A Generic Multi-Objective Optimization of Machining Processes Using an End-to-End Evolutionary Algorithm
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThis work studied a methodology to use multi objective GA to achieve multi objective optimization for machining processes. The Pareto front is calculated for final solution selection.
There are several very critical issues in this work that needs to be addressed.
1. When for each individual result of a machining process, cutting force, energy, surface roughness, etc. there are already established physics modeling based or machine learning based methods to estimate those result, why in this work some of the parameters are calculated using physics model some uses machine learning model is unclear.
2. For the ones that uses physics model, proper citations are not provided.
3. All the data-driven machine learning based models, the data collection, training, and accuracy of such trained models are not provided. And as a result, it is unclear how those models perform in this work.
4. Is the paper talking about multi-step optimization or multi-step machining process? The reviewer finds both mixed used in this work. It seems should be the optimizations are happening for each step within a multi-step machining process. Please clarify and make it clear.
Comments on the Quality of English LanguagePlease also go through a thorough editing of this manuscript. There are many typos, wrong grammars, and ambiguous sentences in this work. The English language problem may contribute heavily for the audience to not well understanding this work, including the aforementioned critical issues the reviewer have identified.
Author Response
Please see the attachment.
This work studied a methodology to use multi objective GA to achieve multi objective optimization for machining processes. The Pareto front is calculated for final solution selection.
There are several very critical issues in this work that needs to be addressed.
Comment 1. When for each individual result of a machining process, cutting force, energy, surface roughness, etc. there are already established physics modeling based or machine learning based methods to estimate those result, why in this work some of the parameters are calculated using physics model some uses machine learning model is unclear.
Response: We are sorry for our unclear statements, we are intended to illustrate that the proposed method proposed in this paper can be well adopted to different kinds of objective functions, i.e., physics, machine learning or hybrid. To make this point clearer, an additional framework about the exploitation of the proposed method is presented in this paper.
Comment 2. For the ones that uses physics model, proper citations are not provided.
Response: According to the reviewer’s comments, the citations are provided in the revised manuscript. And it has been highlighted using red font.
Comment 3. All the data-driven machine learning based models, the data collection, training, and accuracy of such trained models are not provided. And as a result, it is unclear how those models perform in this work.
Response: According to the reviewer’s comment, the corresponding contents are added in the revised manuscript. The details refereeing to the training process and data collection are added in the Section 4.1. And the accuracy analysis is provided in the Section 4.2. To make the readers more clearer, all of the revised part are highlighted using red font.
Comment 4. Is the paper talking about multi-step optimization or multi-step machining process? The reviewer finds both mixed used in this work. It seems should be the optimizations are happening for each step within a multi-step machining process. Please clarify and make it clear.
Response: We are sorry for our unclear statements, we want to propose a novel optimization method, which are suitable for both the single-step machining and multi-step machining process. To make this idea more clearer, the corresponding descriptions are unified in the revised paper.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsThe research presents a promising approach to optimizing machining process parameters with a novel framework. However, to maximize its impact and applicability, the study could benefit from expanded validation, incorporation of real-time data and AI, a focus on environmental and economic impacts, user-friendly implementation, and scalability. By addressing these areas, the research could contribute even more significantly to the field of manufacturing optimization and provide practical solutions for industry challenges. For example:
· - Integrating real-time data collection and AI-driven adjustments could enhance the framework’s adaptability. For example, using sensors to monitor machining conditions and feeding this data into the optimization algorithm could allow for continuous parameter adjustments, leading to more precise and efficient machining.
· - Machine learning models could be incorporated to predict machining outcomes based on historical data, which would allow the framework to learn and improve over time. This could also help in identifying optimal parameters more quickly by reducing the search space.
· - Given the increasing importance of sustainable manufacturing, the research could include a more detailed assessment of the environmental impact of the optimized parameters. This might involve measuring energy consumption, waste reduction, or carbon footprint associated with different machining setups.
Regarding the conclusions:
· - The conclusion could benefit from a more explicit connection between these contributions and their practical implications in the manufacturing industry. For instance, how does the proposed method specifically improve machining outcomes like efficiency, quality, or environmental impact?
· - The discussion could be enriched by providing examples or scenarios where this flexibility would be particularly advantageous. This would help readers better understand the practical significance of the method in real-world settings.
