Co-Optimization of Vibration Suppression and Data Efficiency in Robotic Manipulator Dynamic Modeling
In response to the limitations of vibration suppression performance caused by the difficulty in accurately modeling nonlinear friction during robotic manipulator dynamics parameter identification, this paper proposes a hybrid identification method based on a Broad Learning System (BLS) optimized by...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/14/7679 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839616618714365952 |
|---|---|
| author | Xiaowei Han Kunru Wu Nanmu Hui |
| author_facet | Xiaowei Han Kunru Wu Nanmu Hui |
| author_sort | Xiaowei Han |
| collection | DOAJ |
| description | In response to the limitations of vibration suppression performance caused by the difficulty in accurately modeling nonlinear friction during robotic manipulator dynamics parameter identification, this paper proposes a hybrid identification method based on a Broad Learning System (BLS) optimized by Particle Swarm Optimization (PSO). First, a joint excitation trajectory is designed using a fifth-order Fourier series with zero boundary conditions to ensure sufficient excitation of system dynamics. Then, a linear regression formulation of the manipulator’s structural dynamics is established, and the BLS network is employed to model the unstructured residuals—primarily arising from nonlinear friction—with high precision. Finally, the PSO algorithm is applied to optimize the hyperparameters of the BLS network, achieving global model optimality. Simulation results demonstrate that under typical motion conditions of the manipulator, the proposed method exhibits excellent capability in capturing nonlinear disturbances, maintaining joint prediction errors below 6 × 10<sup>−12</sup> N·m. This significantly improves the accuracy and robustness of the feedforward vibration suppression control. Moreover, by integrating PSO-based hyperparameter optimization and trajectory design with sufficient excitation, the proposed method enhances data efficiency during the identification process, offering a novel and practical identification strategy for precise modeling and control of complex mechanical systems. |
| format | Article |
| id | doaj-art-3a1a8cc2a8664a809bd1cadfa1fc2a22 |
| institution | Matheson Library |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-3a1a8cc2a8664a809bd1cadfa1fc2a222025-07-25T13:12:03ZengMDPI AGApplied Sciences2076-34172025-07-011514767910.3390/app15147679Co-Optimization of Vibration Suppression and Data Efficiency in Robotic Manipulator Dynamic ModelingXiaowei Han0Kunru Wu1Nanmu Hui2School of Mechanical Engineering, Shenyang University, Shenyang 110044, ChinaSchool of Intelligent Science and Information Engineering, Shenyang University, Shenyang 110044, ChinaSchool of Intelligent Science and Information Engineering, Shenyang University, Shenyang 110044, ChinaIn response to the limitations of vibration suppression performance caused by the difficulty in accurately modeling nonlinear friction during robotic manipulator dynamics parameter identification, this paper proposes a hybrid identification method based on a Broad Learning System (BLS) optimized by Particle Swarm Optimization (PSO). First, a joint excitation trajectory is designed using a fifth-order Fourier series with zero boundary conditions to ensure sufficient excitation of system dynamics. Then, a linear regression formulation of the manipulator’s structural dynamics is established, and the BLS network is employed to model the unstructured residuals—primarily arising from nonlinear friction—with high precision. Finally, the PSO algorithm is applied to optimize the hyperparameters of the BLS network, achieving global model optimality. Simulation results demonstrate that under typical motion conditions of the manipulator, the proposed method exhibits excellent capability in capturing nonlinear disturbances, maintaining joint prediction errors below 6 × 10<sup>−12</sup> N·m. This significantly improves the accuracy and robustness of the feedforward vibration suppression control. Moreover, by integrating PSO-based hyperparameter optimization and trajectory design with sufficient excitation, the proposed method enhances data efficiency during the identification process, offering a novel and practical identification strategy for precise modeling and control of complex mechanical systems.https://www.mdpi.com/2076-3417/15/14/7679dynamic modelingflexible-joint robotsbroad learning systemparticle swarm optimizationvibration control |
| spellingShingle | Xiaowei Han Kunru Wu Nanmu Hui Co-Optimization of Vibration Suppression and Data Efficiency in Robotic Manipulator Dynamic Modeling Applied Sciences dynamic modeling flexible-joint robots broad learning system particle swarm optimization vibration control |
| title | Co-Optimization of Vibration Suppression and Data Efficiency in Robotic Manipulator Dynamic Modeling |
| title_full | Co-Optimization of Vibration Suppression and Data Efficiency in Robotic Manipulator Dynamic Modeling |
| title_fullStr | Co-Optimization of Vibration Suppression and Data Efficiency in Robotic Manipulator Dynamic Modeling |
| title_full_unstemmed | Co-Optimization of Vibration Suppression and Data Efficiency in Robotic Manipulator Dynamic Modeling |
| title_short | Co-Optimization of Vibration Suppression and Data Efficiency in Robotic Manipulator Dynamic Modeling |
| title_sort | co optimization of vibration suppression and data efficiency in robotic manipulator dynamic modeling |
| topic | dynamic modeling flexible-joint robots broad learning system particle swarm optimization vibration control |
| url | https://www.mdpi.com/2076-3417/15/14/7679 |
| work_keys_str_mv | AT xiaoweihan cooptimizationofvibrationsuppressionanddataefficiencyinroboticmanipulatordynamicmodeling AT kunruwu cooptimizationofvibrationsuppressionanddataefficiencyinroboticmanipulatordynamicmodeling AT nanmuhui cooptimizationofvibrationsuppressionanddataefficiencyinroboticmanipulatordynamicmodeling |