Bounds constraints not followed in genetic algorithm ga
1 view (last 30 days)
Show older comments
I have a cost function that is solved using the Hybrid Solver combining ga and fmincon in MATLAB. However, I find that the bounds constraints are not followed in the sense, that the entire range covered by the bound is not utilized during the cost function evaluation.
[x,fval,exitFlag,Output]=ga(@(x) hybrid_cost(x,Tzx,Tzy,st,sr,sp,f0,B,e,N),N*(N+1)/2+2,[],[],[],[],lb,ub,mycon,options);
There are no equality or inequality constraints so these coefficient vectors are placed as null. lb and ub are the lower and upper bounds vectors. After optimization, the resultant optimized vector only gives values in the range [0,0.1], whatever be the bounds applied.
What could be the possible correction?
0 Comments
Answers (0)
See Also
Categories
Find more on Nonlinear Optimization in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!