Parand, Kourosh, Ghaemi Javid, Ghazal Sadat, Jani, Mostafa. (1401). A machine learning approach for solving inverse Stefan problem. هنرهای کاربردی, 13(2), 2233-2246. doi: 10.22075/ijnaa.2021.20548.2170
Kourosh Parand; Ghazal Sadat Ghaemi Javid; Mostafa Jani. "A machine learning approach for solving inverse Stefan problem". هنرهای کاربردی, 13, 2, 1401, 2233-2246. doi: 10.22075/ijnaa.2021.20548.2170
Parand, Kourosh, Ghaemi Javid, Ghazal Sadat, Jani, Mostafa. (1401). 'A machine learning approach for solving inverse Stefan problem', هنرهای کاربردی, 13(2), pp. 2233-2246. doi: 10.22075/ijnaa.2021.20548.2170
Parand, Kourosh, Ghaemi Javid, Ghazal Sadat, Jani, Mostafa. A machine learning approach for solving inverse Stefan problem. هنرهای کاربردی, 1401; 13(2): 2233-2246. doi: 10.22075/ijnaa.2021.20548.2170

A machine learning approach for solving inverse Stefan problem

International Journal of Nonlinear Analysis and Applications
مقاله 180، دوره 13، شماره 2، مهر 2022، صفحه 2233-2246    اصل مقاله (499.57 K)
نوع مقاله: Research Paper
شناسه دیجیتال (DOI): 10.22075/ijnaa.2021.20548.2170
نویسندگان
Kourosh Parand1، 2؛ Ghazal Sadat Ghaemi Javid* 1؛ Mostafa Jani1
1Department of Computer Sciences, Faculty of Mathematical Sciences, Shahid Beheshti University, G.C. Tehran, Iran
2Department of Statistics and Actuarial Science, University of Waterloo, Waterloo, Canada
چکیده
In this paper, we propose a numerical scheme by using Least Squares Support Vector Regression (LS-SVR) for the simulation of the inverse Stefan problem, which has ill-posedness issues. The purpose of this paper is to express the temperature distribution in a homogeneous environment with a phase change. In the proposed machine learning approach, we apply the unconditionally stable Crank-Nicolson method to decrease the computational cost and reduce one of the dimensions. Therefore, we solve an ODE equation at each time step. The training points of the network are chosen as the Chebyshev roots, which have a normal distribution, and our constructed roots, which we describe more precisely later. In the proposed method, the regularization parameter of the SVM aims to overcome the instability issues, leading to convergent approximation. For the given method, both the primal and dual forms are investigated. The dual form of the problem is written in matrix form. Finally, some numerical examples are provided to illustrate the effectiveness and accuracy of the proposed method.
کلیدواژه‌ها
Least squares support vector regression؛ Orthogonal kernel؛ Inverse Stefan problem؛ Collocation method؛ Chebyshev polynomials
مراجع
آمار
تعداد مشاهده مقاله: 45,009
تعداد دریافت فایل اصل مقاله: 51,312
دانشگاه سمنان
پیوندهای مفید
آمار
تعداد نشریات22
تعداد شماره‌ها721
تعداد مقالات10,359
تعداد مشاهده مقاله72,761,951
تعداد دریافت فایل اصل مقاله64,423,371