An Artificial Neural Network for Solving Distributed Optimal Control of the Poisson’s Equation

Ghasemi, Shojaeddin; Effati, Sohrab

doi:10.1007/s11063-018-9806-8

Cited by 10 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lee et al [43] studied new allocation policies considering buyers' demands in the SC management via an ANN. Furthermore, solving OCP has many approaches such as the homotopy perturbation method, variational iteration, neural network, and numerical approaches [44][45][46][47][48][49]. When an OCP solves with a direct method, we face to a nonlinear optimization problem that can be solved with some heuristic algorithms such as PSO (Particle Swarm Optimization), GA (Genetic Algorithm), BAS (Beetle Antennae Search), and RNN (Recurrent Neural Network) [50][51][52][53][54][55][56][57].…”

Section: Introductionmentioning

confidence: 99%

Neural Network for a Novel Disturbance Optimal Control Model for Inventory and Production Planning in a Four-Echelon Supply Chain with Reverse Logistic

Pooya

Mansoori

Eshaghnezhad

et al. 2021

Neural Process Lett

View full text Add to dashboard Cite

The present paper is devoted to modeling and solving the inventory and production planning in a four-echelon supply chain (SC) with reverse logistics, from supplier to after-sales service center and repair center. To the best of our knowledge, this is the first scientific attempt for modeling and resolving the inventory and production planning in an SC with reverse logistics that the problem is modeled by a disturbance optimal control problem (OCP). Both recycling and reworking are assumed in the reverse logistic. There was a disturbance because we considered the demand time-dependent. From the former points the presented model is so close to the real-world problem in the field of SC. The Pontryagin minimum principle is applied to reformulate the OCP into a system of equations. In continuous, the system of equations is solved by an artificial neural network. In the final step, an example and a case study are presented to depict the performance and validity of the model and the method. KeywordsSupply chain planning • Reverse logistic • Service after sale • Optimal control problem with disturbance • Artificial neural network B Alireza Pooya

show abstract

Section: Introductionmentioning

confidence: 99%

Neural Network for a Novel Disturbance Optimal Control Model for Inventory and Production Planning in a Four-Echelon Supply Chain with Reverse Logistic

Pooya

Mansoori

Eshaghnezhad

et al. 2021

Neural Process Lett

View full text Add to dashboard Cite

show abstract

“…[2][3][4][5] The neural network becomes one of the most important modelbased nonlinear control ways due to its good nonlinear approximation and generalization ability. 6,7 Narendra first introduces the nonlinear autoregressive moving average with feedback linearization (NARMA-L2) controller to nonlinear systems, and the controller is identified by the artificial neural network. 8 The main idea of the NARMA-L2 controller is to extract the control signal from the nonlinear dynamic system by Taylor expansion.…”

Section: Introductionmentioning

confidence: 99%

Iterative learning NARMA-L2 control for turbofan engine with dynamic uncertainty in flight envelope

Li¹,

Yan²,

Tang³

et al. 2021

Proceedings of the Institution of Mechanical Engineers, Part G:

View full text Add to dashboard Cite

Nonlinear control of turbofan engines in the flight envelope has attracted much attention in consideration of the inherent nonlinearity of the engine dynamics. Most nonlinear control design techniques rely on the correction theory of reference model parameter to extend the typical flight operations from ground operation. However, dynamic uncertainties in flight envelope lead to the deviation of operating state, and it is negative to control performance. This article is to develop online correction neural network–based speed control approaches for the turbofan engine with dynamic uncertainty in the flight envelope. Two improved online correction nonlinear ways combined with nonlinear autoregressive moving average (NARMA) are proposed, such as gradient search nonlinear autoregressive moving average with feedback linearization (NARMA-L2) control and iterative learning NARMA-L2 control. The contribution of this article is to provide better control quality of fast regulation and less steady errors of engine speed by the proposed methodology in comparison to the conventional NARMA-L2 control. Some important results are reached on both turbofan engine controller design and dynamic uncertainty tolerance at the typical flight operations, and the numerical examples demonstrate the superiority of the proposed control in the flight envelope.

show abstract

Legendre Neural Network Method for Several Classes of Singularly Perturbed Differential Equations Based on Mapping and Piecewise Optimization Technology

Liu

Xing

Wang

et al. 2020

Neural Process Lett

View full text Add to dashboard Cite

An Artificial Neural Network for Solving Distributed Optimal Control of the Poisson’s Equation

Cited by 10 publications

References 16 publications

Neural Network for a Novel Disturbance Optimal Control Model for Inventory and Production Planning in a Four-Echelon Supply Chain with Reverse Logistic

Neural Network for a Novel Disturbance Optimal Control Model for Inventory and Production Planning in a Four-Echelon Supply Chain with Reverse Logistic

Iterative learning NARMA-L2 control for turbofan engine with dynamic uncertainty in flight envelope

Legendre Neural Network Method for Several Classes of Singularly Perturbed Differential Equations Based on Mapping and Piecewise Optimization Technology

Contact Info

Product

Resources

About