Innovative Approaches to Sustainable Computer Numeric Control Machining: A Machine Learning Perspective on Energy Efficiency

Round 1

Reviewer 1 Report (Previous Reviewer 2)

The manuscript under consideration is “Innovative Approaches to Sustainable CNC Machining: A Machine Learning Perspective on Energy Efficiency” (resubmission). The authors have proven they are experienced experimenters and have shown the strong ability to address multiple questions about this research. Undoubtedly, the experimental setup and the results obtained can be useful for extensive audience of professionals who deal with computer-controlled machining. From my point of view the manuscript deserves publishing after fixing some minor issues.

 1. Lines 11, 23. Kindly pay attention that full phrase should go first followed by abbreviation in in parentheses. Examples: lines 13, 31.

2. Line 22: “result” -> “results”.

3. Line 74: “endeavors” -> “parameters”.

4. The sentence in lines 77-78 (“Provides valuable insight…”) has predicate, but has no subject.

5. Line 112: excessive point before reference.

6. Line 169: check if all letters are correct in “naїve Bayes”.

7. Table in line 324 has no caption and is not referenced in the main text.

8. Line 362: “analysist” -> “analysis”.

9. Energy consumption is presented with four, two and one decimal point(s) in Table 4, line 496, lines 469-470 respectively. Kindly leave only significant decimal digits and make quantity of decimal digits the same everywhere for energy consumption values.

10. Line 466. As for me, “respectively” is needed at the end of the sentence.

Minor editing of English language required

Author Response

Thank you for your thoughtful consideration of the manuscript "Innovative Approaches to Sustainable CNC Machining: A Machine Learning Perspective on Energy Efficiency" (resubmission). We greatly value your positive assessment of the authors' expertise and the potential significance of their research in the realm of computer-controlled machining.

Your acknowledgment of the manuscript's potential utility for a wide audience of professionals within the field is sincerely appreciated. We will diligently address the minor issues you have highlighted to ensure the manuscript meets the highest standards before resubmission.

Your feedback is invaluable, and we are grateful for your recommendation of publication pending the resolution of these minor concerns.

Author Response File: Author Response.pdf

Reviewer 2 Report (New Reviewer)

1.     Title needs revision.

2.     Abstract is lacking the main findings and novelty of the work.

3.     The test is lacking continuity specially the start of the introduction section need modification to introduce the readers to the problem statement and significance of your work to the community followed by the research gape analysis and novelty.

4.     What does this statement mean “In the field of machining, the research emphasizes that spindle speed plays a central role in determining overall energy consumption, surpassing even cutting energy”

5.     The introduction section lacks continuity.

6.     Include all relevant papers to the studied topic in introduction section.

7.     Line 190 to 191 does not reflect the equation 4.

8.     The work is lacking energy used in machine setup time and how much it will affect the final findings.

9.     No details regarding the power meter is not included in the current work. What is the sensitivity and resolution of the power meter?

10.  Line 274 typo mistake. Line 313-314,

11.  Section 2.2.2 is really hard to understand.

12.  Why the selected cutting parameters were selected for the current work?

13.  Material property table caption and numbering is missing.

14.  The analysis is lacking the achievement of desired surface quality which is one of the key parameters in machining processes.

15.  How many tests were conducted for each set of cutting parameters, No STD is mentioned in the graph?

16.  The LCA term is very vaguely used in the current study and need more work to properly link it with the current work.

17.   The machine learning section is ok but needs more elaboration and explanation of ML algorithm used in the current work.

Extensive English proofreading is required and the current version is hard to understand and there are many typos, connectivity, continuity, and grammatical mistakes.

Author Response

Thank you for your detailed comments and feedback on our manuscript. We appreciate the thorough review and have taken all of your points into consideration. We have made the necessary revisions to address each of the issues you raised. We have thoroughly proofread the manuscript to ensure clarity and coherence in language. The revisions aim to enhance the overall quality and readability of the manuscript. We appreciate your feedback and the opportunity to improve our work.

