Health index construction and remaining useful life prediction of mechanical axis based on action cycle degradation similarity measurement

doi:10.11772/j.issn.1001-9081.2021010046

Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (11): 3192-3199.DOI: 10.11772/j.issn.1001-9081.2021010046

Special Issue: 人工智能

• Artificial intelligence • Previous Articles Next Articles

Health index construction and remaining useful life prediction of mechanical axis based on action cycle degradation similarity measurement

Yubin ZHOU¹, Hong XIAO¹, Tao WANG², Wenchao JIANG¹^,³(), Meng XIONG³, Zhongtang HE³

^1.School of Computer Science，Guangdong University of technology，Guangzhou Guangdong 510006，China
^2.School of Automation，Guangdong University of technology，Guangzhou Guangdong 510006，China
^3.Cloud Computing Center，Chinese Academy of Sciences，Dongguan Guangdong 523808，China

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 equipment
XIAO Hong，born in 1972，Ph. D.，associate professor. Her research interests include intelligent manufacturing and industrial big data，robot and artificial intelligence
WANG Tao，born in 1983，Ph. D.，associate professor. His research interests include internet of things，big data
JIANG Wenchao，born in 1977，Ph. D.，associate professor. His research interests include cloud computing，big data，complex network， graph data processing
XIONG Meng， born in 1985， senior engineer. His research interests include cloud computing，big data，industrial internet
HE Zhongtang， born in 1971， Ph. D.， senior engineer. His research interests include cloud computing，big data，government
Supported by:
the National Key Research and Development Program of China(2018YFB1004202);the National Natural Science Foundation of China-People’s Government of Guangdong Province Joint Fund(U2001201);the Surface Program of Natural Science Foundation of Guangdong Province(2020A1515010890);the Science and Technology Program of Guangdong Province(2019B010139001);the Science and Technology Program of Guangzhou(201902020016);the Key Technology Project of Foshan in 2019(1920001001367)

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

周玉彬¹, 肖红¹, 王涛², 姜文超¹^,³(), 熊梦³, 贺忠堂³

^1.广东工业大学计算机学院，广州 510006
^2.广东工业大学自动化学院，广州 510006
^3.中国科学院云计算产业技术创新与育成中心，广东东莞 523808

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
肖红（1972—），女，湖北咸宁人，副教授，博士，主要研究方向：智能制造与工业大数据、机器人与人工智能
王涛（1983—），男，湖北荆州人，副教授，博士，主要研究方向：物联网、大数据
姜文超（1977—），男，山东潍坊人，副教授，博士，CCF会员，主要研究方向：云计算、大数据、复杂网络、图数据处理
熊梦（1985—），男，湖北咸宁人，高级工程师，主要研究方向：云计算、大数据、工业互联网
贺忠堂（1971—），男，江苏徐州人，高级工程师，博士，主要研究方向：云计算、大数据、政府云服务平台、城市公共安全云管理。
基金资助:
国家重点研发计划项目(2018YFB1004202);国家自然科学基金委员会-广东省人民政府联合基金资助项目(U2001201);广东省自然科学基金面上项目(2020A1515010890);广东省科技计划项目(2019B010139001);广州市科技计划项目(201902020016);2019年佛山市核心技术攻关项目(1920001001367)

Abstract

Abstract:

