## Abstract

A novel Jacobi neural network method is proposed for solving linear differential-algebraic equations (DAEs) in the paper. First, Jacobi neural network is applied to derive the approximate solutions form of DAEs, and the loss function is constructed for DAEs based on single hidden layer Jacobi neural network structure. Then, we get the optimal output weights of Jacobi neural network by applying extreme learning machine algorithm. In particular, Legendre neural network method and Chebyshev neural network method which have been widely used by scholars are special cases of Jacobi neural network method, and the numerical results of the proposed method are better than these of Legendre neural network method and Chebyshev neural network method. Furthermore, Jacobi neural network method has higher accuracy compared with the approximate analytical methods, the numerical comparison results further show the feasibility and effectiveness of the proposed method for solving the DAEs.

### Similar content being viewed by others

### Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.## References

Benner P, Losse P, Mehrmann V, Voigt M (2015) Numerical linear algebraic methods for linear differential-algebraic equations. In: Surveys in differential-algebraic Equations III. Springer, Cham, pp 117–175

März R, Tischendorf C (1997) Recent results in solving index-2 differential-algebraic equations in circuit simulation. SIAM J Sci Comput 18(1):139–159

Campbell S, Ilchmann A, Mehrmann et al (2019) Applications of differential-algebraic equations: examples and Benchmarks. Springer, Berlin

Petzold L (1982) Differential-algebraic equations are not ODE’s. SIAM J Sci Statist Comput 3(3):367–384

Gear CW, Petzold LR (1984) ODE methods for the solution of differential-algebraic systems. SIAM J Numer Anal 21(4):716–728

Ren L, Wang YM (2017) Numerical methods for a class of differential-algebraic equations. Math Probl Eng 2017:1–10

Çelik E, Bayram M (2003) On the numerical solution of differential-algebraic equations by Padé series. Appl Math Comput 137(1):151–160

Hosseini MM (2005) Numerical solution of linear differential-algebraic equations. Appl Math and Comput 162(1):7–14

Benhammouda B (2016) A novel technique to solve nonlinear higher-index Hessenberg differential-algebraic equations by Adomian decomposition method. SpringerPlus 5(1):1–14

Çelik E, Bayram M, Yeloglu T (2006) Solution of differential-algebraic equations (DAEs) by Adomian decomposition method. Int J Pure Appl Math Sci 3(1):93–100

Soltanian F, Karbassi SM, Hosseini MM (2009) Application of He’s variational iteration method for solution of differential-algebraic equations. Chaos Solitons Fractals 41(1):436–445

Moaddy K, Al-Smadi M, Hashim I (2015) A novel representation of the exact solution for differential-algebraic equations system using residual power series method. Discrete Dyn Nat Soc. ID:205207

Ayaz F (2004) Applications of differential transform method to differential-algebraic equations. Appl Math Comput 152(3):649–657

Soltanian F, Dehghan M, Karbassi SM (2010) Solution of the differential-algebraic equations via homotopy perturbation method and their engineering applications. Int J Comput Math 87(9):1950–1974

Vanani SK, Soleymani F, Avaji M (2011) Legendre wavelet method for solving differential-algebraic equations. J Appl Sci Res 5(9):2105–2110

Yeganeh S, Saadatmandi A et al (2013) The numerical solution of differential-algebraic equations by sinc-collocation method. Comput Appl Math 32(2):343–354

Bayram M (2016) On the numerical solution of differential-algebraic equations (DAEs) by Laguerre polynomials approximation. J Abstr Comput Math 1:58–68

Sun W (2016) Numerical algorithms for differential-algebraic equations of multibody dynamics. In: 2016 16th international conference on control, automation and systems. IEEE, pp 786–791

Hairer E, Lubich C, Roche M (2006) The numerical solution of differential-algebraic systems by Runge–Kutta methods. Springer, Berlin

Kunkel P, Mehrmann V (2006) Differential-algebraic equations: analysis and numerical solution. Eur Math Soc 2:217–270

Kulikov GY, Shindin SK (1999) A local-global stepsize control for multistep methods applied to semi-explicit index 1 differential-algebraic equations. Korean J Comput Appl Math 6(3):463–492

Bulatov MV, Linh VH, Solovarova LS (2016) On BDF-based multistep schemes for some classes of linear differential-algebraic equations of index at most 2. Acta Math Vietnam 41(4):715–730

