A Comprehensive Study on the Optimization of Drilling Performance in Hybrid Nano-Composites and Neat CFRP Composites Using Statistical and Machine Learning Approaches

Round 1

Reviewer 1 Report

In their manuscript, Nargis et al. explore the optimization of drilling performance in hybrid nano-composites and neat CFRP (carbon fiber-reinforced polymer) composites using a statistical and machine-learning approach. The authors present a well-written study, and their conclusion is robustly supported by experimental evidence. The topic is both interesting and significant, as it can offer valuable guidance for the development of CFRP composites. I recommend acceptance with minor revisions.

Here are some comments that the authors may consider to enhance the manuscript:

1. Generalization to Other Fiber-Reinforced Composites: While the conclusion primarily focuses on CFRP composites, it would be beneficial to discuss its applicability to other types of fiber-reinforced composites, such as glass fiber, Kevlar fiber, and Polyimide fiber. Providing insights into the broader scope of the findings and potential implications for different materials would strengthen the manuscript.
2. Figure 5 (b) Notation and Legibility: The notation in Figure 5 (b) should be reorganized for clarity. Additionally, consider improving the legibility of the text within the figures, as small font sizes can hinder readers’ understanding.

no concerns

Author Response

The authors of this paper would like to sincerely thank the reviewer for their valuable comments/suggestions made. Please find the response for each comment in the following paragraphs.

1. Generalization to Other Fiber-Reinforced Composites: While the conclusion primarily focuses on CFRP composites, it would be beneficial to discuss its applicability to other types of fiber-reinforced composites, such as glass fiber, Kevlar fiber, and Polyimide fiber. Providing insights into the broader scope of the findings and potential implications for different materials would strengthen the manuscript.

Response: As per the reviewer’s suggestion, about the implication of this study on different composites, the last point in the conclusion part has been added.

2. Figure 5 (b) Notation and Legibility: The notation in Figure 5 (b) should be reorganized for clarity. Additionally, consider improving the legibility of the text within the figures, as small font sizes can hinder readers’ understanding.

Response: As per the reviewer’s suggestion, the image has been increased in size for better clarity. We deeply apologize, as our system had crashed in the past. The source file of the result analyzed was not found when searched. Hence, the authors could only increase the size of the image for clarity.

Author Response File: Author Response.pdf

Reviewer 2 Report

The authors studied the use of statistics and machine learning for the analysis of drilling of CFRP. While the manuscript is generally well executed, there are several issues that should be addressed before further consideration for publication.

1. Did the authors consider how the nano additives affect the bonding characteristics and thus, the results? Any benchmarking done?

- Su et al. (2024), Directionally induced high-density secondary interaction for enhancing the bonding reliability of titanium alloy and CFRTP via functional Schiff base-contained polymer, Composites Part B: Engineering 275, 111316

- Ouyang et al. (2024), Robot-assisted laser additive manufacturing for high-strength/low-porosity continuous fiber-reinforced thermoplastic composites, Composites Science and Technology 247, 110397

2. What is the purpose of showing Figure 3? The instrument is a standard set up and no labels are shown in the figure. 

3. Some of the regression equation has such small factor, are they still significant?

4. For Table 3, why are the standard deviations not considered as there are replicates used in the experiments?

5. There are little analysis on the results. What are the new insights gained from this work?

Author Response

The authors of this paper would like to sincerely thank the reviewer for their valuable comments/suggestions made. Please find the response for each comment in the following paragraphs.

1. Did the authors consider how the nano additives affect the bonding characteristics and thus, the results? Any benchmarking done?

Response: As per the reviewer’s suggestion, a detailed explanation has been added in the results and discussion part about the bonding of nanoparticles with polymer resin chains. In the previous work of authors, a complete explanation has been provided for articles that have been cited in the running text in the revised manuscript.

Our previous articles are:

a) Shahabaz, S.M.; Shetty, P.K.; Shetty, N.; Sharma, S.; Divakara Shetty, S.; Naik, N. Effect of Alumina and Silicon Carbide Nanoparticle-Infused Polymer Matrix on Mechanical Properties of Unidirectional Carbon Fiber-Reinforced Polymer. Compos. Sci. 2022, 6, 381.

b) Shahabaz, S.M.; Mehrotra, P.; Kalita, H.; Sharma, S.; Naik, N.; Noronha, D.J.; Shetty, N. Effect of Al2O3 and SiC Nano-Fillers on the Mechanical Properties of Carbon Fiber-Reinforced Epoxy Hybrid Composites. Compos. Sci. 2023, 7, 133.

2. What is the purpose of showing Figure 3? The instrument is a standard set up and no labels are shown in the figure.

Response: As per the author's suggestion, Figure 3 has been labeled for better understanding of the readers in the revised manuscript.

3. Some of the regression equation has such small factor, are they still significant??

Response: We completely agree with the reviewer's suggestion on regression equations with small factors not being significant, but for the modeling purpose in machine learning using ANN and RF techniques, full regression equations were required. Hence, we have shown full regression equations in Table 2.

4. For Table 3, why are the standard deviations not considered as there are replicates used in the experiments?

Response: As per the reviewer's suggestion, the standard deviations have been added in Table 3, and their explanation is also provided in the results and discussion section of the revised manuscript.

5. There are little analysis on the results. What are the new insights gained from this work?

Response: From this study, we were able to understand that the artificial neural network (ANN) and random forest (RF) machine learning approaches can be utilized to predict the surface roughness of the composites, which could also be applied to other materials during the machinability study.

Another insight is the surface roughness experimental results closely matched the RSM-predicted values, providing the validity of predictive models in estimating the surface roughness of a material.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

The labelling on the figures is off. Please check the formatting.

Author Response

Response (revision notes) to the Reviewer’s Comments:

The authors of this paper would like to sincerely thank the reviewer for their valuable comments/suggestions made. Please find the response for each comment in the following paragraphs.

The labelling on the figures is off. Please check the formatting.

Response: As per the reviewer’s suggestion, the labelling of the figures has been corrected in the revised manuscript.

Author Response File: Author Response.pdf