Hostname: page-component-586b7cd67f-l7hp2 Total loading time: 0 Render date: 2024-11-27T14:41:10.897Z Has data issue: false hasContentIssue false
  • English
  • Français

Fault diagnosis of robot joint based on BP neural network

Published online by Cambridge University Press:  22 July 2022

Ming Hu ,
Jianguo Wu Open the ORCID record for Jianguo Wu [Opens in a new window] ,
Jing Yang Open the ORCID record for Jing Yang [Opens in a new window] ,
Lijian Zhang  and
Fan Yang
Ming Hu
Affiliation:
Faculty of Mechanical Engineering and Automation, Zhejiang Sci-Tech University, Hangzhou, China
Jianguo Wu
Affiliation:
Faculty of Mechanical Engineering and Automation, Zhejiang Sci-Tech University, Hangzhou, China
Jing Yang*
Affiliation:
Faculty of Mechanical Engineering and Automation, Zhejiang Sci-Tech University, Hangzhou, China
Lijian Zhang
Affiliation:
Beijing Institute of Spacecraft Environmental Engineering, Beijing, China
Fan Yang
Affiliation:
Faculty of Mechanical Engineering and Automation, Zhejiang Sci-Tech University, Hangzhou, China
*
*Corresponding author. E-mail: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

Aiming at the problem of low accuracy of robot joint fault diagnosis, a fault diagnosis method of robot joint based on BP neural network is designed. In this paper, the UR10 robot is taken as the research object, and the end pose data of the robot are collected in real time. By injecting different joint errors and changing the sampling frequency, the joint fault database is collected and established, and the BP neural network is used for training to obtain the robot neural network fault diagnosis model. The fault diagnosis model can output the joint fault of the input end pose data. And we analyzed the influence of different joint angle errors and different training sets on the accuracy of joint fault diagnosis of the robot. The results show that when the sampling frequency is 250 Hz, the simulation result of joint fault diagnosis accuracy with the fault degree of 0.5° is 99.17%, and the experimental result is 97.87%. Compared with traditional data-driven methods, it has higher accuracy and diagnostic efficiency, and compared with existing machine learning methods, it also achieves a high accuracy while reducing the network complexity. The effectiveness of the BP neural network robot joint fault diagnosis method is verified by experiments.

