Purpose
The purpose of this paper is to study the application of entropy based optimized fuzzy logic control for a real-time non-linear system. Optimization of the fuzzy membership function (MF) is one of the most explored areas for performance improvement of the fuzzy logic controllers (FLC). Conversely, majority of previous works are motivated on choosing an optimized shape for the MF, while on the other hand the support of fuzzy set is not accounted.
Design/methodology/approach
The proposed investigation provides the optimal support for predefined MFs by using genetic algorithms-based optimization of fuzzy entropy-based objective function.
Findings
The experimental results obtained indicate an improvement in the performance of the controller which includes improvement in error indices, transient and steady-state parameters. The applicability of proposed algorithm has been verified through real-time control of the twin rotor multiple-input, multiple-output system (TRMS).
Research limitations/implications
The proposed algorithm has been used for the optimization of triangular sets, and can also be used for the optimization of other fussy sets, such as Gaussian, s-function, etc.
Practical implications
The proposed optimization can be combined with other algorithms which optimize the mathematical function (shape), and a potent optimization tool for designing of the FLC can be formulated.
Originality/value
This paper presents the application of a new optimized FLC which is tested for control of pitch and yaw angles in a TRMS. The performance of the proposed optimized FLC shows significant improvement when compared with standard references.
The ability of a neural network to realize some complex nonlinear function makes them attractive for system identification. In the recent past, neural networks trained with back-propagation (BP) learning algorithm have gained attention for the identification of nonlinear dynamic systems. Slower convergence and longer training times are the disadvantages often mentioned when the standard BP algorithm are compared with other competing techniques. In addition, in the standard BP algorithm, the learning rate is fixed and that it is uniform for all weights in a layer. In this paper, we present an improvement to the standard BP algorithm based on the use of an adaptive learning rate and momentum term, where the learning rate is adjusted at each iteration to reduce the training time. Simulation results indicate a faster convergence speed and better error minimization as compared to other competing methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.