A comprehensive survey on functional link neural networks and an adaptive PSO–BP learning for CFLNN

Dehuri, Satchidananda; Cho, Sung-Bae

doi:10.1007/s00521-009-0288-5

Cited by 144 publications

(60 citation statements)

References 121 publications

(142 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is shown that the performance of functional-link NN is similar to that of a NN but with faster convergence and lesser computational complexity. Moreover, a comprehensive survey on various applications of functional-link NN has been proposed in [12].…”

Section: Chih-hong Linmentioning

confidence: 99%

Dynamic Response of Novel Adaptive Modified Recurrent Legendre Neural Network Control for PMSM Servo-Drive Electric Scooter

Lin

2015

Automatika

View full text Add to dashboard Cite

Original scientific paperBecause an electric scooter driven by permanent magnet synchronous motor (PMSM) servo-driven system has the unknown nonlinearity and the time-varying characteristics, its accurate dynamic model is difficult to establish for the design of the linear controller in whole system. In order to conquer this difficulty and raise robustness, a novel adaptive modified recurrent Legendre neural network (NN) control system, which has fast convergence and provide high accuracy, is proposed to control for PMSM servo-driven electric scooter under the external disturbances and parameter variations in this study. The novel adaptive modified recurrent Legendre NN control system consists of a modified recurrent Legendre NN control with adaptation law and a remunerated control with estimation law. In addition, the online parameter tuning methodology of the modified recurrent Legendre NN control and the estimation law of the remunerated control can be derived by using the Lyapunov stability theorem and the gradient descent method. Furthermore, the modified recurrent Legendre NN with variable learning rate is proposed to raise convergence speed. Finally, comparative studies are demonstrated by experimental results in order to show the effectiveness of the proposed control scheme.Key words: Permanent magnet synchronous motor, Legendre neural network, Lyapunov stability Dinamički odziv nove adaptivne modificirane povratne Legendrove neuronske mreže upravljanja sinkronim motorom s permanentnim magnetima za električni skuter. S obzirom da električni skuter pogonjen servo sustavom sa sinkroni motor s permanentnim magnetima ima nelinearnu dinamiku i vremenski promjenjive parametre, njegov dinamički model nije jednostavno odrediti u svrhu dizajniranja linearnog regulatora. Kako bi se riješio taj problem te povećala robusnost predložen je sustav upravljanja korištenjem adaptivne modificirane povratne Legendrove neuronske mreže za upravljanje skuterom pogonjenim servo sustavom sa sinkronim motorom uz prisustvo vanjskog poremećaja i promjenjivih parametara. Predloženo upravljanje ima brzu konvergenciju i visoku preciznost. Sustav upravljanja sastoji se od modificirane povratne Legendrove neuronske moreže s adaptivnim zakonom upravljanja i estimacijom. Dodatno, on-line podešavanje parametara takvog sustava može se dobiti korištenjem Ljapunovljevog teorema o stabilnosti sustava i gradijente metode. Modificirana povratne Legendrove neuronska mreža s promjenjivim vremenom učenja predložena je za povećanje brzine konvergencije. Ispravnost predložene sheme upravljanja provjerena je eksperimentalno.Ključne riječi: sinkroni motor s permanentnim magnetima, Legendrova neuronska mreža, stabilnost po Ljaponovu

show abstract

Section: Chih-hong Linmentioning

confidence: 99%

Dynamic Response of Novel Adaptive Modified Recurrent Legendre Neural Network Control for PMSM Servo-Drive Electric Scooter

Lin

2015

Automatika

View full text Add to dashboard Cite

show abstract

“…In most previous researches, the learning algorithm used for training the FLNN is the Backpropagation (BP) [8,16,22,23,[25][26][27]. BP learning is developed by Rumelhart [28] in which the network is provided with examples of the inputs and desired outputs to be computed, and then the error (difference between actual and expected results) will be calculated.…”

Section: Flnn Learning Schemementioning

confidence: 99%

“…Another limitation of BP-learning algorithm inherit by FLNN-BP is that, the network is very dependent on the choices of initial values of the weights set as well as the parameters in the algorithm such as the learning rate and momentum [8] which make it not very easy to meet the desired convergence criterion during the training.…”

Section: Flnn Learning Schemementioning

confidence: 99%

“…FLNN is a class of higher order neural network (HONNs) that utilized higher combination of it inputs [6,7]. FLNN can capture non-linear input-output mapping, provided that, they are fed with an adequate set of functional inputs [8]. Pao [6] pointed out that FLNN may be conveniently used for function approximation and can be extended for pattern recognition with faster convergence rate and lesser computational load.…”

