A typical dynamic parameter identification method of 6-degree-of-freedom industrial robot

Jiang, Surong; Jiang, Meng; Cao, Yanfei; Hua, Daren; Wu, Hongtao; Ding, Yadong; Chen, Bai

doi:10.1177/0959651817726477

Cited by 14 publications

(14 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The inertia parameters affect the robot's motion performance significantly when the robot is running at high speed [12], the inertia parameter vector of link can be expressed as:…”

Section: Dynamic Model and Identification Adynamics Identification Modelmentioning

confidence: 99%

“…Since the link dynamic parameters are redundant to determine the manipulator dynamic model uniquely, the observation matrix of inverse dynamic identification model is not often a full-rank matrix. The minimum inertia parameters set can be obtained by reducing and eliminating the linear correlation terms in the observation matrix [12]. The inverse dynamic identification model is [24]:…”

Section: Dynamic Model and Identification Adynamics Identification Modelmentioning

confidence: 99%

“…For parameter estimation methods, the least squares method [11], weighted least squares method [12], and maximum likelihood estimation method [9] are popular approaches. Machine learning has the nonlinear fitting ability, which is used to solve the problem of robot parameter identification.…”

Section: Introductionmentioning

confidence: 99%

“…In terms of identification strategy, The one-step identification method easily overwhelms joint parameters with small torque coefficients due to joint coupling. The step-by-step identification method can optimize the identification process and effectively improve identification accuracy [12].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning Aided Dynamic Parameter Identification of 6-DOF Robot Manipulators

et al. 2020

View full text Add to dashboard Cite

Generally, structural uncertainty of the robot dynamics system refers to model error caused by parameter identification, unstructured uncertainty is the unmodeled dynamic characteristic. No matter how elaborate modeling methods are used, there always be uncertainty. Therefore, this paper applies deep learning for the first time to aid robot dynamic parameter identification of 6 degrees of freedom robot manipulator for compensation of uncertain factors. Firstly, the relatively accurate prediction of torque is obtained by the physical dynamic model using the parameters identification method (errors are less than 10% of the maximum torques). Secondly, we propose a novel deep neural network based approach called Uncertainty Compensation Model (UCM) to compensate the torque error introduced by the uncertainty. The UCM mainly composed by proposed Input Control Module (ICM) and Error Learning Models (ELMs) based on Long-Short-Term Memory and attention mechanism. The proposed ICM, which effectively avoids the unnecessary interference, is used to control valid input for ELMs. The ELMs, consisted by ELM units, concern extracting salient features from sequence data to predict the joint error. Also, this paper summarizes the effects of valid input, timestep and attention mechanism on the performance of the UCM. Finally, the verification of parameter identification and torques compensation is carried out by a Universal Robot 5 manipulator. Compared with the prediction torques of physical dynamic model, the proposed UCM has a good ability to capture the friction characteristics and compensate for the error of local maximum torques, which effectively solves the deficiency of the physical dynamics model and improves prediction accuracy (errors are less than 6% of the maximum torques).

show abstract

“…The inertia parameters affect the robot's motion performance significantly when the robot is running at high speed [12], the inertia parameter vector of link can be expressed as:…”

Section: Dynamic Model and Identification Adynamics Identification Modelmentioning

confidence: 99%

Section: Dynamic Model and Identification Adynamics Identification Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning Aided Dynamic Parameter Identification of 6-DOF Robot Manipulators

et al. 2020

View full text Add to dashboard Cite

show abstract

“…With the development of industrial technology, the manufacturing shops in factory are developing gradually from semi-automation to full automation, and the manpower in the production lines are gradually replaced by robots. [1][2][3] Since most operations are repetitive tasks, it requires the robots to have a good control effect on dealing with repetitive motions. However, iterative learning control (ILC) is very effective in handling the systems that perform the same tasks.…”

Section: Introductionmentioning

confidence: 99%

Iterative learning control of robot based on artificial bee colony algorithm

Wang

Chen

et al. 2019

Proceedings of the Institution of Mechanical Engineers, Part I:

Self Cite

View full text Add to dashboard Cite

For the repetitive motion control, inaccurate model, and other issues of industrial robots, this article presents a novel control method that the proportion differentiation-type iterative learning parameters are self-tuning based on artificial bee colony algorithm. Considering the influence of the numerical value of iterative learning parameters on the control system, especially in the early iteration, the control effect is not satisfactory. Thus, the artificial bee colony algorithm is introduced in this article. Using bee colony as search unit, the parameters in iterative learning are optimized through the exchange of information and the survival of fittest between them. And then the optimized results are returned to iterative learning control algorithm. Finally, the digital simulation of a two-degrees-of-freedom manipulator and the experimental verification of a cable-driven robot with its first two joints are carried out. The results show that the iterative learning control based on the artificial bee colony algorithm has faster convergence and better control effect than the iterative learning control with fixed parameters.

show abstract

Dynamic modeling and parameter identification for a gantry-type automated fiber placement machine

Cheng

Guo

et al. 2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Dynamic models play a critical role in the design of model-based controllers, and therefore have a significant effect on the dynamic characteristics of motion equipment. We mainly focus on the dynamic modeling and parameter identification for a gantry-type automated fiber placement (AFP) machine in this paper. First, a dynamic modeling process combining prismatic axes and revolute axes is conducted by the Newton-Euler method, in which the effects of friction and hydraulic balance system are also considered. Then, as the convenience for parameter identification and the application in linearity control, the methods of dynamic model linearization and determination of minimum inertial parameters based on the multi-body system (MBS) theory are proposed, and a dynamic model in the form of linearized minimum inertial parameters is consequently established.To identify the parameters in the model, key issues regarding excitation trajectory, filtering, and identification algorithm are discussed in detail. Finally, corresponding experiments are performed on the AFP machine, and experimental results show that there is a good agreement between the prediction of the model and the measurement in actuality. Data analysis shows that except for Zaxis, the relative error rates of the others are not greater than 5%, which proves the effectiveness of the established dynamic model and the identified parameters.

show abstract

A typical dynamic parameter identification method of 6-degree-of-freedom industrial robot

Cited by 14 publications

References 23 publications

Deep Learning Aided Dynamic Parameter Identification of 6-DOF Robot Manipulators

Deep Learning Aided Dynamic Parameter Identification of 6-DOF Robot Manipulators

Iterative learning control of robot based on artificial bee colony algorithm

Dynamic modeling and parameter identification for a gantry-type automated fiber placement machine

Contact Info

Product

Resources

About