 机械工程学报, 2022, 58(15): 208-215.
[3]	张泽坤, 国凯, 孙杰. 基于扰动观测器的工业机器人高精度闭环鲁棒控制[J]. 机械工程学报, 2022, 58(14): 62-70.
[4]	汤勇, 王志威, 陈恭, 张仕伟, 袁伟. 摆线齿轮低成本冷精整加工关键工艺研究[J]. 机械工程学报, 2022, 58(14): 154-160.
[5]	卢远, 国凯, 孙杰. 工业机器人轨迹精度力-位置复合补偿方法[J]. 机械工程学报, 2022, 58(14): 181-189.
[6]	黄健, 李朝阳, 陈兵奎. RV减速器用新型交错滚子主轴承承载能力分析与试验研究[J]. 机械工程学报, 2021, 57(7): 68-77.
[7]	高贯斌, 张石文, 那靖, 刘飞. 基于标定和关节空间插值的工业机器人轨迹误差补偿[J]. 机械工程学报, 2021, 57(21): 55-67.
[8]	刘冬, 袁利恒, 丛明. 齿轮机器人复杂装配过程在线建模与参数优化[J]. 机械工程学报, 2021, 57(13): 124-131.
[9]	彭鹏, 柯梁亮, 汪久根. 噪声干扰下的RV减速器故障诊断[J]. 机械工程学报, 2020, 56(1): 30-36.
[10]	汪久根, 柯梁亮. 基于残差网络的RV减速器故障诊断[J]. 机械工程学报, 2019, 55(3): 73-80.
[11]	王志江, 薛坤喜, 吴定勇, 杨辉, 申俊琦, 刘杰, 胡绳荪. 基于视觉传感的机器人焊缝纠偏控制系统[J]. 机械工程学报, 2019, 55(17): 48-55.
[12]	周星, 黄石峰, 朱志红. 六关节工业机器人TCP标定模型研究与算法改进[J]. 机械工程学报, 2019, 55(11): 186-196.
[13]	胡瑞钦, 张立建, 孟少华, 董悫, 隆昌宇. 基于柔顺控制的航天器大部件机器人装配技术[J]. 机械工程学报, 2018, 54(11): 85-93.
[14]	史晓佳, 张福民, 曲兴华, 刘柏灵, 王俊龙. KUKA工业机器人位姿测量与在线误差补偿[J]. 机械工程学报, 2017, 53(8): 1-7.
[15]	王田苗;陶永. 我国工业机器人技术现状与产业化发展战略[J]. , 2014, 50(9): 1-13.