Dr\(\breve{a}\)g P, Stycze\(\acute{n}\) K (2013) Inexact Newton method as a tool for solving differential-algebraic systems. In: 2013 federated conference on computer science and information systems. IEEE, pp 639–642

El-Khateb MA, Hussien HS (2009) An optimization method for solving some differential-algebraic equations. Commun Nonlinear Sci Numer Simul 14(5):1970–1977

Particke F, Zhou J, Hiller M, Hofmann C, Thielecke J (2019) Neural network aided potential field approach for pedestrian prediction. In: 2019 Sensor data fusion: trends, solutions, applications. IEEE, pp 1–6

Yuskov IO, Stroganova EP (2020) Application of neural network model design for monitoring wireless communication networks. In: Systems of signals generating and processing in the field of on board communications. IEEE, pp 1–4

Abiodun OI et al (2019) Comprehensive review of artificial neural network applications to pattern recognition. IEEE Access 7:158820–158846

Dua V (2011) An artificial neural network approximation based decomposition approach for parameter estimation of system of ordinary differential equations. Comput Chem Eng 35(3):545–553

Xu LY, Wen H, Zeng ZZ (2007) The algorithm of neural networks on the initial value problems in ordinary differential equations. In: 2007 2nd conference on industrial electronics and applications. IEEE, pp 813–816

Mall S, Chakraverty S (2016) Application of Legendre neural network for solving ordinary differential equations. Appl Soft Comput 43:347–356

Yang YL, Hou MZ, Luo JS (2018) A novel improved extreme learning machine algorithm in solving ordinary differential equations by Legendre neural network methods. Adv Differ Equ 1:469

Lagaris IE, Likas A, Fotiadis DI (1998) Artificial neural networks for solving ordinary and partial differential equations. IEEE Trans Neural Netw 9(5):987–1000

Seddighi Chaharborj S, Mahmoudi Y (2016) Chebyshev neural network model with linear and nonlinear active functions. Int J Basic Appl Sci 5(3):182–187

Gobovic D, Zaghloul ME (1994) Analog cellular neural network with application to partial differential equations with variable mesh-size. In: International symposium on circuits and systems. IEEE 6, pp 359–362

Aein MJ, Talebi HA (2009) Introducing a training methodology for cellular neural networks solving partial differential equations. In: 2009 international joint conference on neural networks. IEEE, pp 71–75

Sun HL, Hou MZ, Yang YL et al (2019) Solving partial differential equation based on Bernstein neural network and extreme learning machine algorithm. Neural Process Lett 50(2):1153–1172

McFall KS (2013) Automated design parameter selection for neural networks solving coupled partial differential equations with discontinuities. J Frankl Inst 350(2):300–317

Rudd K, Ferrari S (2015) A constrained integration (CINT) approach to solving partial differential equations using artificial neural networks. Neurocomputing 155:277–285

Zjavka L, Pedrycz W (2016) Constructing general partial differential equations using polynomial and neural networks. Neural Netw 73:58–69

Mall S, Chakraverty S (2017) Single layer Chebyshev neural network model for solving elliptic partial differential equations. Neural Process Lett 45(3):825–840

Berg J, Nyström K (2018) A unified deep artificial neural network approach to partial differential equations in complex geometries. Neurocomputing 317:28–41

Yang YL, Hou MZ, Sun HL et al (2020) Neural network algorithm based on Legendre improved extreme learning machine for solving elliptic partial differential equations. Soft Comput 24(2):1083–1096

Shirvany Y, Hayati M, Moradian R (2009) Multilayer perceptron neural networks with novel unsupervised training method for numerical solution of the partial differential equations. Appl Soft Comput 9(1):20–29

Lu JY, Luo SW, Qi YJ, Huuang YP (2003) Numerical solution of elliptic partial differential equation using radial basis function neural networks. Neural Netw 16(5–6):729–734

Chedjou JC, Kyamakya K, Latif MA et al (2009) Solving stiff ordinary differential equations and partial differential equations using analog computin based on cellular neural networks. In: 2009 2nd international workshop on nonlinear dynamics and synchronization. IEEE, pp 213–220

Lazovskaya TV, Tarkhov DA (2015) Fresh approaches to the construction of parameterized neural network solutions of a stiff differential equation. St Petersb Polytechn Univers J Phys Math 1(2):192–198

Samath JA, Balasubramaniam P (2007) Solution of differential-algebraic equation systems using neural networks. In: International conference on computational intelligence and multimedia applications, vol 1. IEEE, pp 3–8

