《计算机应用》唯一官方网站 ›› 2021, Vol. 41 ›› Issue (11): 3192-3199.DOI: 10.11772/j.issn.1001-9081.2021010046
周玉彬1, 肖红1, 王涛2, 姜文超1,3(), 熊梦3, 贺忠堂3
收稿日期:
2021-01-11
修回日期:
2021-05-14
接受日期:
2021-05-18
发布日期:
2021-11-29
出版日期:
2021-11-10
通讯作者:
姜文超
作者简介:
周玉彬(1997—),女,湖南常德人,硕士研究生,主要研究方向:工业设备的故障诊断与预测基金资助:
Yubin ZHOU1, Hong XIAO1, Tao WANG2, Wenchao JIANG1,3(), Meng XIONG3, Zhongtang HE3
Received:
2021-01-11
Revised:
2021-05-14
Accepted:
2021-05-18
Online:
2021-11-29
Published:
2021-11-10
Contact:
Wenchao JIANG
About author:
ZHOU Yubin, born in 1997, M. S. candidate. Her research
interests include fault diagnosis and prediction of industrial equipmentSupported by:
摘要:
针对工业机器人机械轴健康管理中检测效率和精准度较低的问题,提出了一种机械轴运行监控大数据背景下的基于动作周期退化相似性度量的健康指标(HI)构建方法,并结合长短时记忆(LSTM)网络进行机器人剩余寿命(RUL)的自动预测。首先,利用MPdist关注机械轴不同动作周期之间子周期序列相似性的特点,并计算正常周期数据与退化周期数据之间的偏离程度,进而构建HI;然后,利用HI集训练LSTM网络模型并建立HI与RUL之间的映射关系;最后,通过MPdist-LSTM混合模型自动计算RUL并适时预警。使用某公司六轴工业机器人进行实验,采集了加速老化数据约1 500万条,对HI单调性、鲁棒性和趋势性以及RUL预测的平均绝对误差(MAE)、均方根误差(RMSE)、决定系数(
中图分类号:
周玉彬, 肖红, 王涛, 姜文超, 熊梦, 贺忠堂. 基于动作周期退化相似性度量的机械轴健康指标构建与剩余寿命预测[J]. 计算机应用, 2021, 41(11): 3192-3199.
Yubin ZHOU, Hong XIAO, Tao WANG, Wenchao JIANG, Meng XIONG, Zhongtang HE. Health index construction and remaining useful life prediction of mechanical axis based on action cycle degradation similarity measurement[J]. Journal of Computer Applications, 2021, 41(11): 3192-3199.
方法 | 周期未对齐距离 |
---|---|
MPdist | 0 |
DTW | 10 709 |
ED | 43 559 |
表1 不同方法动作周期未对齐距离对比
Tab. 1 Misaligned distance comparison of action cycle of different methods
方法 | 周期未对齐距离 |
---|---|
MPdist | 0 |
DTW | 10 709 |
ED | 43 559 |
参数 | 符号 | 参数 | 符号 |
---|---|---|---|
指令位置 | pcmd | 反馈加速度 | afb |
反馈位置 | pfb | 指令速度 | vcmd |
指令力矩 | tcmd | 反馈速度 | vfb |
反馈力矩 | tfb | 位置误差 | pe |
指令加速度 | acmd |
表2 变量名说明
Tab. 2 Description of variable name
参数 | 符号 | 参数 | 符号 |
---|---|---|---|
指令位置 | pcmd | 反馈加速度 | afb |
反馈位置 | pfb | 指令速度 | vcmd |
指令力矩 | tcmd | 反馈速度 | vfb |
反馈力矩 | tfb | 位置误差 | pe |
指令加速度 | acmd |
单调性 | 鲁棒性 | 趋势性 | |
---|---|---|---|
2∶1 | 0.237 0 | 0.835 0 | 0.678 4 |
3∶1 | 0.468 2 | 0.961 5 | 0.864 7 |
4∶1 | 0.537 6 | 0.966 5 | 0.887 0 |
5∶1 | 0.560 7 | 0.968 4 | 0.906 5 |
6∶1 | 0.546 0 | 0.967 9 | 0.895 2 |
7∶1 | 0.560 7 | 0.967 9 | 0.906 5 |
8∶1 | 0.551 7 | 0.966 5 | 0.880 6 |
表3 不同比率的MP距离曲线评价结果对比
Tab. 3 Comparison of evaluation results of MP distance curves with different ratios
单调性 | 鲁棒性 | 趋势性 | |
---|---|---|---|
2∶1 | 0.237 0 | 0.835 0 | 0.678 4 |
3∶1 | 0.468 2 | 0.961 5 | 0.864 7 |
4∶1 | 0.537 6 | 0.966 5 | 0.887 0 |
5∶1 | 0.560 7 | 0.968 4 | 0.906 5 |
6∶1 | 0.546 0 | 0.967 9 | 0.895 2 |
7∶1 | 0.560 7 | 0.967 9 | 0.906 5 |
8∶1 | 0.551 7 | 0.966 5 | 0.880 6 |
方法 | 单调性 | 鲁棒性 | 趋势性 |
---|---|---|---|
MPdist | 0.560 7 | 0.968 4 | 0.906 5 |
DTW | 0.491 3 | 0.969 6 | 0.770 6 |
ED | 0.058 0 | 0.950 2 | 0.203 7 |
TDE | 0.132 9 | 0.952 4 | 0.310 6 |
表4 健康指标评价
Tab. 4 Health index evaluation
方法 | 单调性 | 鲁棒性 | 趋势性 |
---|---|---|---|
