why do i have so many errors when trying to use particle swarm optimisation in matlab?
1 view (last 30 days)
Show older comments
his is my code for the objective function
function y = T(x,c)
% this is the objective function
if x(1)^2-x(2)+1 <= 0
y = x(1)^2 + x(2)^2;
elseif x(1)^2-x(2)+1 > 0
if c == 1
y = x(1)^2 + x(2)^2 + (1/2)*(x(1)^2-x(2)+1)^2;
elseif c == 10
y = x(1)^2 + x(2)^2 + (10/2)*(x(1)^2-x(2)+1)^2;
elseif c == 100
y = x(1)^2 + x(2)^2 + (100/2)*(x(1)^2-x(2)+1)^2;
end
end
And here is my script file in trying to obtain optimal values near global optimum by following the example in this link https://uk.mathworks.com/help/gads/optimize-using-particle-swarm-optimization.html
fun = @T;
n = 2;
rng default
[x,fval,exitflag] = particleswarm(fun,n)
lb = [-50;-50];
ub = -lb;
[x,fval,exitflag] = particleswarm(fun,n,lb,ub)
options = optimoptions('particleswarm','SwarmSize',100);
[x,fval,exitflag] = particleswarm(fun,n,lb,ub,options)
options.HybridFCn= @fmincon;
[x,fval,exitflag] = particleswarm(fun,n,lb,ub,options)
after executing the file i get these errors
Error using particleswarm>makeState (line 700)
Failure in initial objective function evaluation. PARTICLESWARM cannot
continue.
Error in particleswarm>pswcore (line 170)
state = makeState(nvars,lbMatrix,ubMatrix,objFcn,options);
Error in particleswarm (line 152)
[x,fval,exitFlag,output] =
pswcore(objFcn,nvars,lbRow,ubRow,output,options);
Error in question_7b (line 5)
[x,fval,exitflag] = particleswarm(fun,n)
Caused by:
Not enough input arguments.
1 Comment
Adam
on 16 Dec 2016
Just for info, that is only 1 error being reported, it is just giving you the callstack that leads to the error.
Accepted Answer
José-Luis
on 16 Dec 2016
T, and consequently fun expect two arguments. From the documentation of particle swarm:
"Objective function, specified as a function handle. The objective function should accept a row vector of length nvars and return a scalar value."
The function you pass should only have one argument...
3 Comments
Alan Weiss
on 16 Dec 2016
Looks like a typo to me. The correct capitalization is HybridFcn, not HybridFCn.
Alan Weiss
MATLAB mathematical toolbox documentation
More Answers (1)
nazli melek
on 28 Dec 2017
Thanks José-Luis for your help. I faced the same problem and it is solved now
0 Comments
See Also
Categories
Find more on Surrogate 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!