Abstract
Applications of neural network algorithms have been grown in recent years and various architectures have been introduced by researchers for the purpose of solving different types of differential equations. Physics informed neural networks, functional link neural networks, and feed-forward differential equation neural networks are some of these architectures. In this paper, we introduce a new neural network for simulating the behavior of Emden–Fowler-type dynamic modeled as an ordinary/partial/system of differential equation, i.e. ODE/PDE/SDE which is based on the development of two introduced functional link neural network and feed-forward differential equation neural network for the partial/system of differential equations. This algorithm uses roots of shifted Chebyshev polynomials as a training data set and the The Levenberg–Marquardt algorithm is taken as an optimizer. To show the applicability of the proposed network, it is applied to some test problems and the obtained results are compared with some other neural network approaches and also, some other numerical algorithms. The reported results showed that the algorithm proposed in this paper is a powerful method for simulating the behavior of partial and system of differential equations and is more accurate than other methods in the literature.
Similar content being viewed by others
References
McCulloch W, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5:115–133
Mall S, Chakraverty S (2014) Chebyshev neural network based model for solving Lane–Emden type equations. Appl Math Comput 247:100–114
Parand K, Roozbahani Z, Babolghani FB (2013) Solving nonlinear Lane–Emden type equations with unsupervised combined artificial neural networks. Int J Ind Math 5:355–366
Lane J (1870) Solving nonlinear Lane–Emden type equations with unsupervised combined artificial neural networks. Am J Sci Arts 2nd Ser 50:57–74
Emden R (1907) Gaskugeln Teubner. Leipzig und Berlin
Wazwaz AM (2001) A new algorithm for solving differential equations of Lane–Emden type. Appl Math Comput 118:287–310
Liao S (2003) A new analytic algorithm of Lane–Emden type equations. Appl Math Comput 142:1–16
Ramos J (2003) Linearization methods in classical and quantum mechanics. Comput Phys Commun 153:199–208
Ramos J (2008) Series approach to the Lane–Emden equation and comparison with the homotopy perturbation method. Chaos Solitons Fractals 38:400–408
Ramos J (2009) Piecewise-adaptive decomposition methods. Chaos Solitons Fractals 40:1623–1636
Bataineh A, Noorani M, Hashim I (2009) Homotopy analysis method for singular ivps of Emden–Fowler type. Commun Nonlinear Sci Numer Simul 14:1121–1131
Chowdhury M, Hashim I (2009) Solutions of Emden–Fowler equations by homotopy perturbation method. Nonlinear Anal Real World Appl 10:104–115
Aslanov A (2008) Determination of convergence intervals of the series solutions of Emden–Fowler equations using polytropes and isothermal spheres. Phys Lett A 372:3555–3561
Agarwala R, O’Regan D (2007) Second order initial value problems of Lane–Emden type. Appl Math Lett 20:1198–1205
Parand K, Dehghan M, Rezaei A, Ghaderi S (2010) An approximation algorithm for the solution of the nonlinear Lane–Emden type equations arising in astrophysics using Hermite functions collocation method. Comput Phys Commun 181:1096–1108
He JH (2003) Variational approach to the Lane–Emden equation. Appl Math Comput 143:539–541
Ramos JI (2005) Linearization techniques for singular initial-value problems of ordinary differential equations. Appl Math Comput 161:525–542
Yousefi SA (2006) Legendre wavelets method for solving differential equations of Lane–Emden type. Appl Math Comput 181:1417–1422
Dehghan M, Shakeri F (2008) Approximate solution of a differential equation arising in astrophysics using the variational iteration method. New Astron 13:53–59
Chandrasekhar S (1967) Introduction to the study of stellar structure. Dover, New York
