Designing the sinc neural networks to solve the fractional optimal control problem

Document Type : Research Article

Authors

• R. Heydari Dastjerdi
• G. Ahmadi

Department of Mathematics, Payame Noor University, Tehran, Iran.

10.22067/ijnao.2024.86494.1380

Abstract

Sinc numerical methods are essential approaches for solving nonlinear problems. In this work, based on this method, the sinc neural networks (SNNs) are designed and applied to solve the fractional optimal control problem (FOCP) in the sense of the Riemann–Liouville (RL) derivative. To solve the FOCP, we first approximate the RL derivative using Grunwald–Letnikov operators. Then, according to Pontryagin’s minimum principle for FOCP and using an error function, we construct an unconstrained minimization problem. We approximate the solution of the ordinary differential equation obtained from the Hamiltonian condition using the SNN. Simulation results show the efficiencies of the proposed approach. 

Keywords

• Sinc numerical method
• Neural network
• Sinc neural network
• Pontryagin’s minimum principle
• Fractional optimal control problem

Main Subjects

• Control and Optimization

---

References

[1] Agrawal, O.M.P. A general formulation and solution scheme for fractional optimal control problem, Nonlinear Dyn. 38 (2004), 323–337.
[2] Agrawal, O.M.P. A formulation and numerical scheme for fractional optimal control problems, J. Vib. Control. 14 (2008), 1291–1299.
[3] Agrawal, O.M.P. and Baleanu, D. A Hamiltonian formulation and a direct numerical scheme for fractional optimal control problems, J. Vib. Control. 13 (2007), 1269–1281.

[4] Ahmad, H., Khan, M., Ahmad, I., Omri, M. and Alotaibi, M. A meshless method for numerical solutions of linear and nonlinear time-fractional Black–Scholes models, AIMS Math. 8 (2023), 19677–19698.
[5] Alquran, M., Sulaiman, T., Yusuf, A., Alshomrani, A. and Baleanu, D. Nonautonomous lump-periodic and analytical solutions to the (3+1)-dimensional generalized Kadomtsev–Petviashvili equation, Nonlinear Dyn. 111 (2023), 11429–11436.
[6] Ashpazzadeh, E., Lakestani, M. and Yildirim, A. Biorthogonal multiwavelets on the interval for solving multidimensional fractional optimal control problems with inequality constraint, Optim. Control Appl. Math. 41(5) (2020), 1477–1494.
[7] Biswas, R.K. and Sen, S. Fractional optimal control problems with specified final time, J. Comput. Nonlinear Dyn. 6(2) (2010), 021009.
[8] Chowdhury, D.R., Chatterjee, M. and Samanta, R.K. An artificial neural network model for neonatal disease diagnosis, International Journal of Artificial Intelligence and Expert Systems (IJAE), 2(3) (2011), 96–106.
[9] Dong, N.P., Long, H. and Khastan, A. Optimal control of a fractional order model for granular SEIR epidemic with uncertainty, Commun. Nonlinear Sci. Numer. Simul. 88 (2020), 105312.
[10] Effati, S. and Pakdaman, M. Optimal control problem via neural networks, Neural Comput. Appl. 23 (2013), 2093–2100.
[11] Elwasif, W. and Fausett, L.V. Function approximation using a sinc neural network, In: Proceedings of the SPIE, Volume 2760 (1996), 690–701.
[12] Ghasemi, S. and Nazemi, A.R. A neural network method based on MittagLeffler function for solving a class of fractional optimal control problems, AUT J. Model. Simul. 50(2) (2018), 211–218.
[13] Ghasemi, S., Nazemi, A. and Hosseinpour, S. Nonlinear fractional optimal control problems with neural network and dynamic optimization schemes, Nonlinear Dyn. 89 (2017), 2669–2682. 

