Distributed sliding-mode formation control using recurrent interval type 2 fuzzy neural networks for uncertain multi-ballbots

This paper proposes a novel fuzzy modeling approach for identification of dynamic systems. A fuzzy model, recurrent interval type-2 fuzzy neural network (RIT2FNN), is constructed by using a recurrent neural network which recurrent weights, mean and standard deviation of the membership functions are updated. The complete back propagation (BP) algorithm tuning equations used to tune the antecedent and consequent parameters for the interval type-2 fuzzy neural networks (IT2FNNs) are developed to handle the training data corrupted by noise or rule uncertainties for nonlinear system identification involving external disturbances. Only by using the current inputs and most recent outputs of the input layers, the system can be completely identified based on RIT2FNNs. In order to show that the interval IT2FNNs can handle the measurement uncertainties, training data are corrupted by white Gaussian noise with signal-to-noise ratio (SNR) 20 dB. Simulation results are obtained for the identification of nonlinear system, which yield more improved performance than those using recurrent type-1 fuzzy neural networks (RT1FNNs).

Download Full-text

Direct adaptive recurrent interval type 2 fuzzy neural networks control using for a ball robot with a four-motor inverse-mouse ball drive

2013 International Conference on Advanced Robotics and Intelligent Systems ◽

10.1109/aris.2013.6573525 ◽

2013 ◽

Cited By ~ 3

Author(s):

Cheng-Kai Chan ◽

Ching-Chih Tsai

Keyword(s):

Neural Networks ◽

Fuzzy Neural Networks ◽

Fuzzy Neural ◽

Interval Type ◽

Recurrent Interval

Download Full-text

System Identification Based on Dynamical Training for Recurrent Interval Type-2 Fuzzy Neural Network

International Journal of Fuzzy System Applications ◽

10.4018/ijfsa.2011070105 ◽

2011 ◽

Vol 1 (3) ◽

pp. 66-85 ◽

Cited By ~ 5

Author(s):

Tsung-Chih Lin ◽

Yi-Ming Chang ◽

Tun-Yuan Lee

Keyword(s):

Neural Network ◽

Neural Networks ◽

Nonlinear System ◽

Fuzzy Neural Network ◽

Fuzzy Neural Networks ◽

Training Data ◽

Fuzzy Neural ◽

Interval Type ◽

Recurrent Interval

This paper proposes a novel fuzzy modeling approach for identification of dynamic systems. A fuzzy model, recurrent interval type-2 fuzzy neural network (RIT2FNN), is constructed by using a recurrent neural network which recurrent weights, mean and standard deviation of the membership functions are updated. The complete back propagation (BP) algorithm tuning equations used to tune the antecedent and consequent parameters for the interval type-2 fuzzy neural networks (IT2FNNs) are developed to handle the training data corrupted by noise or rule uncertainties for nonlinear system identification involving external disturbances. Only by using the current inputs and most recent outputs of the input layers, the system can be completely identified based on RIT2FNNs. In order to show that the interval IT2FNNs can handle the measurement uncertainties, training data are corrupted by white Gaussian noise with signal-to-noise ratio (SNR) 20 dB. Simulation results are obtained for the identification of nonlinear system, which yield more improved performance than those using recurrent type-1 fuzzy neural networks (RT1FNNs).

Download Full-text

Distributed adaptive dynamic surface formation control for uncertain multiple quadrotor systems with interval type-2 fuzzy neural networks

Transactions of the Institute of Measurement and Control ◽

10.1177/0142331218788115 ◽

2018 ◽

Vol 41 (7) ◽

pp. 1861-1879 ◽

Cited By ~ 4

Author(s):

Teh-Lu Liao ◽

Wei-Shou Chan ◽

Jun-Juh Yan

Keyword(s):

Neural Networks ◽

Formation Control ◽

Control Method ◽

Fuzzy Neural Networks ◽

Consensus Algorithm ◽

Dynamic Surface ◽

Adaptive Dynamic ◽

Fuzzy Neural ◽

Interval Type

This paper presents a distributed adaptive formation control method for uncertain multiple quadrotor systems under a directed graph that characterizes the interaction among the leader and followers. The proposed approach is based on an adaptive dynamic surface control, consensus algorithm and graph theory, where the system uncertainties are approximately modelled by interval type-2 fuzzy neural networks. The adaptive laws of interval type-2 fuzzy neural network parameters are derived from the stability analysis. In this study, the robust stability of the closed-loop system is guaranteed by the Lyapunov theorem, and the leader-follower formation goal can be asymptotically achieved. The developed control scheme is applied to the followers of quadrotor systems for performance evaluations. Simulation results are also provided to compare with the existing methods and reveal the superiority of the proposed adaptive formation controller.

Download Full-text