Adaptive neural model optimized by modified differential evolution for identifying 5-DOF robot manipulator dynamic system

This paper proposes an adaptive neural network (ANN) model for modeling the nonlinear dynamic of a robot manipulator based on experimental input–output data from the system. The ANN model is created by combining the multilayer perceptron neural network structure and the nonlinear auto-regressive with eXogenous input model and is trained by the modified differential evolution (MDE) algorithm. The effectiveness of the proposed method is evaluated and compared with other algorithms such as the back-propagation algorithm, the traditional differential evolution and the hybrid differential evolution–back-propagation algorithm. The results prove that the proposed ANN model optimized by the MDE algorithm for the 5-DOF robot manipulator dynamic is successfully modeled and performed well.

[1]  Maxime Gautier,et al.  Identification of joint stiffness with bandpass filtering , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[2]  Sung-Bae Cho,et al.  Towards Crafting a Smooth and Accurate Functional Link Artificial Neural Networks Based on Differential Evolution and Feature Selection for Noisy Database , 2015, Int. J. Comput. Intell. Syst..

[3]  Qingfu Zhang,et al.  Differential Evolution With Composite Trial Vector Generation Strategies and Control Parameters , 2011, IEEE Transactions on Evolutionary Computation.

[4]  Adam P. Piotrowski,et al.  Differential Evolution algorithms applied to Neural Network training suffer from stagnation , 2014, Appl. Soft Comput..

[5]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[6]  Janez Brest,et al.  Performance comparison of self-adaptive and adaptive differential evolution algorithms , 2007, Soft Comput..

[7]  Nurhan Karaboga,et al.  Performance Comparison of Genetic and Differential Evolution Algorithms for Digital FIR Filter Design , 2004, ADVIS.

[8]  Juan Eduardo Velázquez-Velázquez,et al.  Identification of a Cylindrical Robot Using Recurrent Neural Networks , 2015 .

[9]  Mikael Norrlöf,et al.  Closed-Loop Identification of an Industrial Robot Containing Flexibilities , 2003 .

[10]  Kyoung Kwan Ahn,et al.  A New Approach of the 2-Axes PAM Robot arm Identification using Neural MIMO NARX Model , 2013, Int. J. Artif. Intell. Tools.

[11]  Faa-Jeng Lin,et al.  Wavelet Fuzzy Neural Network With Asymmetric Membership Function Controller for Electric Power Steering System via Improved Differential Evolution , 2015, IEEE Transactions on Power Electronics.

[12]  Vadlamani Ravi,et al.  Differential evolution trained wavelet neural networks: Application to bankruptcy prediction in banks , 2009, Expert Syst. Appl..

[13]  Laura Giarré,et al.  NARX models of an industrial power plant gas turbine , 2005, IEEE Transactions on Control Systems Technology.

[14]  Amit Konar,et al.  Differential Evolution Using a Neighborhood-Based Mutation Operator , 2009, IEEE Transactions on Evolutionary Computation.

[15]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[16]  Nguyen Ngoc Son,et al.  Adaptive displacement online control of shape memory alloys actuator based on neural networks and hybrid differential evolution algorithm , 2015, Neurocomputing.

[17]  Jouni Lampinen,et al.  A Fuzzy Adaptive Differential Evolution Algorithm , 2005, Soft Comput..

[18]  P. N. Suganthan,et al.  Differential Evolution Algorithm With Strategy Adaptation for Global Numerical Optimization , 2009, IEEE Transactions on Evolutionary Computation.

[19]  Han-Xiong Huang,et al.  A proposed iteration optimization approach integrating backpropagation neural network with genetic algorithm , 2015, Expert Syst. Appl..

[20]  Eugen Diaconescu,et al.  The use of NARX neural networks to predict chaotic time series , 2008 .

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

[22]  Himansu Das,et al.  A Novel PSO Based Back Propagation Learning-MLP (PSO-BP-MLP) for Classification , 2015 .

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

[24]  Alberto Tesi,et al.  On the Problem of Local Minima in Backpropagation , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Bidyadhar Subudhi,et al.  A differential evolution based neural network approach to nonlinear system identification , 2011, Appl. Soft Comput..

[26]  J. De Schutter,et al.  Dynamic Model Identification for Industrial Robots , 2007, IEEE Control Systems.

[27]  Madhumita Panda,et al.  A Hybrid Differential Evolution and Back-Propagation Algorithm for Feedforward Neural Network Training , 2013 .

[28]  René Thomsen,et al.  A comparative study of differential evolution, particle swarm optimization, and evolutionary algorithms on numerical benchmark problems , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[29]  L. Piroddi,et al.  An identification algorithm for polynomial NARX models based on simulation error minimization , 2003 .

[30]  Geir Hovland,et al.  Identification of Coupled Elastic Dynamics Using Inverse Eigenvalue Theory , 2001 .

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

[32]  Saku Kukkonen,et al.  Real-parameter optimization with differential evolution , 2005, 2005 IEEE Congress on Evolutionary Computation.

[33]  H. Tamura,et al.  An improved backpropagation algorithm to avoid the local minima problem , 2004, Neurocomputing.