Author Response File: Author Response.pdf

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

1. The following terms "machining" and "cutting" are mentioned in the manuscript. Exactly what processing operation are you performing? If it is milling, that term should be used in all places in the manuscript.

2. At the end of the Introduction section, explicitly state the scientific contribution of this research and the scientific hypothesis.

3. Detailed information about the fixture and cutting tools used should be given. Their choice should also be justified.

4. How were widths of cut, depths of cut, feed rate and spindle speeds selected? Why they are representative of your research.

5. It is not clear what is new in theory and/or experimental research. Emphasize this in the manuscript.

6. Detailed data on the workpiece material are missing.

7. Performance metric with different algorithm should be analysed and discussed in detail.

8. Assessment of the negative impact on the environment, i.e. life cycle assessment would significantly improve the quality of research.

9. The discussion of the obtained results should be more intensive. If possible, the results should be compared with the results of previous research.

10. The conclusions should be supplemented. The conclusions should state the possibilities of practical application, limitations and future research

Author Response

1. Content Description and Contextualization:

   • Reviewer: The content is not succinctly described and contextualized with respect to previous and present theoretical background and empirical research on the topic.
   • Author Response: We appreciate the reviewer's feedback and will revise the manuscript to ensure a more concise and well-contextualized presentation of the content in relation to the theoretical background and empirical research.

2. Relevance of Cited References:

   • Reviewer: All the cited references are relevant to the research.
   • Author Response: We thank the reviewer for confirming the relevance of the cited references to our research. We will ensure that the reference list accurately supports our study.

3. Clarity of Research Design, Questions, Hypotheses, and Methods:

   • Reviewer: The research design, questions, hypotheses, and methods are clearly stated.
   • Author Response: We are pleased to receive positive feedback on the clarity of our research design, questions, hypotheses, and methods. If there are specific aspects that the reviewer suggests improving further, we would welcome additional comments.

4. Coherence, Balance, and Compelling Arguments:

   • Reviewer: The arguments and discussion of findings are coherent, balanced, and compelling.
   • Author Response: We are grateful for the positive assessment of the coherence, balance, and compelling nature of our arguments and findings. We will ensure that these qualities are maintained and enhanced throughout the manuscript.

5. Clarity of Results in Empirical Research:

   • Reviewer: For empirical research, the results are clearly presented.
   • Author Response: We appreciate the reviewer's acknowledgment of the clarity in presenting empirical research results. Any specific suggestions for improvement in result presentation will be carefully considered.

6. Adequacy of Referencing:

   • Reviewer: The article is adequately referenced.
   • Author Response: Thank you for confirming the adequacy of referencing. We will review and update the reference section as needed to ensure accuracy and completeness.

7. Support for Conclusions:

   • Reviewer: The conclusions are thoroughly supported by the results presented in the article or referenced in secondary literature.
   • Author Response: We are pleased that the conclusions are well-supported. If there are specific areas that could benefit from further support or clarification, we would be grateful for additional feedback.

Author Response File: Author Response.pdf

Reviewer 2 Report

The manuscript under consideration is “Innovative Approaches to Sustainable CNC Machining: A Machine Learning Perspective on Energy Optimization”. The authors employ Machine Learning to establish correlation between energy consumption of 5-axis CNC machine and different manufacturing parameters during machining 6000 series aluminium alloy.

