An Iterative Procedure for Optimizing the Performance of the Fuzzy-Neural Job Cycle Time Estimation Approach in a Wafer Fabrication Factory

Algorithm 2

The sample MATLAB code for the BPN approach.

tn_input=[0.843  0.831  ⋯;0.839  0.859  ⋯;0.9  0.9  ⋯;0.878  0.889  ⋯;0.875  0.858  ⋯;

0.822  0.827  ⋯]

tn_target=[0.849  0.849  ⋯]

net=newff ([0  1;0  1;0  1;0  1;0  1;0  1],[12,1], {"logsig","logsig"},"trainlm");

net=init(net);

net.trainParam.show=10;

net.trainParam.lr=0.1;

net.trainParam.epochs=1000;

net.trainParam.goal=1e−4;

[net,tr]=train(net,tn_input,tn_target);

tn_output=sim(net,tn_input)

te_input=[0.825  0.844⋯;0.824  0.835  ⋯;0.9  0.9  ⋯;0.878  0.889  ⋯;0.883  0.875  ⋯;

0.807  0.820  ⋯]

te_output=sim(net,te_input)