Modeling the Mechanical Properties of Heat-Treated Mg-Zn-RE-Zr-Ca-Sr Alloys with the Artificial Neural Network and the Regression Model

Round 1

Reviewer 1 Report

The authors present an interesting work on Materials informatics. In this case, an artificial neural network approach and a regression model are presented to predict the mechanical property of heat-treated Mg-Zn-RE-Zr-Ca-Sr magnesium alloys. This is an active and dynamic line that is currently consolidating. That is of interest to the community thanks to the opportunity to be more efficient in experimentation and predict exotic and novel properties of new materials. Particularly in this work, the authors present a data set for the modeling of artificial neural networks (ANN), which help to identify microhardness properties of heat-treated Mg-Zn-RE-Zr-Ca-Sr alloys through hardness tests.

However, the great challenge in using (ANN) is centered on the origin of the data. When the authors mention that a backpropagation (BP) neural network has been established using experimental data, the data's source, quality, quantity, and reproducibility are not clear. Doubts remain about the propagation of errors, whether a Round-Robin Sample has been carried out or how the process has been guaranteed, not giving statistical weight to a particular data group. The analysis would be seriously affected, so this should be further explored.

This is the main challenge of this type of approach. The prediction of the mechanical property as a function of the composition and the heat treatment process ultimately depends on the origin of the experimental data. Before accepting the article, the authors must look into these aspects, clarify the category and statistical weight of the input variables for the BP network model, and contrast (highly recommended with a Bayesian statistical approach) the results beyond a reliable correlation coefficient.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

The paper titled “Modeling of the Mechanical Property of Heat-Treated Mg-Zn-RE-Zr-Ca-Sr Alloys by Artificial Neural Network and Regression Model” reports the ANN model and multiple regression model, which were developed to predict the mechanical properties of heat-treated Mg-Zn-RE-Zr-Ca-Sr alloys. The research was aimed to provide a new strategy for the development of Mg alloys that is actual and important in terms of modern industrial needs. The paper can be accepted for publication after minor revision. The comments are listed below.

1. Use uniformly “aging” or “ageing”
2. “light-weight magnesium alloys have been paid more and more attention” –?– “light-weight magnesium alloys have attracted more and more attention”
3. RE within the Mg-Zn-RE-Zr alloy should be defined when first used.
4. “In recent years, artificial neural networks (ANNs) have been powerful and flexible modeling tools” –?– “In recent years, artificial neural networks (ANNs) have become powerful and flexible modeling tools”
5. Tables should appear in the text in the same order as they cited.
6. There are two “Figure 2” in the manuscript.
7. As stated “Table 2 summaries the experimental results, which is attached to the end of the article”. Actually, Table 2 does not exist. The table at “the end of the article” is named as Table 1 in Appendix A.

Author Response

Please see the attachment.

Author Response File: Author Response.docx