SLeNN-ELM: A shifted Legendre neural network method for fractional delay differential equations based on extreme learning machine

Yinlin Ye; Yajing Li; Hongtao Fan; Xinyi Liu; Hongbing Zhang; Yinlin Ye; Yajing Li; Hongtao Fan; Xinyi Liu; Hongbing Zhang

doi:10.3934/nhm.2023020

Networks and Heterogeneous Media

2023, Volume 18, Issue 1: 494-512. doi: 10.3934/nhm.2023020

Previous Article Next Article

Research article Special Issues

SLeNN-ELM: A shifted Legendre neural network method for fractional delay differential equations based on extreme learning machine

College of Science, Northwest A & F University, Yangling, Shaanxi 712100, China

Received: 15 November 2022 Revised: 25 December 2022 Accepted: 26 December 2022 Published: 16 January 2023

In this paper, we introduce a shifted Legendre neural network method based on an extreme learning machine algorithm (SLeNN-ELM) to solve fractional differential equations with constant and proportional delays. Based on the properties of Caputo fractional derivatives and shifted Legendre polynomials, the fractional derivatives of SLeNN can be represented analytically without other numerical techniques. SLeNN, in terms of neural network architecture, uses a function expansion block to replace the hidden layer, and thus improving the computational efficiency by reducing parameters. In terms of solving technology of neural networks, the extreme learning machine algorithm is used to replace the traditional gradient-based training algorithm. It dramatically improves our solution efficiency. In addition, the proposed method does not require parameter initialization randomly, making the neural network solution stable. Finally, three examples with constant delays and three examples with proportional delays are given, and the effectiveness and superiority of the proposed method are verified by comparison with other numerical methods.
Citation: Yinlin Ye, Yajing Li, Hongtao Fan, Xinyi Liu, Hongbing Zhang. SLeNN-ELM: A shifted Legendre neural network method for fractional delay differential equations based on extreme learning machine[J]. Networks and Heterogeneous Media, 2023, 18(1): 494-512. doi: 10.3934/nhm.2023020

Related Papers:

Abstract

In this paper, we introduce a shifted Legendre neural network method based on an extreme learning machine algorithm (SLeNN-ELM) to solve fractional differential equations with constant and proportional delays. Based on the properties of Caputo fractional derivatives and shifted Legendre polynomials, the fractional derivatives of SLeNN can be represented analytically without other numerical techniques. SLeNN, in terms of neural network architecture, uses a function expansion block to replace the hidden layer, and thus improving the computational efficiency by reducing parameters. In terms of solving technology of neural networks, the extreme learning machine algorithm is used to replace the traditional gradient-based training algorithm. It dramatically improves our solution efficiency. In addition, the proposed method does not require parameter initialization randomly, making the neural network solution stable. Finally, three examples with constant delays and three examples with proportional delays are given, and the effectiveness and superiority of the proposed method are verified by comparison with other numerical methods.