1. From my point of view, publishing this manuscript in its current condition is not possible because it is written in unacceptable style. “Highly artistic” expressions are repeatedly used in the text. Examples are:

surge in efficiency (lines 35-36); meticulously designed experiments (40); this study delves into the intricate interplay (41); the foundation for a nuanced analysis, unraveling the nuanced relationships (46); The primary objective of this research is to pave the way (52); The overarching goal is to establish (53-54); By adopting this holistic approach (55); This insight becomes pivotal in crafting targeted and impactful strategies (64-65); these techniques allow us to decipher the intricate connections between various parameters (85-86); Linear regression, a fundamental technique, assumes a linear relationship between input variables and output (87-89); various research endeavors (106); optimization procedures … become indispensable (121-122); to enhance parallel metaheuristics on the shop floor (12-130); The machine tool requires a foundational energy input for its operation and overall  readiness (188-189); This encompasses the essential energy for the machinery's functionality and ensuring it is ready for operation (189-190); Preceding our research endeavors (250); These meters have been strategically installed on the distribution board, selectively placed at key locations rather than being ubiquitously deployed (253-255); Our data acquisition methodology entails the meticulous recording (255-256); To streamline our monitoring process, we initiated the installation of current transformers (270-271); deliberate design (273); nuanced understanding (274); meticulous attention (279); we enhance the precision of our observations (287-288); valuable insights into the interplay (288); This integration … further enriches our study (289-290); offering a comprehensive view of energy utilization (290); In essence, the journey toward a reduced carbon footprint for a 5-axis CNC machine requires a multifaceted strategy. Each facet, from energy calculation and optimization to maintenance, operator training, and lifecycle analysis, plays a crucial role in achieving the overall goal of sustainability. This holistic approach not only benefits the environment but also contributes to more efficient and responsible manufacturing practices. In the pursuit of predicting energy consumption in machining processes, leveraging Machine Learning emerges as a robust and effective methodology (543-549).

The authors should understand that scientific paper is not a poem. The article has to be rewritten in the strict manner in which scientific papers are usually prepared. Avoid emotional expressions and praise, especially regarding your own work and your own results.

2. Large portions of text do not content any meaningful information. These are just common words about the subject under study. This concerns the entire Abstract and Introduction (up to line 82), Research methodology (lines 106-143) and entire Conclusion. There is a suspicion that the artificial intellect services (like chatGPT) were used during text preparation. If this was a case, kindly avoid using this practice in the future.

3. A few comments on the essence of the work.

 - The authors used interesting approach to collect information from CNC 5-axis machine during its operation. This approach definitely is able to provide important data and can be used for process optimization.

- Fig. 4 shows only part of Hartford 5A-25R 5-axis Machining Center. Fig. 5 demonstrates simulation of cutting process. It would be interesting for readers to see the photo of entire Hartford 5A-25R 5-axis Machining Center and, additionally, enlarged view of processing (cutting) unit.

- The authors compare four different algorithms from sklearn library. It would be interesting to add ensemble-based algorithms to this analysis. The sklearn.ensemble module includes ensemble-based methods for classification, regression and anomaly detection. Additionally, XGBoost is an optimized distributed gradient boosting library designed to be highly efficient, flexible and portable. It implements machine learning algorithms under the Gradient Boosting framework. XGBoost provides a parallel tree boosting (also known as GBDT, GBM) that solve many data science problems in a fast and accurate way. It can be the case, that using ensemble-based gradient boosting algorithms in this research would improve performance metrics.

- Table 2 contains experimental parameters for modeling. In order to obtain energy consumption in watt-hours, the machining time (or machining distance) should be stabilized at certain level. This information should be added to Table 2.

- It is shown, that spindle speed is the most important feature for energy consumption. But this is obvious thing. Power of spindle drive motor is 7.5 kW. Powers of other motors are significantly lower. Is it possible to extract more information from these studies?

- It is found, that 6 Wh for every 1000 rpm increase in spindle speed is achieved. Is this a meaningful value for Machining Center with 20 kW power consumption?

As a conclusion, it should be noted that the authors have performed significant amount of work in a very important field using high-precision equipment. Despite the fact that this version of the manuscript cannot be recommended for publication, I believe that it is possible to improve the article significantly in a reasonable amount of time.

There is no problems in English. But the style of the article is inappropriate for scientific papers.