MPdist | 0.560 7 | 0.968 4 | 0.906 5 |
DTW | 0.491 3 | 0.969 6 | 0.770 6 |
ED | 0.058 0 | 0.950 2 | 0.203 7 |
TDE | 0.132 9 | 0.952 4 | 0.310 6 |
时间步 | MAE | RMSE | |
---|---|---|---|
3 | 0.036 6 | 0.065 2 | 0.957 5 |
6 | 0.028 9 | 0.056 9 | 0.966 9 |
10 | 0.036 6 | 0.070 5 | 0.947 2 |
20 | 0.032 4 | 0.076 3 | 0.928 5 |
表5 LSTM网络时间步调整评价
Tab. 5 Evaluation of LSTM network time step adjustment
时间步 | MAE | RMSE | |
---|---|---|---|
3 | 0.036 6 | 0.065 2 | 0.957 5 |
6 | 0.028 9 | 0.056 9 | 0.966 9 |
10 | 0.036 6 | 0.070 5 | 0.947 2 |
20 | 0.032 4 | 0.076 3 | 0.928 5 |
方法 | MAE | RMSE | ER | EP | LP | |
---|---|---|---|---|---|---|
MPdist-LSTM | 0.028 9 | 0.056 9 | 0.966 9 | [ | 19 | 13 |
MPdist-RNN | 0.030 5 | 0.067 1 | 0.943 7 | 15 | 18 | |
DTW-LSTM | 0.033 8 | 0.072 1 | 0.935 8 | 14 | 20 | |
TDE-LSTM | 0.104 7 | 0.134 6 | 0.781 8 | 16 | 18 | |
LSTM | 0.106 4 | 0.210 4 | 0.501 9 | 15 | 19 |
表6 剩余寿命预测评价
Tab. 6 Evaluation of remaining useful life prediction
方法 | MAE | RMSE | ER | EP | LP | |
---|---|---|---|---|---|---|
MPdist-LSTM | 0.028 9 | 0.056 9 | 0.966 9 | [ | 19 | 13 |
MPdist-RNN | 0.030 5 | 0.067 1 | 0.943 7 | 15 | 18 | |
DTW-LSTM | 0.033 8 | 0.072 1 | 0.935 8 | 14 | 20 | |
TDE-LSTM | 0.104 7 | 0.134 6 | 0.781 8 | 16 | 18 | |
LSTM | 0.106 4 | 0.210 4 | 0.501 9 | 15 | 19 |
1 | 王桃章,王宇,王宇斐,等.深度学习在机器人加工颤振辨识中的应用[J].机械科学与技术,2021,40(2):188-192. 10.1016/j.ast.2020.106435 |
WANG T Z, WANG Y, WANG Y F, et al. Application of deep learning in robot chatter identification [J]. Mechanical Science and Technology for Aerospace Engineering, 2021, 40(2): 188-192. 10.1016/j.ast.2020.106435 | |
2 | 周济.智能制造是“中国制造2025”主攻方向[J].企业观察家,2019(11):54-55. 10.3969/j.issn.1004-132X.2015.17.001 |
ZHOU J. Intelligent manufacturing is the main direction of “made in China 2025” [J]. Enterprise Observer, 2019(11): 54-55. 10.3969/j.issn.1004-132X.2015.17.001 | |
3 | 赵威,王锴,徐皑冬,等.面向智能制造的工业机器人健康评估方法[J].机器人,2020,42(4):460-468. 10.13973/j.cnki.robot.190438 |
ZHAO W, WANG K, XU A D, et al. An industrial robot health assessment method for intelligent manufacturing [J]. Robot, 2020, 42(4): 460-468. 10.13973/j.cnki.robot.190438 | |
4 | 彭宇,刘大同.数据驱动故障预测和健康管理综述[J].仪器仪表学报,2014,35(3):481-495. 10.3969/j.issn.0254-3087.2014.03.001 |
PENG Y, LIU D T. Data-driven prognostics and health management: a review of recent advances [J]. Chinese Journal of Scientific Instrument, 2014, 35(3): 481-495. 10.3969/j.issn.0254-3087.2014.03.001 | |
5 | KUMAR H S, PAI S P, SRIRAM N S, et al. Rolling element bearing fault diagnostics: development of health index [J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2017, 231(21): 3923-3939. 10.1177/0954406216656214 |
6 | 彭开香,皮彦婷,焦瑞华,等.航空发动机的健康指标构建与剩余寿命预测[J].控制理论与应用,2020,37(4):713-720. 10.7641/CTA.2019.90039 |
PENG K X, PI Y T, JIAO R H, et al. Health indicator construction and remaining useful life prediction for aircraft engine [J]. Control Theory and Applications, 2020, 37(4):713-720. 10.7641/CTA.2019.90039 | |