Singh R (2018) Analytical approach for computation of exact and analytic approximate solutions to the system of Lane-Emden-Fowler type equations arising in astrophysics. Eur Phys J Plus 133:320
Flockerzi D, Sundmacher K (2011) On coupled Lane–Emden equations arising in dusty fluid models. J Phys Conf Ser 268:012006
Wazwaz AM (2005) Analytical solution for the time-dependent Emden–Fowler type of equations by Adomian decomposition method. Appl Math Comput 166:638–651
Horedt G (1986) Seven-digit tables of Lane–Emden functions. Astrophys Space Sci 126:357–408
Wazwaz A-M, Rach R (2011) Comparison of the Adomian decomposition method and the variational iteration method for solving the Lane-Emden equations of the first and second kinds. Kybernetes 40:1305–1318
Wazwaz AM, Rach R, Duan JS (2013) Adomian decomposition method for solving the Volterra integral form of the Lane–Emden equations with initial values and boundary conditions. Appl Math Comput 219:5004–5019
Wazwaz A-M (2014) The variational iteration method for solving the Volterra integro-differential forms of the Lane–Emden equations of the first and the second kind. J Math Chem 52:613–626
Wazwaz A-M, Khuri SA (2015) The variational iteration method for solving the Volterra integro-differential forms of the Lane–Emden and the Emden-Fowler problems with initial and boundary value conditions. Open Eng 5:31–41
Yuzbasi S, Sezer M (2011) A collocation approach to solve a class of Lane–Emden type equations. J Adv Res Appl Math 2:58–73
Yüzbaşı Ş (2011) A numerical approach for solving a class of the nonlinear Lane–Emden type equations arising in astrophysics. Math Methods Appl Sci 34:2218–2230
Yüzbaşı Ş, Sezer M (2013) An improved bessel collocation method with a residual error function to solve a class of Lane–Emden differential equations. Math Comput Model 57:1298–1311
Boyd JP (2011) Chebyshev spectral methods and the Lane–Emden problem. Numer Math Theory Methods Appl 4:142–157
Calvert V, Mashayekhi S, Razzaghi M (2015) Solution of Lane–Emden type equations using rational Bernoulli functions. Math Method Appl Sci 39:1268–1284
Marzban H, Tabrizidooz H, Razzaghi M (2008) Hybrid functions for nonlinear initial-value problems with applications to Lane–Emden type equations. Phys Lett A 372:5883–5886
Parand K, Pirkhedri A (2010) Sinc-collocation method for solving astrophysics equations. New Astron 15:533–537
Lakestani M, Dehghan M (2013) Four techniques based on the B-spline expansion and the collocation approach for the numerical solution of the Lane-Emden equation. Math Methods Appl Sci 36:2243–2253
Gürbüz B, Sezer M (2014) Laguerre polynomial approach for solving Lane–Emden type functional differential equations. Appl Math Comput 242:255–264
Bhrawy A, Alofi A (2012) A Jacobi–Gauss collocation method for solving nonlinear Lane–Emden type equations. Commun Nonlinear Sci Numer Simul 17:62–70
Singh R, Garg H, Guleria V (2019) Haar wavelet collocation method for Lane–Emden equations with Dirichlet, Neumann and Neumann-Robin boundary conditions. J Comput Appl Math 346:150–161
Parand K, Hashemi S (2016) RBF-DQ method for solving non-linear differential equations of Lane–Emden type. Ain Shams Eng J 9:615–629
Parand K, Hemami M (2017) Numerical study of astrophysics equations by meshless collocation method based on compactly supported radial basis function. Int J Appl Comput Math 3(2):1053–1075
Mall S, Chakraverty S (2015) Numerical solution of nonlinear singular initial value problems of Emden–Fowler type using Chebyshev neural network method. Neurocomputing 149:975–982
Ahmad I, Raja MAZ, Bilal M, Ashraf F (2017) Neural network methods to solve the Lane–Emden type equations arising in thermodynamic studies of the spherical gas cloud model. Neural Comput Appl 28:929–944
Ahmad I, Raja MAZ, Bilal M, Ashraf F (2016) Bio-inspired computational heuristics to study Lane–Emden systems arising in astrophysics model. SpringerPlus 5:1866