Author Response

1. Quality of English Language:

   • Reviewer's Comment: Moderate editing of English language required.
   • Response: Thank you for highlighting the need for moderate editing. We appreciate your feedback, and we will thoroughly review and edit the manuscript to improve the overall clarity and fluency of the language.

2. Content Contextualization:

   • Reviewer's Comment: Content is not succinctly described and contextualized with respect to previous and present theoretical background and empirical research.
   • Response: We acknowledge the reviewer's concern and will make necessary adjustments to ensure that the content is more succinctly described and well-contextualized within the existing theoretical framework and empirical research.

3. Relevance of Cited References:

   • Reviewer's Comment: All the cited references are relevant to the research.
   • Response: We appreciate the acknowledgment of the relevance of our cited references. We will ensure that all references contribute meaningfully to the research and align with the study's objectives.

4. Clarity of Research Design, Questions, Hypotheses, and Methods:

   • Reviewer's Comment: The research design, questions, hypotheses, and methods are not clearly stated.
   • Response: We value this feedback and understand the importance of clarity in presenting our research design, questions, hypotheses, and methods. We already revise and enhance these sections to provide a clearer understanding of our study.

5. Coherence of Arguments and Discussion:

   • Reviewer's Comment: The arguments and discussion of findings are coherent, balanced, and compelling.
   • Response: We are pleased to hear that our arguments and discussion have been found coherent, balanced, and compelling. We will ensure to maintain this standard and make any necessary enhancements for further clarity.

6. Presentation of Empirical Research Results:

   • Reviewer's Comment: The results for empirical research are clearly presented.
   • Response: We appreciate the positive feedback on the presentation of our empirical research results. We will review the results section to maintain clarity and enhance it further if needed.

7. Adequacy of Referencing:

   • Reviewer's Comment: The article is adequately referenced.
   • Response: We thank the reviewer for confirming the adequacy of our referencing. We will ensure that all relevant sources are appropriately cited and contribute effectively to the scholarly context.

8. Support for Conclusions:

   • Reviewer's Comment: The conclusions are not thoroughly supported by the results presented in the article or referenced in secondary literature.
   • Response: We recognize the importance of strong support for our conclusions. We will carefully review and strengthen the connection between our conclusions and the presented results and relevant secondary literature.

Author Response File: Author Response.pdf

Reviewer 3 Report

This paper utilizes the machine learning algorithms to explore the potential relationship between the machining parameters and the energy consumption. The experiments are carried out using a CNC 5-axis milling machine with various machining parameters, toolpath planning, and dry cutting condition. The results show that there is a strong correlation between spindle speed and energy consumption. In addition, the machine learning regression algorithms like Decision Tree Regressor and Random Forest Regressor can well fit the relationship between machining parameters and energy consumption. The paper is well organized but has few innovations. There has been a lot of research on modeling and optimizing the energy consumption of machine tools based on intelligent algorithms such as machine learning and deep learning. Therefore, this paper is not innovative to carry out research on energy consumption of machine tools using existing machine learning regression algorithms. And there are some suggestions for the authors:

(1)   Energy optimization is mentioned in the title and abstract of this paper, but there is no energy optimization related content in the paper. Therefore, it is recommended that the authors revise the title and abstract to match the content in the text.

(2)   It is recommended that the review in Section 2.1 be placed in Section 1. In addition, the Section 2.1 should focus on a detailed introduction of the machine learning algorithms used.

(3)   How were the machining parameters determined for the nine experimental data in Table 2? In addition, were the results of the subsequent experiments based on the data in Table 2 or on the comprehensive dataset containing 243 data points mentioned in the text? How was the dataset divided for machine learning model training and testing? It is recommended that the authors give a detailed explanation.

(4)   In Table 3, the term Constant and the value “0.93-0.33” in Experiment 1 are confusing. And, why is the T-value for depth of cut in Experiment 1 empty? Why is the R-squared expressed as a percentage?

(5)   The meaning of the vertical axis of Figure 6 and the title of the figure are not clearly explained.