7 | GUO L, LEI Y G, LI N P, et al. Deep convolution feature learning for health indicator construction of bearings [C]// Proceedings of the 2017 Prognostics and System Health Management Conference. Piscataway: IEEE, 2017: 1-6. 10.1109/phm.2017.8079167 |
8 | GUO L, LEI Y G, LI N P, et al. Machinery health indicator construction based on convolutional neural networks considering trend burr [J]. Neurocomputing, 2018, 292: 142-150. 10.1016/j.neucom.2018.02.083 |
9 | CHEN L T, XU G H, ZHANG S C, et al. Health indicator construction of machinery based on end-to-end trainable convolution recurrent neural networks [J]. Journal of Manufacturing Systems, 2020, 54: 1-11. 10.1016/j.jmsy.2019.11.008 |
10 | MAO W T, LIU Y M, DING L, et al. A new structured domain adversarial neural network for transfer fault diagnosis of rolling bearings under different working conditions [J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: Article No.3509013. 10.1109/tim.2020.3038596 |
11 | 赵浩铭.基于信号分析的工业机器人故障诊断研究[D].沈阳:沈阳建筑大学,2014:1-27. 10.18057/ijasc.2015.11.1.4 |
ZHAO H M. The fault diagnostic studies of industrial robot based on signal analysis [D]. Shenyang: Shenyang Jianzhu University, 2014: 1-27. 10.18057/ijasc.2015.11.1.4 | |
12 | JABER A A, BICKER R. Development of a condition monitoring algorithm for industrial robots based on artificial intelligence and signal processing techniques [J]. International Journal of Electrical and Computer Engineering, 2018, 8(2): 996-1009. 10.11591/ijece.v8i2.pp996-1009 |
13 | FINK O, WANG Q, SVENSÉN M, et al. Potential, challenges and future directions for deep learning in prognostics and health management applications [J]. Engineering Applications of Artificial Intelligence, 2020, 92: Article No.103678. 10.1016/j.engappai.2020.103678 |
14 | CHEN Y H, WANG H L, ZHANG J, et al. Automated recognition of robotic manipulation failures in high-throughput biodosimetry tool [J]. Expert Systems with Applications, 2012, 39(10): 9602-9611. 10.1016/j.eswa.2012.02.145 |
15 | ALGBURI R N A, GAO H L. Health assessment and fault detection system for an industrial robot using the rotary encoder signal [J]. Energies, 2019, 12(14): Article No.2816. 10.3390/en12142816 |
16 | JABER A A, BICKER R. Fault diagnosis of industrial robot gears based on discrete wavelet transform and artificial neural network [J]. Insight: Non-Destructive Testing and Condition Monitoring, 2016, 58(4): 179-186. 10.1784/insi.2016.58.4.179 |
17 | GHARGHABI S, IMANI S, BAGNALL A, et al. Matrix Profile XII: MPdist: a novel time series distance measure to allow data mining in more challenging scenarios [C]// Proceedings of the 2018 IEEE International Conference on Data Mining. Piscataway: IEEE, 2018: 965-970. 10.1109/icdm.2018.00119 |
