Robot manipulator identification based on adaptive multiple-input and multiple-output neural model optimized by advanced differential evolution algorithm

This article proposes a novel advanced differential evolution method which combines the differential evolution with the modified back-propagation algorithm. This new proposed approach is applied to train an adaptive enhanced neural model for approximating the inverse model of the industrial robot arm. Experimental results demonstrate that the proposed modeling procedure using the new identification approach obtains better convergence and more precision than the traditional back-propagation method or the lonely differential evolution approach. Furthermore, the inverse model of the industrial robot arm using the adaptive enhanced neural model performs outstanding results.

[1]  Saudi Arabia,et al.  A Differential Evolution Based Adaptive Neural Network Pitch Controller for a Doubly Fed Wind Turbine Generator System , 2013 .

[2]  Ching-Hung Lee,et al.  Performance enhancement of the differential evolution algorithm using local search and a self-adaptive scaling factor , 2012 .

[3]  Joni-Kristian Kämäräinen,et al.  Differential Evolution Training Algorithm for Feed-Forward Neural Networks , 2003, Neural Processing Letters.

[4]  Yonggwan Won,et al.  The Use of Evolutionary Algorithm in Training Neural Networks for Hematocrit Estimation , 2009 .

[5]  K. Bandurski,et al.  Training neural networks with a hybrid differential evolution algorithm , 2009 .

[6]  M. J. Nigam,et al.  Neuro-Fuzzy based Approach for Inverse Kinematics Solution of Industrial Robot Manipulators , 2008, Int. J. Comput. Commun. Control.

[7]  Nguyen Thanh Nam,et al.  Novel Adaptive Forward Neural MIMO NARX Model for the Identification of Industrial 3-DOF Robot Arm Kinematics , 2012 .

[8]  R. Storn,et al.  Differential Evolution - A simple and efficient adaptive scheme for global optimization over continuous spaces , 2004 .

[9]  J. Humberto Pérez-Cruz,et al.  Evolving intelligent system for the modelling of nonlinear systems with dead-zone input , 2014, Appl. Soft Comput..

[10]  Saikat Singha Roy.  Effective System Identification Using Fused Network and DE Based Training Scheme , 2013 .

[11]  Xiaodong Liu,et al.  The PID Controller Based on the Artificial Neural Network and the Differential Evolution Algorithm , 2012, J. Comput..

[12]  M. Bialko,et al.  Training of artificial neural networks using differential evolution algorithm , 2008, 2008 Conference on Human System Interactions.

[13]  Sibarama Panigrahi,et al.  A Modified Differential Evolution Algorithm trained Pi-Sigma Neural Network for Pattern Classification , 2013 .

[14]  Swati Swayamsiddha,et al.  Nonlinear System Identification using Evolutionary Computing based Training Schemes , 2013 .

[15]  Jose de Jesus Rubio,et al.  Modified optimal control with a backpropagation network for robotic arms , 2012 .

[16]  Bidyadhar Subudhi,et al.  Nonlinear system identification using memetic differential evolution trained neural networks , 2011, Neurocomputing.

[17]  Stefen Hui,et al.  Application of feedforward neural networks to dynamical system identification and control , 1993, IEEE Trans. Control. Syst. Technol..

[18]  Springer-Verlag London,et al.  Adaptive neural controller for space robot system with an attitude controlled base , 2013 .

[19]  Cheng-Jian Lin,et al.  DESIGN OF A RECURRENT FUNCTIONAL NEURAL FUZZY NETWORK USING MODIFIED DIFFERENTIAL EVOLUTION , 2010 .

[20]  Fernando Bordignon,et al.  Uninorm based evolving neural networks and approximation capabilities , 2014, Neurocomputing.

[21]  José de Jesús Rubio,et al.  Dynamic model with sensor and actuator for an articulated robotic arm , 2012, Neural Computing and Applications.

[22]  José de Jesús Rubio,et al.  Evolving intelligent algorithms for the modelling of brain and eye signals , 2014, Appl. Soft Comput..