Roul P, Madduri H, Agarwal R (2019) A fast-converging recursive approach for Lane–Emden type initial value problems arising in astrophysics. J Comput Appl Math 359:182–195
Singh H, Srivastava H, Kumar D (2018) A reliable algorithm for the approximate solution of the nonlinear Lane–Emden type equations arising in astrophysics. Numer Meth PDE 34:1524–1555
Elgindy KT, Refat HM (2018) High-order shifted Gegenbauer integral pseudo-spectral method for solving differential equations of Lane-Emden type. Appl Numer Math 128:98–124
Verma AK, Kayenat S (2018) On the convergence of Mickens’ type nonstandard finite difference schemes on Lane–Emden type equations. J Math Chem 56:1667–1706
Singh R, Singh S, Wazwaz AM (2016) A modified homotopy perturbation method for singular time dependent Emden–Fowler equations with boundary conditions. J Math Chem 54:918–931
Singh R, Wazwaz AM (2016) Numerical solution of the time dependent Emden–Fowler equations with boundary conditions using modified decomposition method. Appl Math Inf Sci 10:403–408
Chowdhury MSH, Hashim I (2007) Solutions of time-dependent Emden–Fowler type equations by homotopy-perturbation method. Phys Lett A 368:305–313
Ucar MF (2018) Finite element method for the solution of a time-dependent heat-like Lane–Emden equation. Univers J Math Appl 1:258–261
Wazwaz AM (2013) A reliable iterative method for solving the time-dependent singular Emden–Fowler equations. Cent Eur J Eng 3:99–105
Lee H, Kang IS (1990) Neural algorithm for solving differential equations. J Comput Phys 91:110–131
Meade AJ Jr, Fernandez AA (1994) The numerical solution of linear ordinary differential equations by feedforward neural networks. Math Comput Model 19:1–25
Meade AJ Jr, Fernandez AA (1994) Solution of nonlinear ordinary differential equations by feedforward neural networks. Math Comput Model 20:19–44
Lagaris IE, Likas A, Fotiadis DI (1998) Artificial neural networks for solving ordinary and partial differential equations. IEEE Trans Neural Netw 9:987–1000
Mai-Duy N, Tran-Cong T (2001) Numerical solution of differential equations using multiquadric radial basis function networks. Neural Netw 14:185–199
Jianyu L, Siwei L, Yingjian Q, Yaping H (2003) Numerical solution of elliptic partial differential equation using radial basis function neural networks. Neural Netw 16:729–734
Effati S, Pakdaman M (2010) Artificial neural network approach for solving fuzzy differential equations. Inf Sci 180:1434–1457
Asari SS, Amirfakhrian M, Chakraverty S (2019) Application of radial basis functions in solving fuzzy integral equations. Neural Comput Appl 31:6373–6381
Golbabai A, Seifollahi S (2006) Numerical solution of the second kind integral equations using radial basis function networks. Appl Math Comput 174:877–883
Golbabai A, Mammadov M, Seifollahi S (2009) Solving a system of nonlinear integral equations by an RBF network. Comput Math Appl 57:1651–1658
Raja MAZ, Samar R, Manzar MA, Shah SM (2017) Design of unsupervised fractional neural network model optimized with interior point algorithm for solving Bagley-Torvik equation. Math Comput Simul 132:139–158
Raja MAZ, Manzar MA, Samar R (2015) An efficient computational intelligence approach for solving fractional order Riccati equations using ANN and SQP. Appl Math Model 39:3075–3093
Raja MAZ, Khan JA, Qureshi IM (2011) Solution of fractional order system of Bagley–Torvik equation using evolutionary computational intelligence. Math Probl Eng 2011:1–18
Ahmad I, Bilal M, Anwar N et al (2017) Stochastic numerical treatment for solving Falkner–Skan equations using feedforward neural networks. Neural Comput Appl 28:1131–1144
Raja MAZ, Azad S, Shah SM (2017) Bio-inspired computational heuristics to study the boundary layer flow of the Falkner-Scan system with mass transfer and wall stretching. Appl Soft Comput 57:293–314
Sabir Z, Manzar MA, Raja MAZ, Sheraz M, Wazwaz AM (2018) Neuro-heuristics for nonlinear singular Thomas–Fermi systems. Appl Soft Comput 65:152–169