Aiming at the problems of low detection efficiency and accuracy in the health management process of industrial robot axis， a new Health Index （HI） construction method based on action cycle degradation similarity measurement under the background of mechanical axis operation monitoring big data was proposed， and the robot Remaining Useful Life （RUL） prediction was carried out by combining Long Short-Term Memory （LSTM） network. Firstly， MPdist was used to focus on the similarity features of sub-cycle sequences between different action cycles of mechanical axis， and the deviation distance between normal cycle data and degradation cycle data was calculated， so that the HI was constructed. Then， the LSTM network model was trained by HI set， and the mapping relationship between HI and RUL was established. Finally， the MPdist-LSTM hybrid model was used to automatically calculate the RUL and give early warning in time. The six-axis industrial robot of a company was used to carry the experiments， and about 15 million pieces of data were collected. The monotonicity， robustness and trend of HI and Mean Absolute Error （MAE）， Root Mean Square Error （RMSE）， R-Square （ $R 2$ ）， Error Range （ER）， Early Prediction （EP） and Late Prediction （LP） of RUL were tested. The proposed method were compared with the methods such as Dynamic Time Warping （DTW）， Euclidean Distance （ED）， Time Domain Eigenvalue （TDE） combined with LSTM， MPdist combined with RNN and LSTM. The experimental results show that， compared with other comparison methods， the proposed method has the HI monotonicity and trend higher by at least 0.07 and 0.13 respectively， the higher RUL prediction accuracy， and the smaller ER， which verifies the effectiveness of the proposed method.

Key words: MPdist, Long Short-Term Memory (LSTM) network, similarity measurement, Health Index (HI) construction, Remaining Useful Life (RUL) prediction

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（ $R 2$ ）、误差区间（ER）、早预测（EP）和晚预测（LP）等指标进行了实验测试，将该方法分别与动态时间规整（DTW）、欧氏距离（ED）、时域特征值（TDE）结合LSTM的方法，MPdist结合循环神经网络（RNN）和LSTM等方法进行比较。实验结果表明，相较于其他对比方法，所提方法所构建HI的单调性和趋势性分别至少提高了0.07和0.13，RUL预测准确率更高，ER更小，验证了所提方法的有效性。

关键词: MPdist, 长短时记忆网络, 相似性度量, 健康指标构建, 剩余寿命预测

CLC Number:

TP206.3

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.

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》唯一官方网站, 2021, 41(11): 3192-3199.

Figures/Tables 18

Fig. 1 Schematic diagram of misaligned action cycle

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

Fig. 2 Schematic diagram of similarity comparison

Fig. 3 Framework of remaining useful life prediction based on MPdist-LSTM

Fig. 4 Flow chart of health index construction and remaining useful life prediction

Fig. 5 Schematic diagram of early prediction and late prediction

Fig. 6 Six-axis industrial robot of a company

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

Tab. 3 Comparison of evaluation results of MP distance curves with different ratios

$T 1$ 和 $T 2$ 与 $L$ 比率	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

Tab. 3 Comparison of evaluation results of MP distance curves with different ratios

$T 1$ 和 $T 2$ 与 $L$ 比率	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

Fig. 7 Schematic diagram of MPdist similarity measurement of feedback torque

Fig. 8 Smoothed multivariable MP distance curve

Fig. 9 HI curves of four-axis feedback torque for three robots

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

Fig. 10 Schematic diagram of remaining useful life marking

Fig. 11 Structure of input and output of neural network

Tab. 5 Evaluation of LSTM network time step adjustment

时间步	MAE	RMSE	$R 2$
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

Tab. 5 Evaluation of LSTM network time step adjustment

时间步	MAE	RMSE	$R 2$
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

Tab. 6 Evaluation of remaining useful life prediction

方法	MAE	RMSE	$R 2$	ER	EP	LP
MPdist-LSTM	0.028 9	0.056 9	0.966 9	［8，12］	19	13
MPdist-RNN	0.030 5	0.067 1	0.943 7	$[- 16,15]$	15	18
DTW-LSTM	0.033 8	0.072 1	0.935 8	$[- 48,20]$	14	20
TDE-LSTM	0.104 7	0.134 6	0.781 8	$[- 32,48]$	16	18
LSTM	0.106 4	0.210 4	0.501 9	$[- 60,60]$	15	19

Tab. 6 Evaluation of remaining useful life prediction

方法	MAE	RMSE	$R 2$	ER	EP	LP
MPdist-LSTM	0.028 9	0.056 9	0.966 9	［8，12］	19	13
MPdist-RNN	0.030 5	0.067 1	0.943 7	$[- 16,15]$	15	18
DTW-LSTM	0.033 8	0.072 1	0.935 8	$[- 48,20]$	14	20
TDE-LSTM	0.104 7	0.134 6	0.781 8	$[- 32,48]$	16	18
LSTM	0.106 4	0.210 4	0.501 9	$[- 60,60]$	15	19

