TY - GEN
T1 - A novel optimization robust design of artificial neural networks to solve the inverse kinematics of a manipulator of 6 DOF
AU - Ibarra-Perez, Teodoro
AU - Del Rosario Martinez-Blanco, Ma
AU - Olivera-Domingo, Fernando
AU - Manuel Ortiz-Rodriguez, Jose
AU - Gomez-Escribano, Javier
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/3/10
Y1 - 2021/3/10
N2 - In the design of neural networks, generally the selection of the structural parameters is chosen through trial and error procedures, consuming large amounts of resources and unavailable time, without guaranteeing the optimal configuration of the parameters that allow obtaining the best performance of the network. In this paper, the robust design methodology of artificial neural networks based on the Taguchi philosophy was used to select the optimal parameters in a back-propagation network architecture to solve the inverse kinematics in a 6 degrees of freedom robotic manipulator. The parameters to optimize were the number of hidden layers, the number of neurons per layer, the learning rate, the momentum, the number of neurons per layer and the size of the training set versus the test set. Allowing to identify all the combinations possible in relation to the number of variables involved by performing a significant number of experiments compared to other methods where they usually run a huge number of experiments.
AB - In the design of neural networks, generally the selection of the structural parameters is chosen through trial and error procedures, consuming large amounts of resources and unavailable time, without guaranteeing the optimal configuration of the parameters that allow obtaining the best performance of the network. In this paper, the robust design methodology of artificial neural networks based on the Taguchi philosophy was used to select the optimal parameters in a back-propagation network architecture to solve the inverse kinematics in a 6 degrees of freedom robotic manipulator. The parameters to optimize were the number of hidden layers, the number of neurons per layer, the learning rate, the momentum, the number of neurons per layer and the size of the training set versus the test set. Allowing to identify all the combinations possible in relation to the number of variables involved by performing a significant number of experiments compared to other methods where they usually run a huge number of experiments.
KW - artificial neural networks
KW - backpropagation
KW - optimization
KW - robot kinematics
UR - http://www.scopus.com/inward/record.url?scp=85112570942&partnerID=8YFLogxK
U2 - 10.1109/ICIT46573.2021.9453701
DO - 10.1109/ICIT46573.2021.9453701
M3 - Contribución a la conferencia
AN - SCOPUS:85112570942
T3 - Proceedings of the IEEE International Conference on Industrial Technology
SP - 838
EP - 843
BT - Proceedings - 2021 22nd IEEE International Conference on Industrial Technology, ICIT 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 22nd IEEE International Conference on Industrial Technology, ICIT 2021
Y2 - 10 March 2021 through 12 March 2021
ER -