Adaptive Fuzzy Neural Control for Robotic Arm
DOI:
https://doi.org/10.37628/jvdt.v2i2.1447Abstract
Many systems are nonlinear in real life. Nowadays, neural networks are widely used for control of nonlinear control systems. The most important property of Neural Network is the capability to solve the nonlinear functions to the required accuracy. The other advantages are their adaptive nature and parallel processing capability. In control engineering, objects are mostly undefined, so that Fuzzy control technique will be useful. The adaptive neural fuzzy inference system (ANFIS), a proper blend of neural control and fuzzy logic has achieved remarkable success in nonlinear control systems. Proper combination of both methods extracts the advantages of both techniques, i.e., self-learning nature of neural network and adaptability of fuzzy systems can form a better performance than simple neural network or fuzzy logic.
References
Jung Seul, Kim SS. Hardware implementation of a real time Neural network controller with a DSP and an FPGA for nonlinear systems. IEEE Trans Ind Electron. 2007;54(1, February). pp. 265–71. doi: 10.1109/TIE.2006.888791.
Cho Hyun Cheol, Sami Fadali M. Nonlinear network Induced time Delay systems with stochastic learning. IEEE Trans Control Syst Technol;19(4, July):843–51.
Zhaoxu Yu, Du Hongbin. Adaptive neural control for uncertain stochastic nonlinear strict feedback systems with time varying delays. Elsevier J Neurocomput. 2011, pp. No;73:2072–82.