· - One improvement is explicitly connecting the proposed method to tangible benefits in manufacturing, such as reduced production costs, enhanced product quality, or lower environmental impact. This would reinforce the practical relevance of the research.
· - Consider expanding the scope of future work beyond optimization speed. For instance, exploring the integration of real-time monitoring systems, predictive maintenance, or the use of digital twins in the optimization process could offer exciting new research directions.
Author Response
The research presents a promising approach to optimizing machining process parameters with a novel framework. However, to maximize its impact and applicability, the study could benefit from expanded validation, incorporation of real-time data and AI, a focus on environmental and economic impacts, user-friendly implementation, and scalability. By addressing these areas, the research could contribute even more significantly to the field of manufacturing optimization and provide practical solutions for industry challenges.
Comment 1: For example: Integrating real-time data collection and AI-driven adjustments could enhance the framework’s adaptability. For example, using sensors to monitor machining conditions and feeding this data into the optimization algorithm could allow for continuous parameter adjustments, leading to more precise and efficient machining.
Response: We are grateful for your comments. Admittedly, this integration between real-time data collection and AI-driven adjustments could enhance the framework’s adaptability. While, the main purpose of this paper is to provide an optimization method for the single-step or multi-step machining process. In the next study, we would like to realize your ideas, and we hope we can make a cooperation about this study.
Comment 2: Machine learning models could be incorporated to predict machining outcomes based on historical data, which would allow the framework to learn and improve over time. This could also help in identifying optimal parameters more quickly by reducing the search space.
Response: As commented by the reviewer, the machine learning models could be incorporated to predict machining outcomes. Thus, this paper has taken the machine learning into consideration to develop the objective functions. To make this point clearer, the framework marked using Fig. 1 is added in the revised manuscript.
Comment 3: Given the increasing importance of sustainable manufacturing, the research could include a more detailed assessment of the environmental impact of the optimized parameters. This might involve measuring energy consumption, waste reduction, or carbon footprint associated with different machining setups.
Response: We are grateful with the reviewer’s opinion, the sustainable manufacturing is considered in this paper. The indicators for the sustainable aspect are the energy consumed in the machining process. And the corresponding descriptions about the sustainable indicators are added in the Section 2.2, and highlighted using red font.
Regarding the conclusions:
Comment 4: The conclusion could benefit from a more explicit connection between these contributions and their practical implications in the manufacturing industry. For instance, how does the proposed method specifically improve machining outcomes like efficiency, quality, or environmental impact?
Response: We are grateful with the reviewer’s opinion, the corresponding contents have been improved as your requirements.
Comment 5: The discussion could be enriched by providing examples or scenarios where this flexibility would be particularly advantageous. This would help readers better understand the practical significance of the method in real-world settings.
Response: As commented by the reviewer, the discussion about the flexibility is provided in the revised manuscript. The corresponding contents are presented in the Section 5, and highlighted using red font.
Comment 6: One improvement is explicitly connecting the proposed method to tangible benefits in manufacturing, such as reduced production costs, enhanced product quality, or lower environmental impact. This would reinforce the practical relevance of the research.
Response: We are very agreeing with the reviewer’s comment, the goal of the optimization in the manufacturing industry is to pursue a higher quality, higher efficiency and lower environmental impact. To this end, the optimization objectives selected in this paper are surface roughness, material removal rate and energy consumption. Besides, the cutting force is also provided in this paper as the objectives, which further ensure the machined quality.
Comment 7: Consider expanding the scope of future work beyond optimization speed. For instance, exploring the integration of real-time monitoring systems, predictive maintenance, or the use of digital twins in the optimization process could offer exciting new research directions.
Response: As commented by reviewer, the scope of future work is taking more consideration about the integration of real-time monitoring systems, predictive maintenance, or the use of digital twins in the optimization process could offer exciting new research directions.
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for AuthorsDear Authors,
The paper titled "A Generic Multi-Objective Optimization of Machining Process Using an End-to-End Evolutionary Algorithm" represents a significant contribution to the field of machining process optimization. However, there are some issues that could be improved:
The Abstract must have the following logic:
Purpose; Design/methodology / approach; Findings; Practical implications; Originality/ value;
The conclusion must have:
Remember the objective of the study
Main findings
Theoretical and practical implications
Originality of the study
Study limitations
Future lines of research
- Additional questions:
• Methodology Clarification: Could the authors provide a more detailed explanation of the methodologies applied in the study? Specifically, what were the criteria for selecting the algorithms used, and how do they compare to alternative methods in the literature?
