Prediction Analysis of Surface Roughness of Aluminum Al6061 in End Milling CNC Machine Using Soft Computing Techniques
Round 1
Reviewer 1 Report (New Reviewer)
The subject of the paper is interesting. The manuscript is well planned however, the Authors should pay attention to some aspects listed below:
- In the introduction section, Authors should clearly highlight the novelty of their work
- The analysis should be supplemented with a comparison of the obtained results with literature references and results of other researchers
- In the abstract section, the Authors should clearly express the importance of this review
- Many abbreviations are used in the manuscript, authors should make sure all are explained
- Conclusions should be more expanded
- References should be formatted according to the journal's requirements
Author Response
REVIEWER 1
1. The novelty of the work is explained in the introduction. To highlight it, we have inserted the following statement:
“This is where resides the particularity of the present study, in the fact that an extended number of models and hyperparameters have been considered, which brings to the study variety of combinations the best result is depending on.”
2. Comparison of the obtained results and results of other researchers have been supplemented in paragraph 3.7. Literature references have been provided
3. In abstract, a sentence has been provided to add the importance of this review.
4. We have explained all the abbreviations including: CNC, FIS and characters decribed in figure 1 have been explained.
5. The conclusion has been expanded giving also a projection of our future work.
6. The references have been attended and corrected.
Author Response File: 
Author Response.docx
Reviewer 2 Report (New Reviewer)
Dear Authors,
the paper is interesting and fits in with the current trends in optimizing manufacturing processes and product quality using artificial intelligence methods. In order to improve the paper, please make the following corrections:
1. Figure 1 - Please add explanations of the characters used in the figure: l, Yi, etc.
2. The introduction section needs some content expansion.In order to get a full presentation of the topic of the publication and introduce the reader to these issues, the following should be done:
- page 2 - references to literature are missing. Especially the 2nd, 3rd, 4th and 5th paragraphs.
- after an introduction to the concept of roughness and machining to obtain it, it is advisable to present roughness measurement methods, for example:
contact methods: https://doi.org/10.1002/sia.7068
non-contact methods: https://doi.org/10.3390/cryst11111371
Then write what measurement methods you have chosen for your research and why they are sufficient or the best.
- then descriptions of artificial intelligence methods for roughness prediction - and this part is sufficiently well prepared by the authors
3. 30 parts of the material were made by changing the cutting parameters. Has the repeatability of the obtained results been checked? For example, making 3 samples using the same process parameters and measuring their roughness.
4. Roughness measurement results from actual measurement tests are missing. Please provide the roughness results obtained with the measuring machine, and then present the results of the AI methods.
5. Did the authors write their own program code for AI methods or did they use ready-made tools?
6. Improve the quality, resolution of figures.
Author Response
REVIEWER 2
1. Missing explanations of characters have been added
‘where yi is the vertical distance from the mean line to a given data point along the profile line and l is the mean width of the profile line.’
- Missing literature references have been added;
- Common methods used for surface roughness measurement and type of measurement used in the present study have been stated
3. Clarification has been made in the paragraph of “Methods” in connection with repeatability in measurement.
“The measurements of the surface roughness were done 3 times and the average was taken for all the 30 samples This study employed response surface methodology to design the template used for the experiment and in this design there are rooms for repeatability of the samples which gives a good optimisation analysis”
4. The roughness results obtained with the measuring machine, and then present the results of the AI methods have been provided in the Result summary
5. Clarifications have been made in the Methods: ‘developed using ready-made artificial intelligence models on MatLab interface”
6. Figures have been improved at the best possible for better reading
Author Response File: Author Response.docx
Reviewer 3 Report (New Reviewer)
Title of the paper: Prediction Analysis of Surface Roughness of Aluminum Al6061 in End Milling CNC Machine using Soft Computing Techniques
General observations: The present research provides the artificial neural network (ANN) and adaptive network-based fuzzy inference system (ANFIS) approaches to predict and monitor the surface roughness of Aluminum Al6061 machined blocks. Furthermore, both models have been hybridized with genetic algorithm (GA) and particle swarm optimization (PSO) to investigate the potential enhancement of the prediction performance of the hybrid approach. The results show that factors such as the population size, the acceleration values, the choice of membership functions, and the number of neurons and layers significantly influence the prediction performance of the proposed models
1) Please include the following research on the surface finish investigation of aluminum alloy 6061:
· Wang, S.J., To, S., Chen, X. and Chen, X.D., 2015. An investigation on surface finishing in ultra-precision raster milling of aluminum alloy 6061. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 229(8), pp.1289-1301.
· Sreenivasulu, R. and Rao, C.S., 2012. Application of grey relational analysis for surface roughness and roundness error in drilling of Al 6061 alloy. International journal of lean thinking, 3(2), pp.67-78.
2) Please reframe “The surface roughness that T. Singh, P. Kumar, and J.P. Misra [17] regard to be a performance feature have been predicted using ANFIS modeling.”
3) Please refer to Figure 4. (a): Aluminum blocks, the magnification index with Ra value may be provided.
4) Please refer to Figure 2. Artificial neural network structure looks incomplete, input 3 may be modified, and various other notations may be modified accordingly.d.
5) Please refer to Figure 11. ANFIS surface view., the figure may be improved by naming input and output variables used in the research. Further, the inference may also be drawn and documented in the manuscript.
6) Several figures are not discussed in the manuscript, for instance, Figures 3,5,9,10, etc.
7) Table 9 is not discussed in the manuscript.
8) Regression coefficients named R2 and R2 in the manuscript may be used as R2 throughout the manuscript for uniformity.
9) Please refer to Table 9. Results summary, bullets may be removed from the column of the training function.
10) Acceleration values or Acceleration factors with unique notation may be used throughout the manuscript for uniformity.
Author Response
REVIEWER 3
1. The suggested research has been included in the Introduction
2. The sentence has been reframed
3. The magnification index with Ra value has been provided
4. The Figure 2 has been corrected
5. The figure 11 has been improved with Input 1, input 2 and output replaced by Speed, Feed and surface roughness respectively.
6. The figure 5 has been cited in the manuscript. As for other figures, they have already been mentioned.
7. Table 9 is cited in paragraph 3.7
8. R2 have been changed into R2 throughout the manuscript
9. Bullets in the training column have been removed
10. Acceleration factors with unique notation may be used throughout the manuscript for uniformity.
Author Response File: Author Response.docx
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.
Round 1
Reviewer 1 Report
The authors have not adequately addressed the comments of the reviewer. The authors rather tried to defend this incomplete manuscript by their previously published work. It is just a continuation of their previous works.
