RSM And ANFIS Based Parameters Prediction of Robot Using GRA

  • Authors

    • P. Gopu
    • M. Dev Anand
    • . .
    2018-12-09
    https://doi.org/10.14419/ijet.v7i4.36.24208
  • Robot, response surface methodology, adaptive neuro fuzzy inference system.
  • Ability of robot arm manipulation must be highly accurate and repeatable one. Performance uncertainty is causes by some noise factor. The effects of these factors were model to reduce the uncertainty of the robotic arm performance. In this paper highlights the prediction of output parameters robot cell data like X, Y and Z axis through Response Surface Methodology (RSM) and Adaptive Neuro Fuzzy Inference System (ANFIS) for reduce the performance variation of the robot. The input kinematic parameters like θ1, θ2, θ3, θ4, θ5 has been considered and the output multi objective parameters X, Y and Z axis has been converted in to single objective parameter. The graph which plots between parameters and the output response indicates the influence of the every single parameter for the performance output contribution. From the simulated values of Response Surface Methodology and Adaptive Neuro Fuzzy Inference System, the percentage of error obtained in Adaptive Neuro Fuzzy Inference System has minimum one when compared with Response Surface Methodology of prediction.

     

     

  • References

    1. [1] Zhang J & Cai J, “Error Analysis and Compensation Method of 6-axis Industrial Robotâ€, International Journal on Smart Sensing and Intelligent Systems, Vol.6, No.4, (2013).

      [2] Rout BK & Mittal RK, “Tolerance Design of Robot Parameters Using Taguchi Methodâ€, Elsevier, Mechanical Systems and Signal Processing, (2005).

      [3] Shiakolas PS, Conrad KL & Yih TC, “On the Accuracy, Repeatability, and Degree of Influence of Kinematics Parameters for Industrial Robotsâ€, International Journal of Modelling and Simulation, Vol.22, No.3, (2002).

      [4] Butler S & Demiris Y, “Predicting the Movements of Robot Teams Using Generative Modelsâ€, Distributed Autonomous Robotic Systems, Vol.8, (2009), pp.533-542.

      [5] Trung TT, Guang LW & Long PT, “Tolerance Design of Robot Parameters Using Generalized Reduced Gradient Algorithmâ€, International Journal of Materials, Mechanics and Manufacturing, Vol.5, No.2, (2016).

  • Downloads

  • How to Cite

    Gopu, P., Dev Anand, M., & ., . (2018). RSM And ANFIS Based Parameters Prediction of Robot Using GRA. International Journal of Engineering & Technology, 7(4.36), 604-607. https://doi.org/10.14419/ijet.v7i4.36.24208