References

[1]	C. T. Baker, C. A. Paul, D. R. Willé, Issues in the numerical solution of evolutionary delay differential equations, Adv. Comput. Math, 3 (1995), 171–196. https://doi.org/10.1007/BF02988625 doi: 10.1007/BF02988625
[2]	R. D. Driver, Ordinary and delay differential equations, New York: Springer, 2012.
[3]	Y. Kuang, Delay Differential Equations with Applications in Population Dynamics, New York: Academic Press, 1993.
[4]	J. N. Luo, W. H. Tian, S. M. Zhong, K. B. Shi, X. M. Gu, W. Q. Wang, Improved delay-probability-dependent results for stochastic neural networks with randomly occurring uncertainties and multiple delays, Int. J. Syst. Sci., 49 (2018), 2039–2059. https://doi.org/10.1080/00207721.2018.1483044 doi: 10.1080/00207721.2018.1483044
[5]	H. Singh, A new numerical algorithm for fractional model of Bloch equation in nuclear magnetic resonance, Alex. Eng. J., 55 (2016), 2863–2869. https://doi.org/10.1016/j.aej.2016.06.032 doi: 10.1016/j.aej.2016.06.032
[6]	H. Singh, Numerical simulation for fractional delay differential equations, Int. J. Dyn. Control, 9 (2021), 463–474. https://doi.org/10.1007/s40435-020-00671-6 doi: 10.1007/s40435-020-00671-6
[7]	J. R. Ockendon, A. B. Tayler, The dynamics of a current collection system for an electric locomotive, Proc. R. Soc. Lond. Ser. A, 322 (1971), 447–468. https://doi.org/10.1098/rspa.1971.0078 doi: 10.1098/rspa.1971.0078
[8]	V. Kolmanovskii, A. Myshkis, Introduction to the Theory and Applications of Functional Differential Equations, Berlin: Springer Science & Business Media, 1999.
[9]	U. Farooq, H. Khan, D. Baleanu, M. Arif, Numerical solutions of fractional delay differential equations using Chebyshev wavelet method, J. Comput. Appl. Math., 38 (2019), 1–13. https://doi.org/10.1007/s40314-019-0953-y doi: 10.1007/s40314-019-0953-y
[10]	M. L. Morgado, N. J. Ford, P. M. Lima, Analysis and numerical methods for fractional differential equations with delay, J. Comput. Appl. Math., 252 (2013), 159–168. https://doi.org/10.1016/j.cam.2012.06.034 doi: 10.1016/j.cam.2012.06.034
[11]	S. Bhalekar, S. Daftardar-Gejji, A predictor-corrector scheme for solving nonlinear delay differential equations of fractional order, J. Fract. Calc. Appl., 1 (2011), 1–9.
[12]	W. Wang, Y. Zhang, S. Li, Stability of continuous Runge-Kutta-type methods for nonlinear neutral delay-differential equations, Appl. Math. Model., 33 (2009), 3319–3329. https://doi.org/10.1016/j.apm.2008.10.038 doi: 10.1016/j.apm.2008.10.038
[13]	B. P. Moghaddam, Z. S. Mostaghim, A numerical method based on finite difference for solving fractional delay differential equations, J. Taibah Univ. Sci., 7 (2013), 120–127. https://doi.org/10.1016/j.jtusci.2013.07.002 doi: 10.1016/j.jtusci.2013.07.002
[14]	P. Rahimkhani, Y. Ordokhani, E. Babolian, A new operational matrix based on Bernoulli wavelets for solving fractional delay differential equations, Numer. Algorithms, 74 (2017), 223–245. https://doi.org/10.1007/s11075-016-0146-3 doi: 10.1007/s11075-016-0146-3
[15]	R. K. Pandey, N. Kumar, R. Mohaptra, An approximate method for solving fractional delay differential equations, Int. J. Appl. Comput. Math., 3 (2017), 1395–1405. https://doi.org/10.1007/s40819-016-0186-3 doi: 10.1007/s40819-016-0186-3
[16]	U. Saeed, M. Rehman, M. A. Iqbal, Modified Chebyshev wavelet methods for fractional delay-type equations, Appl. Math. Comput., 264 (2015), 431–442. https://doi.org/10.1016/j.amc.2015.04.113 doi: 10.1016/j.amc.2015.04.113
