Advanced Multiresponse Process Optimisation by Tatjana V. Šibalija & Vidosav D. Majstorović

Author:Tatjana V. Šibalija & Vidosav D. Majstorović
Language: eng
Format: epub
Publisher: Springer International Publishing, Cham

lp.mc = 0.9

Figure 3.26 shows an example of the results of network training, validation and testing results in Matlab, The Neural Network Toolbox.

Fig. 3.26An example of presentation of the network training, validation and testing results, in Matlab Neural Network Toolbox

After the network training, it is necessary to analyse the network outputs. First, the simulation of network results is performed for the whole set of process parameters (vector INPUT) and the whole set of a synthetic process performance γ k , for all experimental trials (k = 1, …, m), and then the linear regression between the actual network outputs and the original data from the vector INPUT is performed, using the following commands:y = sim (NN, INPUT)

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.