Raja MAZ, Zameer A, Khan AU, Wazwaz AM (2016) A new numerical approach to solve Thomas-Fermi model of an atom using bio-inspired heuristics integrated with sequential quadratic programming. SpringerPlus 5:1400
Mall S, Chakraverty S (2016) Hermite functional link neural network for solving the Van der Pol-duffing oscillator equation. Neural Comput 28:1574–1598
Ozer S, Chen CH, Cirpan HA (2011) A set of new Chebyshev Kernel functions for support vector machine pattern classification. Pattern Recognit 44:1435–1447
Padierna LC, Carpio M, Rojas-Domínguez A, Puga H, Fraire H (2018) A novel formulation of orthogonal polynomial kernel functions for SVM classifiers: the Gegenbauer family. Pattern Recognit 84:211–225
Parodi M, Gómez JC (2014) Legendre polynomials based feature extraction for online signature verification. Consistency analysis of feature combinations. Pattern Recognit 47:128–140
Benouini R, Batioua I, Zenkouar K, Zahi A, Najah S, Qjidaa H (2019) Fractional-order orthogonal Chebyshev moments and moment invariants for image representation and pattern recognition. Pattern Recognit 86:332–343
Benouini R, Batioua I, Zenkouar K, Mrabti F et al (2019) New set of generalized Legendre moment invariants for pattern recognition. Pattern Recognit Lett 123:39–46
Mason JC, Handscomb DC (2002) Chebyshev polynomials. CRC Press, Cambridge
Shen J, Tang T (2006) Spectral and high-order methods with applications. Science Press of China, Beijing
Shen J, Tang T, Wang L (2011) Spectral methods algorithms, analyses and applications. Springer, Berlin
Bhrawy A, Zaky M (2016) Shifted fractional-order Jacobi orthogonal functions: application to a system of fractional differential equations. Appl Math Model 40(2):832–845
Hadian Rasanan AH, Bajalan N, Parand K, Rad JA (2020) Simulation of nonlinear fractional dynamics arising in the modeling of cognitive decision making using a new fractional neural network. Math Methods Appl Sci 43(3):1437–1466
Hadian-Rasanan AH, Rahmati D, Gorgin S, Parand K (2020) A single layer fractional orthogonal neural network for solving various types of Lane–Emden equation. New Astron 75:101307
Levenberg K (1944) A method for the solution of certain non-linear problems in least squares. Q Appl Math 2:164–168
Marquardt DW (1963) An algorithm for least-squares estimation of nonlinear parameters. J. Soc Ind Appl Math 11:431–441
Luo X-L, Liao L-Z, Wah Tam H (2007) Convergence analysis of the Levenberg–Marquardt method. Optim Methods Soft 22:659–678
Subudhi B, Jena D (2008) Differential evolution and Levenberg Marquardt trained neural network scheme for nonlinear system identification. Neural Process Lett 27:285–296
Wilamowski BM, Yu H (2010) Improved computation for Levenberg–Marquardt training. IEEE Trans Neural Netw 21:930–937
Parand K, Yousefi H, Delkhosh M (2016) A numerical approach to solve Lene–Emden-type equations by the fractional order of rational Bernoulli functions. Rom J Phys 62:1–24
Seidov Z (2004) Lane–Emden equation: perturbation method, arXiv preprint. arXiv:astro-ph/0402130
Horedt GP (2004) Polytropes: applications in astrophysics and related fields. Kluwer Academic Publishers, New York
El-Gamel M, El-bashbashy W, El-Shenawy A (2014) Numerical solutions for the time-dependent Emden–Fowler-type equations by B-spline method. Appl Math 5(4):593–600
Acknowledgements
The corresponding author’s work as well as the work of the third author was supported by a grant from IPM (Grant number: 3-1399-18), and also by the Center of Excellence in Cognitive Neuropsychology (CECN). They sincerely thank IPM and CECN for their supports.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Omidi, M., Arab, B., Rasanan, A.H.H. et al. Learning nonlinear dynamics with behavior ordinary/partial/system of the differential equations: looking through the lens of orthogonal neural networks. Engineering with Computers 38 (Suppl 2), 1635–1654 (2022). https://doi.org/10.1007/s00366-021-01297-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00366-021-01297-8