18 | YEH C C M, ZHU Y, ULANOVA L, et al. Matrix profile I: all pairs similarity joins for time series: a unifying view that includes motifs, discords and shapelets [C]// Proceedings of the 2016 IEEE 16th International Conference on Data Mining. Piscataway: IEEE, 2016: 1317-1322. 10.1109/icdm.2016.0179 |
19 | SENIN P. Dynamic time warping algorithm review [EB/OL]. [2020-12-22].. |
20 | JEONG Y S, JEONG M K, OMITAOMU O A. Weighted dynamic time warping for time series classification [J]. Pattern Recognition, 2011, 44(9): 2231-2240. 10.1016/j.patcog.2010.09.022 |
21 | ZHANG B, ZHANG L J, XU J W. Degradation feature selection for remaining useful life prediction of rolling element bearings [J]. Quality and Reliability Engineering International, 2016, 32(2): 547-554. 10.1002/qre.1771 |
22 | GERS F A, SCHMIDHUBER J, CUMMINS F. Learning to forget: Continual prediction with LSTM [J]. Neural Computation, 2000, 12(10): 2451-2471. 10.1162/089976600300015015 |
23 | ELSHEIKH A, YACOUT S, OUALI M S. Bidirectional handshaking LSTM for remaining useful life prediction [J]. Neurocomputing, 2019, 323: 148-156. 10.1016/j.neucom.2018.09.076 |
24 | ZHANG C, LIM P, QIN A K, et al. Multiobjective deep belief networks ensemble for remaining useful life estimation in prognostics [J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 28(10): 2306-2318. 10.1109/tnnls.2016.2582798 |
25 | LI X, DING Q, SUN J Q. Remaining useful life estimation in prognostics using deep convolution neural networks [J]. Reliability Engineering and System Safety, 2018, 172: 1-11. 10.1016/j.ress.2017.11.021 |
26 | ZHANG J J, WANG P, YAN R Q, et al. Long short-term memory for machine remaining life prediction [J]. Journal of Manufacturing Systems, 2018, 48(Pt C): 78-86. 10.1016/j.jmsy.2018.05.011 |
[1] | 张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614. |
[2] | 丁尹, 桑楠, 李晓瑜, 吴飞舟. 基于循环神经网络的电信行业容量数据预测方法[J]. 计算机应用, 2021, 41(8): 2373-2378. |
[3] | 赵小虎, 李晓. 基于多特征提取的图像语义描述算法[J]. 计算机应用, 2021, 41(6): 1640-1646. |
[4] | 杨蒙蒙, 张爱华. 基于灰度共生矩阵和同步正交匹配追踪的分形图像压缩[J]. 计算机应用, 2021, 41(5): 1445-1449. |
[5] | 胡立华, 左威健, 聂瑶瑶. 基于加权相似性度量的特征匹配方法[J]. 计算机应用, 2021, 41(2): 511-516. |
[6] | 邱宁佳, 王晓霞, 王鹏, 王艳春. 融合语法规则的双通道中文情感模型分析[J]. 计算机应用, 2021, 41(2): 318-323. |
[7] | 董永峰, 刘超, 王利琴, 李英双. 融合多跳关系路径信息的关系推理方法[J]. 计算机应用, 2021, 41(10): 2799-2805. |
[8] | 马停停, 冀天娇, 杨冠羽, 陈阳, 许文波, 刘宏图. 基于长短时记忆神经网络的手足口病发病趋势预测[J]. 计算机应用, 2021, 41(1): 265-269. |
[9] | 戎炜, 蒋哲远, 谢昭, 吴克伟. 基于聚类关联网络的群组行为识别[J]. 计算机应用, 2020, 40(9): 2507-2513. |
[10] | 傅洪亮, 雷沛之. 基于去噪自编码器和长短时记忆网络的语音测谎算法[J]. 计算机应用, 2020, 40(2): 589-594. |
[11] | 朱霖, 宁芊, 雷印杰, 陈炳才. 基于遗传算法选优的集成手段与时序卷积网络的涡扇发动机剩余寿命预测[J]. 计算机应用, 2020, 40(12): 3534-3540. |
[12] | 马伟苹, 李文新, 孙晋川, 曹鹏霞. 基于粗精立体匹配的双目视觉目标定位方法[J]. 计算机应用, 2020, 40(1): 227-232. |
[13] | 章永来, 周耀鉴. 聚类算法综述[J]. 计算机应用, 2019, 39(7): 1869-1882. |
[14] | 闻畅, 刘宇, 顾进广. 基于注意力机制的双向长短时记忆网络模型突发事件演化关系抽取[J]. 计算机应用, 2019, 39(6): 1646-1651. |
[15] | 姜逸凡, 叶青. 基于孪生神经网络的时间序列相似性度量[J]. 计算机应用, 2019, 39(4): 1041-1045. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||