Optimal Design of Hot-Dip Galvanized DP Steels via Artificial Neural Networks and Multi-Objective Genetic Optimization
, Gerardo Altamirano-Guerrero 1,*, Patricia S. Costa 2, Antonio E. Salas-Reyes 3, Armando Salinas-Rodríguez 4 and Frank Goodwin 5Round 1
Reviewer 1 Report
I found consistent misuses of capital letters in this manuscript, such as “Advanced High-Strength Steels”, “Artificial Neural Networks”, and “Genetic Algorithm” which require the modification. (Line 80) Why did the authors focus combining ANN and GA? The motivation of this research is not clearly presented in Section 1. (Line 83) There is no explanation for BPNN before the first appearance of this abbreviation. The full term came in Section 4, which is not accepted. (Line 145) As the authors mentioned earlier, the architecture has a vast effect on ANN performance. Nevertheless, they did neither perform an hyperparameter tuning nor provide a reason for their architecture (i.e, 3-9-9-3) which is bit odd in the field of machine learning. The authors should, at least, rationalize why they chose such an architecture for their ANN model. In the similar manner, the manuscript should provide more detailed information that is essential to describe their ANN model (which is very typical in the field of machine learning) like the number of epochs, used language and libraries (e.g., Python, Tensorflow…), dropout, activation function, and so on. I could barely find the description about the genetic algorithm used in this work in Section 2.2. This must be strengthened more. (Line 193) Please provide what (a) to (i) indicates, not only in the main article but also in the caption of Figure 4.Author Response
"Please see the attachment."
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Only the mechanical properties were predicted/simulated. Although the microstructure was NOT predicted/simulated, the manuscript claims that the microstructure was also simulated - Line 86 P. 2, line 283 P.10 and eventually some additional location . this misleads the reader to believe that the microstructure was predicted/simulated. Please formulate the manuscript in a way to eliminate this misleading of the reader.
Author Response
"Please see the attachment."
Author Response File: Author Response.pdf
Reviewer 3 Report
please read carefully attached file
Comments for author File: Comments.pdf
Author Response
"Please see the attachment."
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
The authors have properly answered my previous comments.
Reviewer 3 Report
Good work and well done
This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.