Section: Introductionmentioning

confidence: 99%

“…In the training of FLNN the mostly used algorithm is the Backpropagation (BP) learning algorithm. However, one of the crucial problems with BP-learning algorithm is that it can easily get trapped in local optima [8]. To improve this, the Artificial Bee Colony (ABC) optimization algorithm is proposed in this work to be used to optimize the weight in FLNN instead of the BP-learning algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Functional Link Neural Network – Artificial Bee Colony for Time Series Temperature Prediction

Hassim

Ghazali

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Higher Order Neural Networks (HONNs) have emerged as an important tool for time series prediction and have been successfully applied in many engineering and scientific problems. One of the models in HONNs is a Functional Link Neural Network (FLNN) known to be conveniently used for function approximation and can be extended for pattern recognition with faster convergence rate and lesser computational load compared to ordinary feedforward network like the Multilayer Perceptron (MLP). In training the FLNN, the mostly used algorithm is the Backpropagation (BP) learning algorithm. However, one of the crucial problems with BP learning algorithm is that it can be easily gets trapped on local minima. This paper proposed an alternative learning scheme for the FLNN to be applied on temperature forecasting by using Artificial Bee Colony (ABC) optimization algorithm. The ABC adopted in this work is known to have good exploration and exploitation capabilities in searching optimal weight especially in numerical optimization problems. The result of the prediction made by FLNN-ABC is compared with the original FLNN architecture and toward the end we found that FLNN-ABC gives better result in predicting the next-day ahead prediction.

show abstract

Fractional Chebyshev functional link neural network‐optimization method for solving delay fractional optimal control problems with Atangana‐Baleanu derivative

Kheyrinataj

Nazemi

2020

Optim Control Appl Methods

View full text Add to dashboard Cite

In this article, we propose a higher order neural network, namely the functional link neural network (FLNN), for the model of linear and nonlinear delay fractional optimal control problems (DFOCPs) with mixed control-state constraints. We consider DFOCPs using a new fractional derivative with nonlocal and nonsingular kernel that was recently proposed by Atangana and Baleanu.The derivative possesses more important characteristics that are very useful in modelling. In the proposed method, a fractional Chebyshev FLNN is developed. At the first step, the delay problem is transformed to a nondelay problem, using a Padé approximation. The necessary optimality condition is stated in a form of fractional two-point boundary value problem. By applying the fractional integration by parts and by constructing an error function, we then define an unconstrained minimization problem. In the optimization problem, trial solutions for state, co-state and control functions are utilized where these trial solutions are constructed by using single-layer fractional Chebyshev neural network model. We then minimize the error function using an unconstrained optimization scheme based on the gradient descent algorithm for updating the network parameters (weights and bias) associated with all neurons. To show the effectiveness of the proposed neural network, some numerical results are provided. K E Y W O R D SAtangana-Baleanu derivative, delay fractional optimal control problems, fractional Chebyshev polynomials, functional link neural network, optimization, Padé approximation 1 808 /journal/oca Optim Control Appl Meth. 2020;41:808-832.KHEYRINATAJ and NAZEMI 809 cannot be used in modeling of the complex control systems. To bypass these difficulties, Caputo and Fabrizio proposed a so-called Caputo-Fabrizio derivative based on the exponential kernel 10 instead of the power principle. After that, Atangana and Baleanu (AB) 2 generalized the Caputo-Fabrizio derivative using the Mittag-Leffler function as one of the best candidates among existing kernels which is both nonsingular and nonlocal. The control of systems with time delay and obtaining their approximate solutions are very important issues in control theory. Optimal control problems with delay arise in many important applications in science and engineering. [11][12][13] Some researchers have extended this model to the scope of fractional calculus. From these works, we can mention, Chelyshkov wavelets, 14 Legendre operational method, 15 Müntz-Legendre spectral method 16 , block-pulse function, 17 Bernoulli wavelet 18 , Bernstein polynomials 19 , discretization-based methods, 20,21 and embedding approach. 22 In the above-mentioned works, the functions are approximated locally, using the discretization of domain into the number of finite elements. Despite providing good approximations to the solution of problem, these methods have difficulties. Due to discretization of domain via meshing, these methods need a high computational time when the control problems have high-order dimension. Also, d...

show abstract

A comprehensive survey on functional link neural networks and an adaptive PSO–BP learning for CFLNN

Cited by 144 publications

References 121 publications

Dynamic Response of Novel Adaptive Modified Recurrent Legendre Neural Network Control for PMSM Servo-Drive Electric Scooter

Dynamic Response of Novel Adaptive Modified Recurrent Legendre Neural Network Control for PMSM Servo-Drive Electric Scooter

Functional Link Neural Network – Artificial Bee Colony for Time Series Temperature Prediction

Fractional Chebyshev functional link neural network‐optimization method for solving delay fractional optimal control problems with Atangana‐Baleanu derivative

Contact Info

Product

Resources

About