scholarly journals Forward Kinematics for Suspended Under-Actuated Cable-Driven Parallel Robots: A Neural Network Approach

2021 ◽  
Author(s):  
Utkarsh A. Mishra ◽  
Stéphane Caro
Keyword(s):  
Neural Network ◽  
Parallel Robot ◽  
Parallel Robots ◽  
Least Square ◽  
Equilibrium Equations ◽  
Neural Network Approach ◽  
Comparison Results ◽  
Unsupervised Neural Network ◽  
Non Linear ◽  
Neural Network Algorithm

Abstract Kinematic analysis of under-constrained Cable-Driven Parallel Robots has been a topic of interest because of the inherent coupling between the loop-closure and static equilibrium equations. The paper proposes an unsupervised neural network algorithm to perform real-time forward geometrico-static analysis of such robots in a suspended configuration under the action of gravity. The formulation determines a non-linear function approximation to model the problem and proves to be efficient in solving for consecutive and close waypoints in a path. The methodology is applied on a six-degree-of-freedom (6-DOF) spatial under-constrained suspended cable-driven parallel robot. Specific comparison results to show the effectiveness of the proposed method in tracking a given path and degree of constraint satisfaction are presented against the results obtained from non-linear least-square optimization.

scholarly journals Excitation Forces Estimation for Non-linear Wave Energy Converters: A Neural Network Approach

2020 ◽  
Vol 53 (2) ◽  
pp. 12334-12339
Author(s):  
M. Bonfanti ◽  
F. Carapellese ◽  
S.A. Sirigu ◽  
G. Bracco ◽  
G. Mattiazzo
Keyword(s):  
Neural Network ◽  
Wave Energy ◽  
Linear Wave ◽  
Network Approach ◽  
Neural Network Approach ◽  
Wave Energy Converters ◽  
Non Linear ◽  
Energy Converters

Simultaneous base and tool calibration for self-calibrated parallel robots

Robotica ◽  
2002 ◽  
Vol 20 (4) ◽  
pp. 367-374 ◽  
Author(s):  
Guilin Yang ◽  
I-Ming Chen ◽  
Song Huat Yeo ◽  
Wee Kiat Lim
Keyword(s):  
Parallel Robot ◽  
Parallel Robots ◽  
Sufficient Accuracy ◽  
Least Square ◽  
Mobile Platform ◽  
Calibration Model ◽  
End Effector ◽  
The World ◽  
Kinematic Transformation ◽  
Kinematic Errors

In this paper, we focus on the base and tool calibration of a self-calibrated parallel robot. After the self-calibration of a parellel robot by using the built-in sensors in the passive joints, its kinematic transformation from the robot base to the mobile platform frame can be computed with sufficient accuracy. The base and tool calibration, hence, is to identify the kinematic errors in the fixed transformations from the world frame to the robot base frame and from the mobile platform frame to the tool (end-effector) frame in order to improve the absolute positioning accuracy of the robot. Using the mathematical tools from group theory and differential geometry, a simultaneous base and tool calibration model is formulated. Since the kinematic errors in a kinematic transformation can be represented by a twist, i.e. an element of se(3), the resultant calibration model is simple, explicit and geometrically meaningful. A least-square algorithm is employed to iteratively identify the error parameters. The simulation example shows that all the preset kinematic errors can be fully recovered within three to four iterations.

scholarly journals High genetic differentiation of grapevine rootstock varieties determined by molecular markers and artificial neural networks

2019 ◽  
Vol 42 ◽  
pp. e43475 ◽  
Author(s):  
Marcia Oliveira Costa ◽  
Livia Santos Capel ◽  
Carlos Maldonado ◽  
Freddy Mora ◽  
Claudete Aparecida Mangolin ◽  
...  
Keyword(s):  
Neural Network ◽  
Molecular Markers ◽  
Genetic Differentiation ◽  
Allelic Frequency ◽  
Self Organizing Map ◽  
Neural Network Approach ◽  
New Varieties ◽  
Neural Network Algorithm ◽  
Artificial Neural ◽  
The Individual

The genetic differentiation of grapevine rootstock varieties was inferred by the Artificial Neural Network approach based on the Self-Organizing Map algorithm. A combination of RAPD and SSR molecular markers, yielding polymorphic informative loci, was used to determine the genetic characterization among the rootstock varieties 420-A, Schwarzmann, IAC-766 Campinas, Traviú, Kober 5BB, and IAC-572 Jales. A neural network algorithm, based on allelic frequency, showed that the individual grapevine rootstocks (n = 64) were grouped into three genetically differentiated clusters. Cluster 1 included only the Kober 5BB rootstock, Cluster 2 included rootstocks of the varieties Traviú and IAC-572, and Cluster 3 included 420-A, Schwarzmann and IAC-766 plants. Evidence from the current study indicates that, despite the morphological similarities of the 420-A and Kober 5BB varieties, which share the same genetic origin, two new varieties were generated that are genetically divergent and show differences in performance.

Sign in / Sign up

Export Citation Format

Share Document