The first argument of the fmincon() function is This argument is used to tell fmincon() that the cost function is defined in the function “cost_function(x)” that is defined on the code lines 26-32. We use the code line 23 to solve the problem. The first option tells MATLAB that we plan to use the build-in “fmincon” function to solve the problem. We we the option “Display” to “iter” to monitor and plot the optimization progress. We can select an algorithm, set the optimization tolerances, or even tell the optimizer to use the gradient of the cost function. The code line 21 defines the options for the solver. However, in our case, we are considering an unconstrained problem, so these constraints are left empty. We can use the code lines 10-15 to define the constraints for the optimizer. The solution to the optimization problem is stored in “solution”. On the code line 1, we can see that this function returns several variables. That is, the name of the function should correspond to the name used in the function declaration/definition. It is important to save this function in a new folder, and to name this function ” minimize_cost_function.m”. % notice that this function can access the arguments of the function % algorithm can be 'interior-point', 'SQP','active set', and 'trust region reflective' % x C(x) <= 0, Ceq(x) = 0 (nonlinear constraints) % min J(x) subject to: Aineq*x <= Bineq, Aeq*x = Beq (linear constraints) % fmincon attempts to solve problems of the form: % summary of the optimization problem-general form
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |