Forward Kinematics of Delta Manipulator by Novel Hybrid Neural Network

For the parallel configuration of the robot manipulator, the solution of Forward Kinematics (FK) is tough as compared to Inverse Kinematics (IK). This work presents a novel hybrid method of optimizing an Artificial Neural Network (ANN) specifically Multilayer Perceptron (MLP) with Genetic Algorithm...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mahesh A. Makwana, Haresh P. Patolia
Formato:	article
Lenguaje:	EN
Publicado:	International Journal of Mathematical, Engineering and Management Sciences 2021
Materias:	forward kinematics parallel manipulator artificial neural network genetic algorithm feed forward back propagation Technology T Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/edfc224ab3ee473b840605d92e8221d3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:edfc224ab3ee473b840605d92e8221d3
record_format	dspace
spelling	oai:doaj.org-article:edfc224ab3ee473b840605d92e8221d32021-12-04T05:29:29ZForward Kinematics of Delta Manipulator by Novel Hybrid Neural Network10.33889/IJMEMS.2021.6.6.1002455-7749https://doaj.org/article/edfc224ab3ee473b840605d92e8221d32021-12-01T00:00:00Zhttps://ijmems.in/cms/storage/app/public/uploads/volumes/100-IJMEMS-21-0119-6-6-1694-1708-2021.pdfhttps://doaj.org/toc/2455-7749For the parallel configuration of the robot manipulator, the solution of Forward Kinematics (FK) is tough as compared to Inverse Kinematics (IK). This work presents a novel hybrid method of optimizing an Artificial Neural Network (ANN) specifically Multilayer Perceptron (MLP) with Genetic Algorithm (GA) and Step-wise Linear Regression (SWLR) to solve the complex FK of Delta Parallel Manipulator (DPM). The joint space angular positional data has been iterated using IK to generate point cloud of Cartesian space positional data. This data set is highly random and broad which leads to higher-order nonlinearity. Hence, normalization of the dataset has been done to avoid outliers from the dataset and to achieve better performance. The developed ANN based MLP gave a mean square error of 0.0000762 and an overall R2 value of 0.99918. Finally, the proposed network has been simulated to solve FK of the parallel manipulator and to check its efficacy. For given joint angles, the proposed network predicted positional values which are in good approximation with known trajectory solved by standard analytical method.Mahesh A. MakwanaHaresh P. PatoliaInternational Journal of Mathematical, Engineering and Management Sciencesarticleforward kinematicsparallel manipulatorartificial neural networkgenetic algorithmfeed forward back propagationTechnologyTMathematicsQA1-939ENInternational Journal of Mathematical, Engineering and Management Sciences, Vol 6, Iss 6, Pp 1694-1708 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	forward kinematics parallel manipulator artificial neural network genetic algorithm feed forward back propagation Technology T Mathematics QA1-939
spellingShingle	forward kinematics parallel manipulator artificial neural network genetic algorithm feed forward back propagation Technology T Mathematics QA1-939 Mahesh A. Makwana Haresh P. Patolia Forward Kinematics of Delta Manipulator by Novel Hybrid Neural Network
description	For the parallel configuration of the robot manipulator, the solution of Forward Kinematics (FK) is tough as compared to Inverse Kinematics (IK). This work presents a novel hybrid method of optimizing an Artificial Neural Network (ANN) specifically Multilayer Perceptron (MLP) with Genetic Algorithm (GA) and Step-wise Linear Regression (SWLR) to solve the complex FK of Delta Parallel Manipulator (DPM). The joint space angular positional data has been iterated using IK to generate point cloud of Cartesian space positional data. This data set is highly random and broad which leads to higher-order nonlinearity. Hence, normalization of the dataset has been done to avoid outliers from the dataset and to achieve better performance. The developed ANN based MLP gave a mean square error of 0.0000762 and an overall R2 value of 0.99918. Finally, the proposed network has been simulated to solve FK of the parallel manipulator and to check its efficacy. For given joint angles, the proposed network predicted positional values which are in good approximation with known trajectory solved by standard analytical method.
format	article
author	Mahesh A. Makwana Haresh P. Patolia
author_facet	Mahesh A. Makwana Haresh P. Patolia
author_sort	Mahesh A. Makwana
title	Forward Kinematics of Delta Manipulator by Novel Hybrid Neural Network
title_short	Forward Kinematics of Delta Manipulator by Novel Hybrid Neural Network
title_full	Forward Kinematics of Delta Manipulator by Novel Hybrid Neural Network
title_fullStr	Forward Kinematics of Delta Manipulator by Novel Hybrid Neural Network
title_full_unstemmed	Forward Kinematics of Delta Manipulator by Novel Hybrid Neural Network
title_sort	forward kinematics of delta manipulator by novel hybrid neural network
publisher	International Journal of Mathematical, Engineering and Management Sciences
publishDate	2021
url	https://doaj.org/article/edfc224ab3ee473b840605d92e8221d3
work_keys_str_mv	AT maheshamakwana forwardkinematicsofdeltamanipulatorbynovelhybridneuralnetwork AT hareshppatolia forwardkinematicsofdeltamanipulatorbynovelhybridneuralnetwork
_version_	1718372827490418688

Forward Kinematics of Delta Manipulator by Novel Hybrid Neural Network

Ejemplares similares