Adaptive neural model optimized by modified differential evolution for identifying 5-DOF robot manipulator dynamic system
- 192 Downloads
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.
KeywordsDifferential evolution Back-propagation Nonlinear system identification Robot manipulator
This paper was completely supported by the National Foundation for Science and Technology Development (NAFOSTED), under Grant Number 107.01-2015.23, Viet Nam and the DCSELAB, VNU-HCM, Viet Nam.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
- Das H, Jena AK, Nayak J, Naik B, Behera H (2015) A novel pso based back propagation learning-mlp (pso-bp-mlp) for classification. Computational intelligence in data mining, vol 2. Springer, Berlin, pp 461–471Google Scholar
- Diaconescu E (2008) The use of narx neural networks to predict chaotic time series. Wseas Trans Comput Res 3(3):182–191Google Scholar
- Gämperle R, Müller SD, Koumoutsakos P (2002) A parameter study for differential evolution. Adv Intel Syst Fuzzy Syst Evol Comput 10:293–298Google Scholar
- Gaspar CRM, Velázquez-Velázquez JE, Rodríguez JCT, (2015) Identification of a cylindrical robot using recurrent neural networks. Multibody mechatronic systems, pp 381–389. Springer, BerlinGoogle Scholar
- Hovland G, Berglund E, Hanssen S, AB AR (2001) Identification of coupled elastic dynamics using inverse eigenvalue theory. In: International symposium on robotics, vol 19, p 21Google Scholar
- Karaboga N, Cetinkaya B, (2005) Performance comparison of genetic and differential evolution algorithms for digital fir filter design. Advances in information systems, pp 482–488. Springer, BerlinGoogle Scholar
- Pham MT, Gautier M, Poignet P (2001) Identification of joint stiffness with bandpass filtering. In: Robotics and automation, IEEE international conference on, vol 3, IEEE (2001), pp 2867–2872Google Scholar
- Ronkkonen J, Kukkonen S, Price KV (2005) Real-parameter optimization with differential evolution. Proc IEEE CEC 1:506–513Google Scholar
- Sarangi PP, Sahu A, Panda M (2013) A hybrid differential evolution and back-propagation algorithm for feedforward neural network training. Int J Comput Appl 84(14):1–9Google Scholar
- Vesterstrøm J, Thomsen R (2004) A comparative study of differential evolution, particle swarm optimization, and evolutionary algorithms on numerical benchmark problems. In: Evolutionary computation, congress on, vol 2, IEEE, pp 1980–1987Google Scholar