Real-time load identification method for multi-joint robots based on improved Fourier neural network

PDF(2865 KB)

Journal of Vibration and Shock ›› 2025, Vol. 44 ›› Issue (5) : 314-322.

FAULT DIAGNOSIS ANALYSIS

Real-time load identification method for multi-joint robots based on improved Fourier neural network

YUE Xia, LI Zhibin, ZHANG Chunliang, WANG Yadong, WANG Yuhua, LONG Shangbin*

Author information +

History +

Abstract

The joint robot is used in all kinds of production links, real-time monitoring of the load is the premise to ensure the safe operation of the robot. However, in some special scenarios, the load cannot be measured directly, and the dynamic method is usually used to solve the problem indirectly. Due to its obvious nonlinear characteristics and the uncertainty of model parameters, the accuracy and efficiency of load identification are not high. Therefore, this paper proposes an improved model based on Fourier neural network to realize load identification, so as to improve the prediction accuracy and timeliness of system load parameters. The proposed method uses the convolution and frequency domain truncation mechanism of Fourier neural network to obtain the characteristic signal quickly, and fuses the output result of feedforward neural network to obtain the identification result. Compared with the dynamic model solving method, the proposed method has higher precision and faster calculation speed. It only needs to learn several interphase sample sets within the prediction range to identify any result within the prediction range, and has good generalization ability. At the same time, the network sensitive parameters are analyzed, and the performance is compared with the mature neural network algorithm. In this method, two kinds of neural network models cooperate with each other, which can effectively identify different feature sets in high-dimensional data, so as to realize parameter identification, and provide reference for parameter identification of complex nonlinear systems.

Key words

Industrial robots / Fourier Neural Network / Dynamics / Real-time / Load identification;

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

YUE Xia, LI Zhibin, ZHANG Chunliang, WANG Yadong, WANG Yuhua, LONG Shangbin. Real-time load identification method for multi-joint robots based on improved Fourier neural network[J]. Journal of Vibration and Shock, 2025, 44(5): 314-322

References

[1] 陈仁祥, 谢文举, 杨宝军等. 变初位数据增强和深度特征提取的工业机器人末端抖动状态识别[J]. 振动与冲击, 2023, 42(11): 199-206+251.
CHEN Renxiang, XIE Wenju, YANG Baojun, et al. End jitter state recognition of industrial robots based on variable initial data enhancement and depth feature extraction[J]. Journal of Vibration and Shock, 2019, 42(11): 199-206+251.
[2] 李琳, 古智超, 张铁. 结合机器人柔体动力学和关节力矩反馈的振动控制[J]. 振动与冲击, 2022, 41(11): 235-244.
LI Lin, GU Zhichao, ZHANG Tie. Vibration Control of Robot Combining Flexible Body Dynamics and Joint Torque Feedback[J]. Journal of Vibration and Shock, 202, 41(11): 235-244.
[3] 彭云聪, 秦小林, 张力戈等. 面向图像分类的小样本学习算法综述[J]. 计算机科学, 2022, 49(05): 1-9.
PENG Yuncong, QIN Xiaolin, ZHANG Lige et al. Review of small sample learning algorithms for image classification[J]. Computer Science, 2022, 49(05): 1-9.
[4] 赵志宏, 张然, 刘克俭等. 一种改进原型网络的小样本轴承故障诊断方法[J]. 振动与冲击, 2023, 42(20): 214-221.
ZHAO Zhihong, ZHANG Ran, LIU Kejian, et al. A Small Sample Bearing Fault Diagnosis Method with Improved Prototype Network[J]. Journal of Vibration and Shock, 2019, 42(20): 214-221.
[5] Pan J, Jing B, Jiao X, et al. A Diagnosis Framework for High-reliability Equipment with Small Sample Based on Transfer Learning[J]. Complexity, 2022, 2022.
[6] Doan Q H, Mai S H, Do Q T, et al. A cluster-based data splitting method for small sample and class imbalance problems in impact damage classification[J]. Applied Soft Computing, 2022, 120: 108628.
[7] 张铁, 李熙尧, 邹焱飚. 机器人柔性负载残余振动抑制及测量方式研究[J/OL]. 机械设计与制造: 1-7[2022-03-15].
ZHANG Tie, LI Xiyao, ZOU Yanbiao. Research on Residual Vibration Suppression and Measurement Method of Robot Flexible Load[J/OL]. Machine Design & Manufacture: 1-7[2022-03-15].
[8] 张铁, 覃彬彬, 邹焱飚. 机器人负载的动力学参数辨识[J]. 工程科学学报, 2017, 39(12): 1907-1912.
ZHANG Tie, QIN Binbin, ZOU Yanbiao. Dynamic Parameter identification of robot load[J]. Chinese Journal of Engineering Science, 2017, 39(12): 1907-1912.
[9] Raissi M, Perdikaris P, Karniadakis G E. Physics-informed neural networks: A deeplearning framework for solving forward and inverse problems involving nonlinear partial differential equations[J]. Journal of Computational physics, 2019, 378: 686-707.
[10] Raissi M, Yazdani A, Karniadakis G E. Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations[J]. Science, 2020, 367(6481): 1026-1030.
[11] Zhu Y, Zabaras N, Koutsourelakis P S, et al. Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data[J]. Journal of Computational Physics, 2019, 394: 56-81.
[12] Bar-Sinai Y, Hoyer S, Hickey J, et al. Learning data-driven discretizations for partial differential equations[J]. Proceedings of the National Academy of Sciences, 2019, 116(31): 15344-15349.
[13] Lample G, Charton F. Deep learning for symbolic mathematics[J]. arXiv preprint arXiv:1912.01412, 2019.
[14] Zang Y, Bao G, Ye X, et al. Weak adversarial networks for high-dimensional partial differential equations[J]. Journal of Computational Physics, 2020, 411: 109409.
[15] Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators[J]. Neural networks, 1989, 2(5): 359-366.
[16] Mathieu M, Henaff M, LeCun Y. Fast training of convolutional networks through ffts[J]. arXiv preprint rXiv:1312.5851, 2013.
[17] Li Z, Kovachki N, Azizzadenesheli K, et al. Fourier neural operator for parametric partial differential equations[J]. arXiv preprint arXiv:2010.08895, 2020.
[18] Vahid K A, Prabhu A, Farhadi A, et al. Butterfly transform: An efficient fft based neural architecture design[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020: 12021-12030.
[19] Raviola A,GUIDA R ，MARTIN A D， et al. Effects of Temperature and Mounting Configuration on the Dynamic Parameters Identification of Industrial Robots[J]. Robotics, 2021, 10 (3): 83.
[20] 董稷坤. 机器人负载动力学参数辨识及刚柔耦合误差补偿技术[D]. 北京工业大学, 2023.
[21] ZHANG G, XU Z, HOU Z, et al. A systematic error compensation strategy based on an optimized recurrent neural network for collaborative robot dynamics[J]. Applied Sciences, 2020, 10:6743.
[22] Universal Robots-DH parameters for calculations of kinematics and dynamics[EB/OL]. [2022-01-19].