Self-organization of a recurrent RBF neural network using an information-oriented algorithm

Han, Honggui; Guo, Yanan; Qiao, Junfei

doi:10.1016/j.neucom.2016.11.010

Cited by 23 publications

(4 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the systemic investigation of the recursive neural network, Lu et al 18 proposed a self-organizing RRBF (SR-RBF) neural network based on the spiking mechanism and the improved Levenberg−Marquardt (LM) algorithm. Han et al 19 constructed a improved RRBF based on an information-oriented algorithm (IOA) to adjust the parameters by a gradient algorithm simultaneously. Qiao et al 20 proposed a structure design method based on the recursive orthogonal least squares (ROLS) algorithm for selfadaptive adjustment of the structure of the RRBF neural network.…”

Section: Related Workmentioning

confidence: 99%

Novel Nonlinear Autoregression with External Input Integrating PCA-WD and Its Application to a Dynamic Soft Sensor

Zhang

Han

Yu³

et al. 2020

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Important process or product quality parameters in chemical plants are difficult to measure with sensors for economic or technical reasons and soft measurement is an important solution to measure these key parameters. Aiming at the strong nonlinearity, low prediction accuracy, frequent dynamic changes, and severe collinear interference in actual chemical production processes, this article proposes a dynamic soft sensor model using novel nonlinear autoregression with external input (NARX) based on principal component analysis (PCA) and wavelet denoising (WD) (PCA-WD-NARX). The feature information of the sample data is extracted by the PCA and the collinearity is eliminated at the same time. Moreover, the noise in the data set is eliminated by WD to simplify the complexity of the learning data. Then, the NARX is used to construct the dynamic soft sensor model. Finally, the recommended model is applied to predict the acetic acid content of a purified terephthalic acid (PTA) plant. Through the evaluation indexes of the root-mean-square error (RMSE) and the coefficient of determination (R 2), the experimental results show that the proposed method has the most outstanding prediction accuracy and generalization ability among the NARX model, the NARX integrating the PCA (PCA-NARX) model, the NARX integrating the WD (WD-NARX) model, the Elman model, and the recursive radial basis function (RRBF).

show abstract

Section: Related Workmentioning

confidence: 99%

Novel Nonlinear Autoregression with External Input Integrating PCA-WD and Its Application to a Dynamic Soft Sensor

Zhang

Han

Yu³

et al. 2020

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…Inspired by the work of Han et al [46], a three-layer Recurrent RBFNN is utilized to estimate the unknown modeling errors, viz. f i , i = 2, 4, .…”

Section: B Three-layer Recurrent Rbfnnmentioning

confidence: 99%

Adaptive Trajectory Tracking Control of a Cable-Driven Underwater Vehicle on a Tension Leg Platform

Xia

et al. 2019

IEEE Access

View full text Add to dashboard Cite

This paper focuses on the dynamic modeling, controller design, and simulation verification of a new cable-driven underwater vehicle model system, which is proposed for future application on a tension leg platform. Compared with conventional underwater vehicles, the proposed cable-driven underwater vehicle model system has a unique structure and subjects to not only unknown underwater disturbances but also time-varying nonlinear cable tractions. To achieve accurate and robust trajectory tracking control, a universal high-order nonlinear dynamic model is established with multisource uncertainties, and an integrated estimation-based adaptive backstepping terminal sliding mode controller is designed. The proposed controller utilizes the integrated estimation method to handle the multisource unknown uncertainties, where recurrent radial basis function neural network and disturbance observer are employed for the estimations of uncertainties, and adaptive robust methods are utilized for compensations of estimation errors. The backstepping terminal sliding mode control method is utilized to improve the tracking performance and converging rate. In addition, the issue of ''explosion of complexity'' occurred in a traditional backstepping design is tackled by an adaptive control method, and the input saturation problem is solved by antiwindup compensator. Based on the Lyapunov analysis, all closed-loop signals are proved to be uniformly ultimately bounded. The numerical simulations show that the developed controller is not only robust against environmental disturbances and adaptive to unknown time-varying uncertainties but also able to steer the trajectory tracking errors along the prescribed transient, thus leading to effective cable-driven underwater vehicle model system control. INDEX TERMS Cable-driven underwater vehicle model system, trajectory tracking control, integrated estimation, adaptive backstepping terminal sliding mode control, input saturation.

show abstract

“…control systems and classification,. The most of the ANNs are based on the feed‐forward networks such as the radial basis function neural network and the multilayer perceptron (MLP) . For instance, Kumar and Yadav applied a radial basis function neural network method with MLPs for the solution of differential equations.…”

Section: Introductionmentioning

confidence: 99%

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

Self-organization of a recurrent RBF neural network using an information-oriented algorithm

Cited by 23 publications

References 56 publications

Novel Nonlinear Autoregression with External Input Integrating PCA-WD and Its Application to a Dynamic Soft Sensor

Novel Nonlinear Autoregression with External Input Integrating PCA-WD and Its Application to a Dynamic Soft Sensor

Adaptive Trajectory Tracking Control of a Cable-Driven Underwater Vehicle on a Tension Leg Platform

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

Contact Info

Product

Resources

About