Kozlov D, Tiumentsev YV (2015) Neural network based semi-empirical models for dynamical systems described by differential-algebraic equations. Opt Memory Neural Netw 24(4):279–287

Kozlov DS, Tiumentsev YV (2018) Neural network based semi-empirical models for dynamical systems represented by differential-algebraic equations of index 2. Proc Comput Sci 123:252–257

Wahed ME, Abdelslam ZA, Eldaken OM (2015) A comparative study to solve the differential-algebraic equation systems by using genetic algorithm and neural networks. Sci Technol 1(4):124–136

Yang Z, Lan J, Wu YJ (2019) On solutions to several classes of differential-algebraic equations based on artificial neural networks. Appl Math Mech 40(2):115–126

**(in chinese)**Rostami F, Jafarian A (2018) A new artificial neural network structure for solving high-order linear fractional differential equations. Int J Comput Math 95(3):528–539

Chaharborj SS, Chaharborj SS, Mahmoudi Y (2017) Study of fractional order integro-differential equations by using Chebyshev neural network. J Math Stat 13(1):1–13

Xie Z, Kulasiri D et al (2007) The estimation of parameters for stochastic differential equations using neural networks. Inverse Probl Sci Eng 15(6):629–641

Zhao Y, Lu Q, Feng Z, Xia Y (2012) Delay differential equations under nonlinear impulsive control and applications to neural network models. J Syst Sci Complex 25(4):707–719

Liu HL, Xing BX, Wang Z, Li LJ (2020) Legendre neural network method for several classes of singularly perturbed differential equations based on mapping and piecewise optimization technology. Neural Process Lett 51:2891–2913

Koekoek J, Koekoek R (2000) Differential equations for generalized Jacobi polynomials. J Comput Appl Math 126(1–2):1–31

Doha EH, Bhrawy AH, Ezz-Eldien SS (2012) A new Jacobi operational matrix: an application for solving fractional differential equations. Appl Math Model 36(10):4931–4943

Imani A, Aminataei A, Imani A (2011) Collocation method via Jacobi polynomials for solving nonlinear ordinary differential equations. Int J Math Math Sci 1:383–390

Doha EH, Abdelkawy MA, Amin AZ, Baleanu D (2019) Shifted Jacobi spectral collocation method with convergence analysis for solving integro-differential equations and system of integro-differential equations. Nonlinear Anal Model Control 24(3):332–352

Guo BY, Shen J, Wang LL (2009) Generalized Jacobi polynomials/functions and their applications. Appl Numer Math 59(5):1011–1028

Babuška I, Guo B (2000) Optimal estimates for lower and upper bounds of approximation errors in the p-version of the finite element method in two dimensions. Numer Math 85(2):219–255

Babuška I, Guo B (2002) Direct and inverse approximation theorems for the p-version of the finite element method in the framework of weighted Besov spaces. Part I: approximability of functions in the weighted Besov spaces. SIAM J Numer Anal 39(5):1512–1538

Chihara TS (2011) An introduction to orthogonal polynomials. Courier Corporation, North Chelmsford

Muthukumar P, Ganesh Priya B (2017) Numerical solution of fractional delay differential equation by shifted Jacobi polynomials. Int J Comput Math 94(3):471–492

Pao YH, Phillips SM (1995) The functional link net and learning optimal control. Neurocomputing 9(2):149–164

Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1):489–501

Parkavi RM, Shanthi M, Bhuvaneshwari MC (2017) Recent trends in ELM and MLELM: a review. Adv Sci Tech Eng Syst J 2(1):69–75

Saravi M, Babolian E, England R, Bromilow M (2010) System of linear ordinary differential and differential-algebraic equations and pseudo-spectral method. Comput Math Appl 59(4):1524–1531

## Acknowledgements

This research is supported by the National Natural Science Foundation of China (No. 11971412) and Key Project of Education Department of Hunan Province (Grant No. 20A484).

## Author information

### Authors and Affiliations

### Corresponding author

## Ethics declarations

### Conflict of interest

All authors have no conflict of interest.

## 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

Liu, H., Liu, H., Xu, J. *et al.* Jacobi Neural Network Method for Solving Linear Differential-Algebraic Equations with Variable Coefficients.
*Neural Process Lett* **53**, 3357–3374 (2021). https://doi.org/10.1007/s11063-021-10543-5

Accepted:

Published:

Issue Date:

DOI: https://doi.org/10.1007/s11063-021-10543-5