[14] Hashemi, M., Mirzazadeh, M. and Ahmad, H. A reduction technique to solve the (2+1)-dimensional KdV equations with time local fractional derivatives, Opt. Quantum Electron, 55(8) (2023), 721.
[15] Kirk, D.E. Optimal control theory: An introduction, Donver Publication, Inc. Mineola, New York, 2004.
[16] Lagaris, I.E. and Likas, A. Hamilton–Jacobi theory over time scales and applications to linear-quadratic problems, IEEE Trans Neural Netw. 9(5) (2012), 987–1000.
[17] Latif, S., Sabir, Z., Raja, M., Altamirano, G., Núñez, R., Gago, D., Sadat, R. and Ali, M. IoT technology enabled stochastic computing paradigm for numerical simulation of heterogeneous mosquito model, Multimed Tools Appl. 82 (2023), 18851–18866.
[18] Mohammadzadeh, E., Pariz, N., Hosseini sani, S.K. and Jajarmi, A. Optimal Control for a Class of Nonlinear Fractional-Order Systems Using an Extended Modal Series Method and Linear Programming Strategy, J. Control 10(1) (2016), 51–64.
[19] Nazemi, A. and Effati, S. An application of a merit function for solving convex programming problems, Comput. Ind. Eng. 66(2) (2013), 212–221.
[20] Nazemi, A. and Omidi, F. A capable neural network model for solving the maximum flow problem, J. Comput. Appl. Math. 236(14) (2012), 3498–3513.
[21] Nemati, S., Lima, P.M. and Torres, D.F.M. A numerical approach for solving fractional optimal control problems using modified hat functions, Commun. Nonlinear Sci. Numer. Simul. 78 (2019), 104849.
[22] Qayyum, M., Ahmad, E., Tauseef Saeed, S., Ahmad, H. and Askar, S. Homotopy perturbation method-based soliton solutions of the timefractional (2+1)-dimensionalWu–Zhang system describing long dispersive gravity water waves in the ocean, Front Phys. 11 (2023), 1178154.
[23] Saberi Nik, H., Effati, S. and Yildirim, A. Solution of linear optimal control systems by differential transform method, Neural Comput. Appl. 23 (2013), 1311–1317.

[24] Sabir, Z. and Guirao, J. A soft computing scaled conjugate gradient procedure for the fractional order Majnun and Layla romantic story, Mathematics 11 (2023), 835.
[25] Sabouri, J., Effati, S. and Pakdaman, M. A neural network approach for solving a class of fractional optimal control problems,Neural Process. Lett. 45 (2017), 59–74.
[26] Shi, J., Sekar, B.D., Dong, M.C. and Hu, X.Y. Extract knowledge from site-sampled data sets and fused hierarchical neural networks for detecting cardiovascular diseases, 2012 International Conference on Biomedical Engineering and Biotechnology, (2012), 275–279.
[27] Singh, H., Pandey, R.K. and Kumar, D. A reliable numerical approach for nonlinear fractional optimal control problems, Int. J. Nonlinear Sci. Numer. Simul. 22(5) (2021), 495–507.
[28] Souayeh, B. and Sabir, Z. Designing Hyperbolic Tangent Sigmoid Function for Solving theWilliamson Nanofluid Model, Fractal Fract. 7 (2023), 350.
[29] Stenger, F. A “Sinc-Galerkin” method of solution of boundary value problems, J. Math. Comp. 33(145) (1979), 85–109.
[30] Stenger, F. Sinc-related methods, Numerical Methods Based on Sinc and Analytic Functions, Springer, New York, 1993.
[31] Stenger, F. Summary of Sinc numerical methods, J. Comput. Appl. Math. 121 (2000), 379–420.
[32] Sugihara, M. Optimality of the double exponential formula–functional analysis approach–, Numer. Math. (Heidelb.) 75 (1997), 379–395.
[33] Sugihara, M. Near optimality of the sinc approximation, Math. Comput. 72 (2003), 767–786.
[34] Sulaiman, T.A., Yusuf, A., Alshomrani, A.S. and Baleanu, D. Wave solutions to the more general (2+1)-dimensional Boussinesq equation arising in ocean engineering, Int. J. Mod. Phys. 2350214 (2023), 2350214.

[35] Taherpour, V., Nazari, M. and Nemati, A. A new numerical Bernoulli polynomial method for solving fractional optimal control problems with vector components, Comput. Method. Differ. Equ. 9(2) (2021), 446–466.
[36] Vrabie, D. and Lewis, F. Neural network approach to continuous-time direct adaptive optimal control for partially unknown nonlinear systems, Neural Netw. 22(3) (2009), 237–246.
[37] Zarin, R., Khan, M., Khan, A. and Yusuf, A. Deterministic and fractional analysis of a newly developed dengue epidemic model, Waves Random Complex Media, (2023), 1–34.
[38] Zil-E-Huma, Butt, A., Raza, N., Ahmad, H., Ozsahin, D. and Tchier, F. Different solitary wave solutions and bilinear form for modified mixedKDV equation, Optik, 287 (2023), 171031.