(6)   In Line 447-448, “Figure 6” should be replaced by “Figure 7”.

(7)   In Section 3.2, the English is poorly expressed and even has a lot of speech defects. And the expressions “seepage loss” and “elevation” are confusing.

(8)   In Section 3.2, the analysis in the last paragraph about energy consumption optimization is not related to the previous results. It is recommended that the authors remove it.

(1)   It is recommended that the author check the format of the article carefully and improve the poor English expressions.

Author Response

We appreciate the reviewer's feedback on the quality of English language in the paper. We acknowledge the need for moderate editing to enhance the clarity and coherence of the language. The manuscript has undergone thorough revisions, addressing the identified language issues and ensuring improved readability. We believe these modifications contribute to an overall enhancement of the manuscript's language quality. We value the reviewer's input and are committed to delivering a polished and well-presented final version of the paper.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The manuscript has been corrected and supplemented.

Reviewer 2 Report

Abstract

(16) “Furthermore, the relationship between…” > “The relationship between…”

(17-18) “Subsequently, a machine learning algorithm was developed to classified test method…” > “The machine learning algorithm was developed to classify test methods…”

(19) “…algorithm was implemented and assessed using different classification methode…” >

“…algorithm was implemented and assessed using different classification methods…”

(23) What is RMSE?

(23-24) “…compared to Linear, Lasso and Ridge regression algorithm.” > “…compared to Linear, Lasso and Ridge regression algorithms.”

(24-25) “By integrating conventional and advance regression algorithm into the CNC machining process…” > “By integrating conventional and advanced regression algorithms into the CNC machining process…”

 Keywords

(27) “machine learning methode” > “machine learning methods”

 Introduction

(36) “…promote environmentally conscious methodologies.” > “…promote environment friendly methodologies.”

(38-40) “Through a series of carefully designed experiments conducted on a CNC 5-axis milling  37 machine, this study investigates the complex interaction between various machining parameters, innovative toolpath planning strategies, and consequential energy consumption patterns.”  It is too early to speak about your work here! Introduction should be finished just with focusing on unsolved problem(s) in the area of research and setting the goal for your research. Do not speak about your research in the Introduction.

 I cannot agree with introduction in its present form. You should rewrite it totally in order to proceed. Focus on the subject of implementing ML in manufacturing, not on carbon footprint. You made no experiments concerning evaluation of CO2 emission. Do not speculate on carbon footprint. Drop out Fig. 1 and Fig. 2. They are not relevant to your research. Once more, write acceptable introduction. Make the analysis of implementing ML in manufacturing industry, show significant achievements of different researchers and underline unsolved issues. Then in the last paragraph of Introduction you should state that your research is aimed to solve some given abovementioned issue. No more words about your research.

 Once the introduction is in an acceptable state, it would be possible to talk about the rest of the manuscript.

Minor editing of English language required

Author Response

please see the attachment

Author Response File: Author Response.pdf

Reviewer 3 Report

The response has answered most of my concerns. However, I think the novelty of the proposed algorithm in this paper is still not enough for publication:

(1) Modeling the energy consumption of machine tools is the main focus of this article, and changing the title from "energy optimization" to "energy efficiency" is still not appropriate. In addition, the last sentence of the abstract about "energy savings" is not supported by experimental results.

(2) This paper carries out experiments with a variety of machine learning algorithms for modeling the energy consumption of machine tools and does not contribute substantially to the algorithms themselves. Furthermore, this work has been extensively researched.

(3) The results in Figure 8 see that the correlation coefficient between energy consumption and spindle speed is -0.8, which then indicates that the two are negatively correlated. But intuitively speaking, the two should be positively correlated. The higher the spindle speed, the higher the energy consumption. Therefore, the results of this experiment need to be revisited by the authors.

(4) There are still multiple formatting errors in the text. For example, the caption of Figure 7 is about power, but the figure is about energy consumption.

Author Response

please see the attachment

Author Response File: Author Response.pdf