Design of artificial neural network models optimized with sequential quadratic programming to study the dynamics of nonlinear Troesch’s problem arising in plasma physics

In this study, a computational intelligence technique based on three different designs of artificial neural networks (ANNs) is presented to solve the nonlinear Troesch’s boundary value problem arising in plasma physics. The structure of three ANN models is formulated by incorporating log-sigmoid (ANN-LS), radial-base (ANN-RB) and tan-sigmoid (ANN-TS) kernel functions in the hidden layers. Mathematical modeling of the problem is constructed for all three feed-forward ANN models by defining an error function in an unsupervised manner. Sequential quadratic programming method is employed for the learning of unknown parameters for all three ANN-LS, ANN-RB and ANN-TS schemes. The proposed models are applied to solve variants of Troesch’s problems by taking the small and large values of critical parameter in the system. A comparison of the proposed solution obtained from these models has been made with the standard numerical results of Adams method. The accuracy and convergence of the proposed models are investigated through results of statistical analysis in terms of performance indices based on the mean absolute deviation, root-mean-square error and variance account for.

[1]  Hikmet Caglar,et al.  B-Spline Solution and the Chaotic Dynamics of Troesch's Problem , 2014 .

[2]  S. Momani,et al.  Solution of Inverse Kinematics Problem using Genetic Algorithms , 2016 .

[3]  Ahmed Alsaedi,et al.  An Optimization Algorithm for Solving Systems of Singular Boundary Value Problems , 2014 .

[4]  Muhammad Asif Zahoor Raja,et al.  Unsupervised neural networks for solving Troesch's problem , 2013 .

[5]  Helmi Temimi,et al.  An accurate asymptotic approximation and precise numerical solution of highly sensitive Troesch's problem , 2014, Appl. Math. Comput..

[6]  G. Garcea,et al.  An Efficient Algorithm for Shakedown Analysis Based on Equality Constrained Sequential Quadratic Programming , 2015 .

[7]  Raza Samar,et al.  Numerical treatment of nonlinear MHD Jeffery–Hamel problems using stochastic algorithms , 2014 .

[8]  M. Raja,et al.  Design of bio-inspired computational intelligence technique for solving steady thin film flow of Johnson–Segalman fluid on vertical cylinder for drainage problems , 2016 .

[9]  Zaer S. Abo-Hammour,et al.  Continuous Genetic Algorithm as a Novel Solver for Stokes and Nonlinear Navier Stokes Problems , 2014 .

[10]  D. Gidaspow,et al.  A Model for Discharge of Storage Batteries , 1973 .

[11]  Omar Abu Arqub,et al.  Optimization Solution of Troesch’s and Bratu’s Problems of Ordinary Type Using Novel Continuous Genetic Algorithm , 2014 .

[12]  Manoj Kumar,et al.  An Introduction to Neural Network Methods for Differential Equations , 2015 .

[13]  Naveed Ishtiaq Chaudhary,et al.  Design of bio-inspired computing technique for nanofluidics based on nonlinear Jeffery–Hamel flow equations , 2016 .

[14]  Raja Muhammad Asif Zahoor,et al.  Stochastic numerical treatment for solving Troesch's problem , 2014, Inf. Sci..

[15]  Iftikhar Ahmad,et al.  Stochastic approach for the solution of multi-pantograph differential equation arising in cell-growth model , 2015, Appl. Math. Comput..

[16]  Anupam Yadav,et al.  An efficient algorithm based on artificial neural networks and particle swarm optimization for solution of nonlinear Troesch’s problem , 2015, Neural Computing and Applications.

[17]  Johan Meyers,et al.  Sequential Quadratic Programming (SQP) for optimal control in direct numerical simulation of turbulent flow , 2014, J. Comput. Phys..

[18]  Raja Muhammad Asif Zahoor,et al.  Comparison of three unsupervised neural network models for first Painlevé Transcendent , 2014, Neural Computing and Applications.

[19]  Mohammad Javad Morshed,et al.  Hybrid imperialist competitive-sequential quadratic programming (HIC-SQP) algorithm for solving economic load dispatch with incorporating stochastic wind power: A comparative study on heuristic optimization techniques , 2014 .

[20]  Muhammad Asif Zahoor Raja,et al.  Solution of the one-dimensional Bratu equation arising in the fuel ignition model using ANN optimised with PSO and SQP , 2014 .

[21]  Tingwen Huang,et al.  Synchronization criterion for linearly coupled neural networks with impulsive time window , 2015 .

[22]  Snehashish Chakraverty,et al.  Regression-based weight generation algorithm in neural network for solution of initial and boundary value problems , 2013, Neural Computing and Applications.

[23]  Raja Muhammad Asif Zahoor,et al.  Numerical treatment for nonlinear MHD Jeffery-Hamel problem using neural networks optimized with interior point algorithm , 2014, Neurocomputing.

