TY - JOUR ID - 3153 TI - A Neural Network Method Based on Mittag-Leffler Function for Solving a Class of Fractional Optimal Control Problems JO - AUT Journal of Modeling and Simulation JA - MISCJ LA - en SN - 2588-2953 AU - Ghasemi, S. AU - Nazemi, A.R. AD - Faculty of Mathematical Sciences, Shahrood University of Technology, Shahrood, Iran Y1 - 2018 PY - 2018 VL - 50 IS - 2 SP - 211 EP - 218 KW - Ponteryagin minimum principle KW - fractional optimal control problem KW - artificial neural network KW - equality and inequality constraint KW - optimization DO - 10.22060/miscj.2018.14448.5106 N2 - In this paper, a computational intelligence method is used for solution of fractional optimal control problems (FOCPs) with equality and inequality constraints. According to the Ponteryagin minimum principle (PMP) for FOCP with fractional derivative in the Riemann- Liouville sense and by constructing a suitable error function, we define an unconstrained minimization problem. In the optimization problem, we use trial solutions for the states, Lagrange multipliers and control functions where these trial solutions are constructed by a feed-forward neural network model. We then minimize the error function using a numerical optimization scheme where weight parameters and biases associated with all neurons are unknown. Examples are included to demonstrate the validity and capability of the proposed method. The strength of the proposed method is its equal applicability for the integer-order case as well as fractional order case. Another advantage of the presented approach is to provide results on entire finite continuous domain unlike some other numerical methods which provide solutions only on discrete grid of point. UR - https://miscj.aut.ac.ir/article_3153.html L1 - https://miscj.aut.ac.ir/article_3153_75d18d1f2ccea162cd23632681745a5e.pdf ER -