[17]	S. Panghal, M. Kumar, Optimization free neural network approach for solving ordinary and partial differential equations, Eng. Comput., 37 (2021), 2989–3002. https://doi.org/10.1007/s00366-020-00985-1 doi: 10.1007/s00366-020-00985-1
[18]	A. Jafarian, M. Mokhtarpour, D. Baleanu, Artificial neural network approach for a class of fractional ordinary differential equation, Neural Comput. Appl., 28 (2017), 765–773. https://doi.org/10.1007/s00521-015-2104-8 doi: 10.1007/s00521-015-2104-8
[19]	I. E. Lagaris, A. Likas, D. I. Fotiadis, Artificial neural networks for solving ordinary and partial differential equations, IEEE Trans. Neural Netw., 9 (1998), 987–1000. https://doi.org/10.1109/72.712178 doi: 10.1109/72.712178
[20]	A. Jafarian, S. M. Nia, A. K. Golmankhaneh, D. Baleanu, On artificial neural networks approach with new cost functions, Appl. Math. Comput., 339 (2018), 546–555. https://doi.org/10.1016/j.amc.2018.07.053 doi: 10.1016/j.amc.2018.07.053
[21]	C. C. Hou, T. E. Simos, I. T. Famelis, Neural network solution of pantograph type differential equations, Math. Method. Appl. Sci., 43 (2020), 3369–3374. https://doi.org/10.1002/mma.6126 doi: 10.1002/mma.6126
[22]	B. Shiri, H. Kong, G. C. Wu, C. Luo, Adaptive learning neural network method for solving time-fractional diffusion equations, Neural Comput., 34 (2022), 971–990. https://doi.org/10.1162/neco_a_01482 doi: 10.1162/neco_a_01482
[23]	Y. Ye, H. Fan, Y. Li, X. Liu, H. Zhang, Deep neural network methods for solving forward and inverse problems of time fractional diffusion equations with conformable derivative, Neurocomputing, 509 (2022), 177–192. https://doi.org/10.1016/j.neucom.2022.08.030 doi: 10.1016/j.neucom.2022.08.030
[24]	C. D. Huang, H. Liu, X. Y. Shi, X. P. Chen, M. Xiao, Z. X. Wang, et al., Bifurcations in a fractional-order neural network with multiple leakage delays, Neural Netw., 131 (2020), 115–126. https://doi.org/10.1016/j.neunet.2020.07.015 doi: 10.1016/j.neunet.2020.07.015
[25]	C. J. Xu, D. Mu, Z. X. Liu, Y. C. Pang, M. X. Liao, P. L. Li, et al., Comparative exploration on bifurcation behavior for integer-order and fractional-order delayed BAM neural networks, NONLINEAR ANAL-MODEL, 27 (2022), 1030–1053. https://doi.org/10.15388/namc.2022.27.28491 doi: 10.15388/namc.2022.27.28491
[26]	C. J. Xu, Z. X. Liu, C. Aouiti, P. L. Li, L. Y. Yao, J. L. Yan, New exploration on bifurcation for fractional-order quaternionvalued neural networks involving leakage delays, Cogn. Neurodyn., 16 (2020), 1233–1248. https://doi.org/10.1007/s11571-021-09763-1 doi: 10.1007/s11571-021-09763-1
[27]	B. Yuttanan, M. Razzaghi, T. N. Vo, Legendre wavelet method for fractional delay differential equations, Appl. Numer. Math., 168 (2021), 127–142. https://doi.org/10.1016/j.apnum.2021.05.024 doi: 10.1016/j.apnum.2021.05.024
[28]	H. Marzban, M. Razzaghi, Hybrid functions approach for linearly constrained quadratic optimal control problems, Appl. Math. Model., 27 (2003), 471–485. https://doi.org/10.1016/S0307-904X(03)00050-7 doi: 10.1016/S0307-904X(03)00050-7
[29]	S. S. Yang, C. S. Tseng, An orthogonal neural network for function approximation, IEEE Trans. Syst. Man Cybern., 26 (1996), 779–785. https://doi.org/10.1109/3477.537319 doi: 10.1109/3477.537319
[30]	A. Saadatmandi, M. Dehghan, A new operational matrix for solving fractional-order differential equations, Comput. Math. Appl., 59 (2010), 1326–1336. https://doi.org/10.1016/j.camwa.2009.07.006 doi: 10.1016/j.camwa.2009.07.006