[24]  Raja Muhammad Asif Zahoor,et al.  Design and application of nature inspired computing approach for nonlinear stiff oscillatory problems , 2015, Neural Computing and Applications.

[25]  Elyas Shivanian,et al.  Bio-inspired computing platform for reliable solution of Bratu-type equations arising in the modeling of electrically conducting solids , 2016 .

[26]  Liquan Mei,et al.  An efficient algorithm for solving Troesch's problem , 2007, Appl. Math. Comput..

[27]  Shaher Momani,et al.  Variational iteration method for solving nonlinear boundary value problems , 2006, Appl. Math. Comput..

[28]  Raja Muhammad Asif Zahoor,et al.  Exactly satisfying initial conditions neural network models for numerical treatment of first Painlevé equation , 2015, Appl. Soft Comput..

[29]  Raja Muhammad Asif Zahoor,et al.  Biologically inspired computing framework for solving two-point boundary value problems using differential evolution , 2017, Neural Computing and Applications.

[30]  Raja Muhammad Asif Zahoor,et al.  Numerical treatment for boundary value problems of Pantograph functional differential equation using computational intelligence algorithms , 2014, Appl. Soft Comput..

[31]  M. Pinto,et al.  Existence and Global Convergence of Periodic Solutions in Recurrent Neural Network Models with a General Piecewise Alternately Advanced and Retarded Argument , 2014 .

[32]  Manoj Kumar,et al.  Multilayer perceptrons and radial basis function neural network methods for the solution of differential equations: A survey , 2011, Comput. Math. Appl..

[33]  Raja Muhammad Asif Zahoor,et al.  Numerical treatment for solving one-dimensional Bratu problem using neural networks , 2012, Neural Computing and Applications.

[34]  Junaid Ali Khan,et al.  Stochastic numerical treatment for thin film flow of third grade fluid using unsupervised neural networks , 2015 .

[35]  B. A Troesch,et al.  A simple approach to a sensitive two-point boundary value problem , 1976 .

[36]  Raja Muhammad Asif Zahoor,et al.  A new stochastic approach for solution of Riccati differential equation of fractional order , 2010, Annals of Mathematics and Artificial Intelligence.

[37]  Muhammad Asif Zahoor Raja,et al.  Numerical treatment for boundary value problems of Pantograph functional differential equation using computational intelligence algorithms , 2014 .

[38]  Abdul-Majid Wazwaz,et al.  Nature-inspired computing approach for solving non-linear singular Emden–Fowler problem arising in electromagnetic theory , 2015, Connect. Sci..

[39]  M. Raja.  Stochastic numerical treatment for solving Troesch’s problem , 2014 .

[40]  Abdul-Majid Wazwaz,et al.  Stochastic numerical solver for nanofluidic problems containing multi-walled carbon nanotubes , 2016, Appl. Soft Comput..

[41]  Qiang Xi,et al.  Existence, Uniqueness, and Stability Analysis of Impulsive Neural Networks with Mixed Time Delays , 2014 .

[42]  A. Kouibia,et al.  The variational spline method for solving Troesch’s problem , 2014, Journal of Mathematical Chemistry.

[43]  SuHongye,et al.  Exponential state estimation for discrete-time switched genetic regulatory networks with random delays , 2014 .

[44]  Za'er Salim Abo-Hammour,et al.  Numerical solution of systems of second-order boundary value problems using continuous genetic algorithm , 2014, Inf. Sci..

[45]  Snehashish Chakraverty,et al.  Numerical solution of nonlinear singular initial value problems of Emden-Fowler type using Chebyshev Neural Network method , 2015, Neurocomputing.

[46]  Raja Muhammad Asif Zahoor,et al.  Reliable numerical treatment of nonlinear singular Flierl-Petviashivili equations for unbounded domain using ANN, GAs, and SQP , 2016, Appl. Soft Comput..

[47]  M. A. Manzar,et al.  An efficient computational intelligence approach for solving fractional order Riccati equations using ANN and SQP , 2015 .

[48]  Dale R. Durran,et al.  The Third-Order Adams-Bashforth Method: An Attractive Alternative to Leapfrog Time Differencing , 1991 .

[49]  S. M. Lee,et al.  Stability analysis for discrete-time neural networks with time-varying delays and stochastic parameter uncertainties , 2015 .

[50]  Yusuf Gurefe,et al.  Multiplicative Adams Bashforth–Moulton methods , 2011, Numerical Algorithms.

[51]  Manoj Kumar,et al.  Numerical Solution of Bratu’s Problem Using Multilayer Perceptron Neural Network Method , 2015 .

[52]  Snehashish Chakraverty,et al.  Chebyshev Neural Network based model for solving Lane-Emden type equations , 2014, Appl. Math. Comput..