<![CDATA[One of the central aspects in system identification and prediction is dealing with nonlinearity and uncertainties. This need involves the design of a novel method for achieving high efficiency and effectiveness, which is crucial for several applications. In this paper, a new intelligent control based on a hybrid fuzzy neural network (FNN) combined with a genetic algorithm (GA) is proposed for the prediction and identification of nonlinear systems. Two adaptations are considered in the proposed method: the backpropagation (BP) algorithm and the genetic algorithm method to correct various parameters in the neural network. Through adjustment, the proposed method not only achieves error convergence efficiently and quickly but also ensures continuous error reduction while avoiding the limitation of the regional optimal solution. Mackey-Glass differential delay and fuzzy neural system are utilized for system prediction and identification, respectively. Finally, the performance of the proposed method is justified through an application on a nonlinear system. Based on the findings, this paper proposed a hybrid strategy combining BP-GA and FNN where the outcome is greatly influenced by the balance of accuracy and computational efficiency.]]>
Copyrights © 2024