Keywords

robotBP Neural networkjoint fault diagnosisend poseangle error
Type
Research Article
Information
Robotica , Volume 40 , Issue 12 , December 2022 , pp. 4388 - 4404
Copyright
© The Author(s), 2022. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Tian, C., Jia, P., Yuan, J. and Teng, B., “Application of integrated manufacturing system of flexible production line in spacecraft manufacturing line,” J. Phys. Conf. Ser. 1549(3), 032103 (2020). doi: 10.1088/1742-6596/1549/3/032103.CrossRefGoogle Scholar
Khalastchi, E. and Kalech, M., “Fault detection and diagnosis in multi-robot systems: A survey,” Sensors 19(18), 4019 (2019). doi: 10.3390/s19184019.Google ScholarPubMed
Xia, Y., Wang, W., Song, Z., Xie, Z. and Li, H., “Fault diagnosis of flexible production line machining center based on PCA and ABC-LVQ,” Proc. Inst. Mech. Eng. B J. Eng. Manuf. 235(8), 095440542097051 (2020).Google Scholar
Leng, S., “Scheduling method of green flexible production line for enterprise products based on task priority,” Int. J. Prod. Dev. 2(3), 130 (2020). doi: 10.1504/IJPD.2020.110266.CrossRefGoogle Scholar
Barosz, P., Gołda, G. and Kampa, A., “Efficiency analysis of manufacturing line with industrial robots and human operators,” Appl. Sci. 10(8), 2862 (2020). doi: 10.3390/app10082862.Google Scholar
Wu, J. and Tao, Y., “Overview of the research status of positioning accuracy and reliability of industrial robots,” China Mech. Eng. 31(18), 2180–2188 (2020).Google Scholar
Gao, H., “Development status and trend of industrial robot in China,” Appl. Sci. Innov. Res. 5(2), 49–54 (2021). doi: 10.22158/asir.v5n2p49.Google Scholar
Komal, “Fuzzy fault tree analysis for controlling robot-related accidents involving humans inindustrial plants: A case study,” Int. J. Qual. Reliab. Manag. 38(6), 1342–1365 (2021). doi: 10.1108/IJQRM-03-2020-0069.CrossRefGoogle Scholar
Xu, F., Yang, Z. and Hu, J., “Fault diagnosis of a selective compliance assembly robot arm manipulator based on the end joint motion analysis: Threshold algorithm and experiments,” Trans. Inst. Meas. Control 40(5), 1691–1700 (2018). doi: 10.1177/0142331217690222.CrossRefGoogle Scholar
Ma, H. and Yang, G., “Simultaneous fault diagnosis for robot manipulators with actuator and sensor faults,” Inf. Sci. 366(11), 12–30 (2016). doi: 10.1016/j.ins.2016.05.016.CrossRefGoogle Scholar
Sathish, V., Mikael, N., Michal, O. and Sachit, B., “A transfer entropy based approach for fault isolation in industrial robots,” Lett. Dyn. Syst. Control 2(1), 1–23 (2021). doi: 10.1115/1.4051565.Google Scholar
Huang, H., Xie, X., Wang, J. and Wang, C., “Observer-based fault diagnosis scheme for actuators in robot manipulators,” Meas. Control Technol. 39(09), 25–32 (2020).Google Scholar
Ahmad, S., Zhang, H. and Liu, G., “Distributed fault detection for modular and reconfigurable robots with joint torque sensing: A prediction error based approach,” Mechatronics 23(6), 607–616 (2013). doi: 10.1016/j.mechatronics.2013.05.008.CrossRefGoogle Scholar
Yang, J., Jin, L., Han, Z., Zhao, D. and Hu, M., “Sensitivity analysis of factors affecting motion reliability of manipulator and fault diagnosis based on kernel principal component analysis,” Robotica 40(8), 2547–2566 (2021). doi: 10.1017/S0263574721001788.CrossRefGoogle Scholar
Hong, Y., Sun, Y., Zou, X. and Long, J., “Multi-joint Industrial Robot Fault Identification Using Deep Sparse Auto-Encoder Network with Attitude Data,” In: 2020 Prognostics and Health Management Conference (PHM-Besançon) , Besancon, France (2020) pp. 176–179.Google Scholar
Pan, J., Qu, L. and Peng, K., “Sensor and actuator fault diagnosis for robot joint based on deep CNN,” Entropy 23(6), 751 (2021). doi: 10.3390/e23060751.CrossRefGoogle ScholarPubMed
Jaber, A. A. and Bicker, R., “Fault diagnosis of industrial robot gears based on discrete wavelet transform and artificial neural network,” Insight 58(4), 179–186 (2016). doi: 10.1784/insi.2016.58.4.179.CrossRefGoogle Scholar
Jia, Q., Li, T. and Chen, G., “Sensitivity analysis on factors influencing motion reliability of space manipulator based on the multilayer mapping model,” J. Mech. Eng. 53(11), 10–19 (2017). doi: 10.3901/JME.2017.11.010.CrossRefGoogle Scholar
Xu, X., Cao, D., Zhou, Y. and Gao, J., “Application of neural network algorithm in fault diagnosis of mechanical intelligence,” Mech. Syst. Signal Process. 141(6), 106625 (2020). doi: 10.1016/j.ymssp.2020.106625.CrossRefGoogle Scholar
Pu, J., Diego, C. and Vinicio, S., “Exploiting generative adversarial networks as an oversampling method for fault diagnosis of an industrial robotic manipulator,” Appl. Sci. 10(21), 7712 (2020). doi: 10.3390/app10217712.CrossRefGoogle Scholar
Jaber, A. A. and Bicker, R., “Industrial robot backlash fault diagnosis based on discrete wavelet transform and artificial neural network,” Am. J. Mech. Eng. 41(1), 21–31 (2016). doi: 10.12691/ajme-4-1-4.Google Scholar
Long, J., Mou, J., Zhang, L., Zhang, S. and Li, C., “Attitude data-based deep hybrid learning architecture for intelligent fault diagnosis of multi-joint industrial robots,” J. Manuf. Syst. 61(7), 736–745 (2021). doi: 10.1016/j.jmsy.2020.08.010.CrossRefGoogle Scholar