Prediction of Deposition Layer Morphology Dimensions Based on PSO-SVR for Laser–arc Hybrid Additive Manufacturing

Round 1

Reviewer 1 Report

The paper is well presented and contains original results. However, authors are encouraged to improve their work based on the following comments:

 

1) The novelty of this work must be more explained.

2) The overall language of this manuscript must be improved further especially the selection of words.

3) For general readers, authors are encouraged to discuss other kinds of works on Machine learning models such as: [(a) “Machine learning models for predicting the compressive strength of concrete containing nano silica”, Computers and Concrete, 30(1), 33-42.; (b) “Predicting elemental stiffness matrix of FG nanoplates using Gaussian Process Regression based surrogate model in framework of layerwise model”, Engineering Analysis with Boundary Elements, 143, 779-795.].

 

4) Fig. 6 should be more discussed.

5) Author should add some physical explanation to improve the quality of the paper. Conclusion section must be extended in a few words via main finding and advantages of the methodology.

The English is well written.

Author Response

Please see the attachment

Author Response File: Author Response.docx

Reviewer 2 Report

Report of Manuscript Number: coatings-2430718 

Prediction of deposition layer morphology dimensions based on PSO-SVR
for Laser-Arc Hybrid Additive Manufacturing

This paper reads very comfortable. I can easily understand the idea and techniques. The motivation is clear to me. The results are comprehensive.  In general, the article is good and is interesting, but it requires a minor revision. There are some recommendations:

 

Comments

 

1. The current abstract should be rewritten to provide the highlight of this study.

2. Authors should provide definitions of BPNN, and LightGBM models. in the introduction section.

 

3. There are many research papers study the similar problem which investigated in the present paper. So, the current work should be compared with the following published works in the introduction section

 

https://doi.org/10.3390/su15086437

https://doi.org/10.3390/coatings13030496

https://doi.org/10.1016/j.jmapro.2023.05.032

 

What is exactly the new point of this work?

 

4. Authors should explain more about the novelty of their work in the introduction section.

 

5. The considered Particle Swarm Optimization (PSO) algorithm and the Support Vector Regression (SVR) algorithm are not clear and need to be clarified in depth in the contribution

 

6. The conclusion section should be rewritten to be clear. It must be enriched about discussion on solving considered problem.

Author Response

Please see the attachment

Author Response File: Author Response.docx

Reviewer 3 Report

Dear Authors,

You gave extremely useful material. The manuscript is well-written, the content of the work is presented transparently. The literature review covers the subject area quite broadly. The model predicts the real experiment with high accuracy. And this is the most valuable thing for practice.

There are some minor typos in the text.

in table 1, the symbol for molybdenum must be correctly indicated.

figure 8 should be changed, looks uninformative, the lines overlap each other.

wrong number under figure 9.

At the paper's beginning you give the chemical composition of THQ-50C. The question arises: how did the chemical composition change after the experiment?

Good luck

There are some minor errors in the manuscript.

Author Response

Please see the attachment

Author Response File: Author Response.docx