Total views : 80

Implementation of Dynamics Neural Network in Solving Inverse Function

Affiliations

  • Faculty of Engineering, Technology and Built Environment, UCSI University, Kuala Lumpur, Malaysia

Abstract


Back-Propagation Neural Network (BPNN) has been widely used in solving nonlinear problems. However, there are some limitations in using conventional BPNN especially for high order nonlinear problems. Dynamic Back-Propagation Neural Network (DBPNN) is proposed in this paper to improve the performance of conventional BPNN. Its adaptive learning ability is closer to human being learning behavior in comparing to conventional BPNN. Few simulations have been run to test the robustness of DBPNN and the results are compared to the conventional BPNN.

Keywords

Artificial Intelligences, Neural Networks, Nonlinear Function.

Full Text:

 |  (PDF views: 98)

References


  • Tang SH, Ang CK, Mashohor S, Arrifin MKAM. Predicting the motion of a robot manipulator with unknown trajectories based on artificial neural network. Int J Adv Robot Syst.2014; 11(176):1–9.
  • Ang CK, Tang SH, Mashohor S, Arrifin MKAM. Solving continuous trajectory and forward kinematics simultaneously based on artificial neural network. Int J Comput Commun. 2014; 9(3):253–60.
  • Kumar N, Panwar V, Sukanam N, Sharma SP, Borm JH.Neural network-based nonlinear tracking control of kinematically redundant robot manipulators. Math Comput Model. 2011; 53:1889–901.
  • Shah J, Rattan SS, Nakra BC. Kinematic analysis of 2-DOF planar robot using artificial neural network. World Acad Sci Eng Technol. 2011; 81:282–5.
  • Park H, Lee S, Chu B, Hong D. Obstacle avoidance for robotic excavators using a recurrent neural network. IEEE Int Conf on Smart Manufacturing Application; 2008. p.585–90.
  • Wang J. Obstacle avoidance for kinematically redundant manipulators based on recurrent neural networks. 1st IEEE Int Conf on Intelligent Robotics and Application; 2008 Oct.p. 10–3.
  • Kosko B. Adaptive bidirectional associative memories.Appl Optics. 1987; 26:4947–60.
  • Kim BH. An adaptive neural network learning-based solution for the inverse kinematics of humanoid fingers. Int J Adv Robot Syst. 2014; 11:1–9.
  • Capisani LM, Ferrara A. Trajectory planning and secondorder sliding mode motion/interaction control for robot manipulators in unknown environments. IEEE T Ind Electron. 2012; 29:3189–98.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.