Why is the size of my "narx_net_closed.IW{1}" different from the size of my "mrac_net.LW{3,2}" ? I am refering to Reference Model Controller with MATLAB Script

1 次查看（过去 30 天）
Andrew wee
Andrew wee 2023-3-12
回答： Neha 2023-9-4
Ran in:
% [u,y] = [ouputdata,inputdata];
a=outputdata' %get from the outputdata.mat file attachment
Unrecognized function or variable 'outputdata'.
[r,c]=size(a)
u={}
for w = 1:c
u{w}=[a(1,w);a(2,w);a(3,w)]
end
b=inputdata'
[r1,c1]=size(b)
y={}
for x = 1:c1
y{x}=[b(1,x);b(2,x);b(3,x);b(4,x);b(5,x);b(6,x);b(7,x);b(8,x);b(9,x);b(10,x);b(11,x);b(12,x)]
end
% [X,T] = simpleseries_dataset;
% [u,y] = robotarm_dataset;
% u=[1,2,3];
% y=[4,5,6];
d1 = [1:2];
d2 = [1:2];
S1 = 5;
narx_net = narxnet(d1,d2,S1);
narx_net.divideFcn = '';
narx_net.inputs{1}.processFcns = {};
narx_net.inputs{2}.processFcns = {};
narx_net.outputs{2}.processFcns = {};
narx_net.trainParam.min_grad = 1e-10;
[p,Pi,Ai,t] = preparets(narx_net,u,{},y);
narx_net = train(narx_net,p,t,Pi);
narx_net_closed = closeloop(narx_net);
view(narx_net_closed)
mrac_net = feedforwardnet([S1 1 S1]);
mrac_net.layerConnect = [0 1 0 1;1 0 0 0;0 1 0 1;0 0 1 0];
mrac_net.outputs{4}.feedbackMode = 'closed';
mrac_net.layers{2}.transferFcn = 'purelin';
mrac_net.layerWeights{3,4}.delays = 1:2;
mrac_net.layerWeights{3,2}.delays = 1:2;
mrac_net.layerWeights{3,2}.learn = 0;
mrac_net.layerWeights{3,4}.learn = 0;
mrac_net.layerWeights{4,3}.learn = 0;
mrac_net.biases{3}.learn = 0;
mrac_net.biases{4}.learn = 0;
mrac_net.divideFcn = '';
mrac_net.inputs{1}.processFcns = {};
mrac_net.outputs{4}.processFcns = {};
mrac_net.name = 'Model Reference Adaptive Control Network';
mrac_net.layerWeights{1,2}.delays = 1:2;
mrac_net.layerWeights{1,4}.delays = 1:2;
mrac_net.inputWeights{1}.delays = 1:2;
% [refin,refout] = refmodel_dataset;
p=error'
[r3,c3]=size(p)
refin={}
for k = 1:c2
refin{k}=[p(1,k);p(2,k);p(3,k);p(4,k);p(5,k);p(6,k);p(7,k);p(8,k);p(9,k);p(10,k);p(11,k);p(12,k)]
end
f=modelref'
[r2,c2]=size(f)
refout={}
for m = 1:c2
refout{m}=[f(1,m);f(2,m);f(3,m);f(4,m);f(5,m);f(6,m);f(7,m);f(8,m);f(9,m);f(10,m);f(11,m);f(12,m)]
end
ind = 1:length(refin);
plot(ind,cell2mat(refin),ind,cell2mat(refout))
mrac_net = configure(mrac_net,refin,refout);
mrac_net.LW{3,2} = narx_net_closed.IW{1}; %cause of the problem and why i am asking
mrac_net.LW{3,4} = narx_net_closed.LW{1,2};
mrac_net.b{3} = narx_net_closed.b{1};
mrac_net.LW{4,3} = narx_net_closed.LW{2,1};
mrac_net.b{4} = narx_net_closed.b{2};

请先登录，再回答此问题。

回答（1 个）

Neha
Neha 2023-9-4
Hi Andrew,
I understand that you are facing an error as the size of input weights for the closed NARX network differs from the size of the layer weights pertaining to the MRAC network.
The size of narx_net_closed.IW{1} is 5x6 and the size of mrac_net.LW{3,2} is 5x2.
You can refer to the following documentation link on how the sizes of the weights are calculated:
https://www.mathworks.com/help/deeplearning/ug/neural-network-object-properties.html#:~:text=and%20bias%20vectors.-,net.IW,net.layerWeights%7Bi%2Cj%7D.size,-net.b
Since the number of columns in the layer weights of MRAC is essentially the delays associated with layerWeights{3,2}, you can change the number of delays in line 37 from 2 to 6 to ensure that it is equal to the number of columns in narx_net_closed.IW{1}.
mrac_net.layerWeights{3,2}.delays = 1:6;
Hope this helps!

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by