[31]	H. D. Qu, Z. H. She, X. Liu, Neural network method for solving fractional diffusion equations, Appl. Math. Comput., 391 (2021), 125635. https://doi.org/10.1016/j.amc.2020.125635 doi: 10.1016/j.amc.2020.125635
[32]	H. D. Qu, X. Liu, X. Lu, M. ur Rahman, Z. H. She, Neural network method for solving nonlinear fractional advection-diffusion equation with spatiotemporal variable-order, Chaos Solitons Fractals, 156 (2022), 111856. https://doi.org/10.1016/j.chaos.2022.111856 doi: 10.1016/j.chaos.2022.111856
[33]	J. C. Patra, P. K. Meher, G. Chakraborty, Nonlinear channel equalization for wireless communication systems using Legendre neural networks, Signal Process, 89 (2009), 2251–2262. https://doi.org/10.1016/j.sigpro.2009.05.004 doi: 10.1016/j.sigpro.2009.05.004
[34]	J. C. Patra, C. Bornand, Nonlinear dynamic system identification using Legendre Neural Network, The 2010 international joint conference on neural networks (IJCNN), (2010). https://doi.org/10.1109/IJCNN.2010.5596904 doi: 10.1109/IJCNN.2010.5596904
[35]	G. B. Huang, Q. Zhu, C. K. Siew, Extreme learning machine: theory and applications, Neurocomputing, 70 (2006), 489–501. https://doi.org/10.1016/j.neucom.2005.12.126 doi: 10.1016/j.neucom.2005.12.126
[36]	A. A. Kilbsa, H. M. Srivastava, J. J. Trujillo, Theory and Applications of Fractional Differential Equations, New York: Elsevier, 2006.
[37]	J. Shen, T. Tang, L. L. Wang, Spectral Methods: Algorithms, Analysis and Applications, Berlin: Springer, 2011.
[38]	M. S. Heris, M. Javidi, On fractional backward differential formulas for fractional delay differential equations with periodic and anti-periodic conditions, Appl. Numer. Math., 118 (2017), 203–220. https://doi.org/10.1016/j.apnum.2017.03.006 doi: 10.1016/j.apnum.2017.03.006
[39]	X. Chen, L. Wang, The variational iteration method for solving a neutral functional-differential equation with proportional delays, Comput. Math. Appl., 59 (2010), 2696–2702. https://doi.org/10.1016/j.camwa.2010.01.037 doi: 10.1016/j.camwa.2010.01.037
[40]	A. Bellen, M. Zennaro, Numerical Methods for Delay Differential Equations, Oxford: Oxford University Press, 2013.
[41]	M. A. Iqbal, A. Ali, S. T. Mohyud-Din, Chebyshev wavelets method for fractional delay differential equations, Int. J. Mod. Appl. Phys., 4 (2013), 49–61.
[42]	M. A. Iqbal, U. Saeed, S. T. Mohyud-Din, Modified Laguerre wavelets method for delay differential equation of fractional-order, Egypt. J. Bas. Appl. Sci., 2 (2015), 50–54. https://doi.org/10.1016/j.ejbas.2014.10.004 doi: 10.1016/j.ejbas.2014.10.004
[43]	M. Dehghan, S. A. Yousefi, A. Lotfi, The use of He's variational iteration method for solving the telegraph and fractional telegraph equations, Int. J. Numer. Methods Biomed. Eng., 27 (2011), 219–231. https://doi.org/10.1002/cnm.1293 doi: 10.1002/cnm.1293
[44]	M. Ghasemi, M. Fardi, R. K. Ghaziani, Numerical solution of nonlinear delay differential equations of fractional order in reproducing kernel Hilbert space, Appl. Math. Comput., 268 (2015), 815–831. https://doi.org/10.1016/j.amc.2015.06.012 doi: 10.1016/j.amc.2015.06.012
[45]	J. L. Wei, G. C. Wu, B. Q. Liu, Z. G. Zhao, New semi-analytical solutions of the time-fractional Fokker-Planck equation by the neural network method, Optik, 259 (2022), 168896. https://doi.org/10.1016/j.ijleo.2022.168896 doi: 10.1016/j.ijleo.2022.168896

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)