Identification of time-delay chaotic system with outliers: Fuzzy neural networks using hybrid learning algorithm

Abstract

A hybrid learning algorithm is proposed to train fuzzy neural networks (FNNs) for identifying a time-delay chaotic system with outliers. In the proposed algorithm, integrating support vector regression (SVR) and annealing robust timevarying learning algorithm (ARTVLA) to optimize FNNs. In the evolutionary procedure, first, SVR is adopted to determine the number of hidden layer nodes and the initial structure of the FNNs. After initialization, ARTVLA with nonlinear time-varying learning rate is then applied to train FNNs. In ARTVLA, the determination of the learning rate would be an important work for the trade-off between stability and speed of convergence. A computationally efficient optimization method, particle swarm optimization (PSO) method, is adopted to simultaneously find optimal learning rates. Due to the advantages of SVR and ARTVLA (SVR-ARTVLA), the proposed FNNs (SVR-ARTVLAFNNs) have good performance for identifying a time-delay chaotic system: Mackey Glass system with outliers. Simulation results are illustrated the effectiveness and feasibility of the proposed SVR-ARTVLA-FNNs.

Singular value decomposition based learning identification for linear time‐varying systems: From recursion to iteration

“…It is apparent from (12) that P j (k) is a symmetric positive definite matrix. If the input signals are not persistently exciting, however, ( 14) can render P j (k) non-positive definite.…”

“…7 Many identification methods have been proposed for linear time-varying (LTV) systems, including wavelet-based methods, 8,9 fuzzy methods, 10,11 and neural-learning-based methods. [12][13][14][15] This article focuses on two specific methods: recursion and iteration.…”

“…Although time‐invariant models can characterize such systems over short intervals, the time‐varying behavior must be considered for proper modeling and control in cases of fast variations 7 . Many identification methods have been proposed for linear time‐varying (LTV) systems, including wavelet‐based methods, 8,9 fuzzy methods, 10,11 and neural‐learning‐based methods 12‐15 . This article focuses on two specific methods: recursion and iteration.…”

Improved memetic algorithm for nonlinear identification of a three-dimensional elliptical vibration cutting system

“…In MAs, individuals may undergo local improvement before transmitting their genes to their offspring. [28][29][30][31] However, conventional local refinement efficiency is relatively low.…”