Functional link artificial neural network filter based on the q-gradient for nonlinear active noise control

Yin, Kaili; Zhao, Haiquan; Lu, Lu

doi:10.1016/j.jsv.2018.08.015

Cited by 33 publications

(12 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The weight vector of FLANN is expressed by W = [ w 1 , w 2 , … , w n ]. The outputs of FLANN with n nonlinear activation functions can be calculated according to Equation :

\overset{y}{true} = G ((), V W^{T}) .

…”

Section: Methodsmentioning

confidence: 99%

“…For the PSO‐RBFNN model, a structure of a 30‐node hidden layer is adopted, and the weights and thresholds are optimized by PSO, where a population size of 120, maximum number of iterations of 1000, learning factor of 1.5, and inertia weight of 0.5 are used, and the initial position of the particle and the initial velocity is generated randomly. For the FLANN model, a learning parameter of 0.7, number of iterations of 1000, and expected error of 0.001 are used . For the FLPEM model, the iteration termination condition is that the error between the predicted value and the actual value is less than 10 −12 and prediction error criterion J 2 ( ϑ ) is used.…”

Section: Formulation Of Energy Efficiency Optimization Model Of the Ementioning

confidence: 99%

“…The FLANN was initially proposed by Pao et al and can be used to improve the high computational complexity and nonlinearity in a single-layer neural network. 34 There are only two layers in FLANN, input and output layers. Because there is no hidden layer, the training computational complexity of the algorithm is reduced significantly.…”

Section: Functional Link Artificial Neural Networkmentioning

confidence: 99%

“…The outputs of FLANN with n nonlinear activation functions can be calculated according 34 to Equation 1:…”

Section: Functional Link Artificial Neural Networkmentioning

confidence: 99%

“…For the FLANN model, a learning parameter of 0.7, number of iterations of 1000, and expected error of 0.001 are used. 34 For the FLPEM model, the iteration termination condition is that the error between the predicted value and the actual value is less than 10 −12 and prediction error criterion J 2 (ϑ) is used. And an expanded nonlinear function, f (x) = 1/1 + e −x , is used in the FLANN, FLLS, and FLPEM models.…”

Section: Material-product Model Of the Ethylene Production Process mentioning

confidence: 99%

See 4 more Smart Citations

Energy efficiency optimization of ethylene production process with respect to a novel FLPEM‐based material‐product nexus

2019

View full text Add to dashboard Cite

Summary Energy efficiency optimization and energy management can bring multiple economic benefits for the complicated petrochemical industries. However, the influence of the production scale and materials, and the uncertain data have a direct impact on the production prediction and energy efficiency optimization of ethylene production process, which is ignored by the conventional optimization strategies. To achieve energy management and reduce energy consumption considering the production technology, total energy, and material flows, a multiobjective energy efficiency optimization scheme for the ethylene production process with respect to material‐product nexus is proposed. Specifically, a total‐factor material‐product nexus model of the ethylene production is established by a novel functional link prediction error method–integrated algorithm, providing system‐level material equilibrium constraints for the energy efficiency optimization scheme. Then an optimization model with two mutually complementary energy efficiency indicators is established and implemented by the multiobjective particle swarm optimization integrating functional link prediction error method. The proposed energy efficiency optimization scheme is applied into a practical ethylene plant, and the optimization results demonstrate that energy efficiency of this plant is increased by 10.30%, synthetical energy consumption is decreased by 13.05%, and energy cost is decreased by 10.42%.

show abstract

“…The weight vector of FLANN is expressed by W = [ w 1 , w 2 , … , w n ]. The outputs of FLANN with n nonlinear activation functions can be calculated according to Equation :

\overset{y}{true} = G ((), V W^{T}) .

…”

Section: Methodsmentioning

confidence: 99%

Section: Formulation Of Energy Efficiency Optimization Model Of the Ementioning

confidence: 99%

Section: Functional Link Artificial Neural Networkmentioning

confidence: 99%

“…The outputs of FLANN with n nonlinear activation functions can be calculated according 34 to Equation 1:…”

Section: Functional Link Artificial Neural Networkmentioning

confidence: 99%

Section: Material-product Model Of the Ethylene Production Process mentioning

confidence: 99%

See 3 more Smart Citations

Energy efficiency optimization of ethylene production process with respect to a novel FLPEM‐based material‐product nexus

2019

View full text Add to dashboard Cite

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

FLANN Adaptive Filter

Zhao

Chen

2023

Efficient Nonlinear Adaptive Filters

View full text Add to dashboard Cite

Functional link artificial neural network filter based on the q-gradient for nonlinear active noise control

Cited by 33 publications

References 36 publications

Energy efficiency optimization of ethylene production process with respect to a novel FLPEM‐based material‐product nexus

Energy efficiency optimization of ethylene production process with respect to a novel FLPEM‐based material‐product nexus

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

FLANN Adaptive Filter

Contact Info

Product

Resources

About