• Algorithm Selection: What were the main factors that influenced the choice of the specific algorithms implemented in the research? Were there other algorithms considered, and if so, why were they ultimately not used?
• Pseudo-code Provision: It would be beneficial for the readers to understand the detailed implementation of the algorithms. Could the authors provide pseudo-codes for each of the algorithms utilized in the study? This will help in replicating the work and validating the results.
• Novelty in Algorithm Design: The manuscript mentions that certain innovations were introduced in the algorithms. Could the authors elaborate on these innovations? Specifically, how do these modifications improve upon existing methods, and can this be clearly demonstrated within the pseudo-codes?
Author Response
The paper titled "A Generic Multi-Objective Optimization of Machining Processes Using an End-to-End Evolutionary Algorithm" represents a significant contribution to the field of machining process optimization. However, there are some issues that could be improved:
The Abstract must have the following logic: Purpose; Design/methodology / approach; Findings; Practical implications; Originality/ value;
Response：According to the reviewers ‘comment, the corresponding contents have been improved. The improved abstract is as follows:
Abstract: Machining processes have been widely employed in the modern manufacturing industry to transform raw materials into final products, and they are of great importance in improving the environmental impact and production efficiency of this industry. The selection of appropriate machining process parameters can effectively improve the environmental impact and production efficiency of a process. However, most existing studies on the optimization of these parameters have targeted optimization techniques or modeling methods, and have seldom taken into consideration the adaptability of the machining process. Thus, they suffer from poor generalization and flexibility in actual deployment. Based on this, a generic optimization framework based on the end-to-end evolutionary algorithm was proposed in this study, which can be adapted to various machining optimization problems, to guide the operators in selecting the best parameters in an automated way. Firstly, a modeling framework was introduced to guide the operators to develop optimization objectives. Subsequently, a flexible optimization algorithm was employed to generate Pareto front solutions. Finally, the CRITIC-TOPSIS method was employed to provide a final solution from the different Pareto solutions generated. Experiments were conducted on a milling machine to demonstrate the effectiveness and advantages of the proposed method. The results showed that the proposed method is flexible and applicable for the optimization of the different machining steps and objectives.
The conclusion must have: Remember the objective of the study, Main findings, Theoretical and practical implications, Originality of the study, Study limitations, Future lines of research
Response：According to the reviewers ‘comment, the corresponding contents have been improved. The revised part are highlight as red font in the revised manuscript.
- Additional questions:
• Methodology Clarification: Could the authors provide a more detailed explanation of the methodologies applied in the study? Specifically, what were the criteria for selecting the algorithms used, and how do they compare to alternative methods in the literature?
• Algorithm Selection: What were the main factors that influenced the choice of the specific algorithms implemented in the research? Were there other algorithms considered, and if so, why were they ultimately not used?
Response: We are sorry for unclear statements, the main purpose of this study is to provide a generic optimization method, and this generic optimization method can be adopted to different objectives, which is formed using different algorithms, such as machine learning, physics-machine learning hybrid and physical model. Those different type of objectives can be unified and served as the objective functions in this paper. To make this point clearer, the corresponding contents have been rewritten, and a framework is added in the revised paper marked using Fig. 1.
Pseudo-code Provision: It would be beneficial for the readers to understand the detailed implementation of the algorithms. Could the authors provide pseudo-codes for each of the algorithms utilized in the study? This will help in replicating the work and validating the results.
Response: As commented by the reviewer, the pseudo-codes for the NSGA-II and TOPSIS are both supplied in the revised manuscript.
- Novelty in Algorithm Design: The manuscript mentions that certain innovations were introduced in the algorithms. Could the authors elaborate on these innovations? Specifically, how do these modifications improve upon existing methods, and can this be clearly demonstrated within the pseudo-codes?
Response: We are sorry for our unclear statements, the innovations of this paper is to develop an end-to-end framework, which incorporates the different modeling method into together to fulfill an optimization. The innovations of the algorithm are not put a high attention in this paper. Admittedly, the employed modeling algorithm and optimization algorithm usually suffers some limitations during the application stage. In the future, the improvement in the algorithm would be conducted.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Comments and Suggestions for AuthorsThanks for making the revisions.
The updates look good to me.