Fig. 12 Prediction results of MPdist-LSTM

References 26

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]	Xiaoyu HUA, Dongfen LI, You FU, Kejun BI, Shi YING, Ruijin WANG. Industrial chain risk assessment and early warning model combining hierarchical graph neural network and long short-term memory [J]. Journal of Computer Applications, 2024, 44(10): 3223-3231.
[2]	Hanxiao SHI, Leichun WANG. Short-term power load forecasting by graph convolutional network combining LSTM and self-attention mechanism [J]. Journal of Computer Applications, 2024, 44(1): 311-317.
[3]	Kai XU, Qikai GAO, Ming YIN, Jingjing TAN. Trajectory similarity measurement algorithm based on three-dimensional space area division [J]. Journal of Computer Applications, 2024, 44(1): 318-323.
[4]	Zhiping ZHU, Yan YANG, Jie WANG. Scene graph-aware cross-modal image captioning model [J]. Journal of Computer Applications, 2024, 44(1): 58-64.
[5]	Li’an CHEN, Yi GUO. Text sentiment analysis model based on individual bias information [J]. Journal of Computer Applications, 2024, 44(1): 145-151.
[6]	Jiagao WU, Shiwen ZHANG, Yudong JIANG, Linfeng LIU. Social-interaction GAN for pedestrian trajectory prediction based on state-refinement long short-term memory and attention mechanism [J]. Journal of Computer Applications, 2023, 43(5): 1565-1570.
[7]	Haiyu YANG, Wenpu GUO, Kai KANG. Signal modulation recognition method based on convolutional long short-term deep neural network [J]. Journal of Computer Applications, 2023, 43(4): 1318-1322.
[8]	Chunyong YIN, Liwen ZHOU. Unsupervised time series anomaly detection model based on re-encoding [J]. Journal of Computer Applications, 2023, 43(3): 804-811.
[9]	Bennian YU, Yongzhao ZHAN, Qirong MAO, Wenlong DONG, Honglin LIU. Double complex convolution and attention aggregating recurrent network for speech enhancement [J]. Journal of Computer Applications, 2023, 43(10): 3217-3224.
[10]	LIU Hui, MA Xiang, ZHANG Linyu, HE Rujin. Aspect-based sentiment analysis model integrating match-LSTM network and grammatical distance [J]. Journal of Computer Applications, 2023, 43(1): 45-50.
[11]	ZHANG Jun, WU Pengli, SHI Lukui, SHI Jin, PAN Bin. Deep learning model for multi-station temperature prediction combined with MOD11A1 and surface meteorological station data [J]. Journal of Computer Applications, 2023, 43(1): 321-328.
[12]	Yinglü XUAN, Yuan WAN, Jiahui CHEN. Time series classification by LSTM based on multi-scale convolution and attention mechanism [J]. Journal of Computer Applications, 2022, 42(8): 2343-2352.
[13]	Yifei WANG, Lei YU, Fei TENG, Jiayu SONG, Yue YUAN. Resource load prediction model based on long-short time series feature fusion [J]. Journal of Computer Applications, 2022, 42(5): 1508-1515.
[14]	An YANG, Qun JIANG, Gang SUN, Jie YIN, Ying LIU. Power data analysis based on financial technical indicators [J]. Journal of Computer Applications, 2022, 42(3): 904-910.
[15]	Chong CHEN, Zhu YAN, Jixuan ZHAO, Wei HE, Huaqing LIANG. Prediction of NOx emission from fluid catalytic cracking unit based on ensemble empirical mode decomposition and long short-term memory network [J]. Journal of Computer Applications, 2022, 42(3): 791-796.

Health index construction and remaining useful life prediction of mechanical axis based on action cycle degradation similarity measurement

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

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 18

References 26

Related Articles 15

Recommended Articles

Metrics