Multi-Robot Collaborative Flexible Manufacturing and Digital Twin System Design of Circuit Breakers
Round 1
Reviewer 1 Report
The article under review presents a multi-robot cooperative flexible manufacturing system (FMS) proposed by the authors, which implements the automatic manufacturing of circuit breakers (CBs).
In the Introduction and Related Work sections, the prerequisites for conducting research are considered: the design and purpose of circuit breakers are described; the expediency of the transition from semi-automated production to the multi-robot cooperative FMS proposed by the authors is indicated. In the main parts of the paper, a dual robot arm collaborative control strategy is presented: an analysis of forward and inverse kinematics is given; a cooperative space analysis of the dual robot arm is given too; a trajectory optimization of the dual robot arm is considered (in this case, the authors propose to use the deep deterministic policy gradient (DDPG) algorithm). The results of simulation experiments are presented. Part of the paper is devoted to the design of a digital twin (DT) system for a multi-robot cooperative FMS. The results of system feasibility verification proposed by the authors are presented. It is shown that the overall assembly efficiency of circuit breakers is increased by 22%.
In general, this is an interesting paper that can be useful to specialists in the field of Industry 4.0. However, during the review, I would give the authors the following recommendations, which, in my opinion, would improve the quality of the paper:
- The paper contains many abbreviations that are deciphered on the first reading. Nevertheless, for the convenience of readers, I consider it appropriate to collect all the abbreviations and give their transcripts at the end of the paper.
- I suggest that the authors supplement the Introduction section by giving clear statements of the purpose and objectives of their research, and also provide a description of the structure of the paper at the end of the section.
- In my opinion, the authors should explain the choice of the Deep Deterministic Policy Gradient (DDPG) algorithm. It is possible to give in the Introduction section its advantages and disadvantages in application to the problem solved in the paper with other machine learning algorithms.
- In some figures, for example, Figures 2, 7, 8 and 20, some inscriptions are difficult to read. This needs to be corrected.
- In my opinion, in the Conclusion section, the scientific achievements of the authors obtained as a result of the presented study should have been more clearly formulated.
- Do the authors of the paper have plans for further research? I propose to describe them at the end of the paper.
I would like to thank the authors for the quality research and congratulate the authors on a well-prepared article. I recommend this article for publication after minor revision.
Author Response
Thank you for your precious comments and advice. Those comments are all valuable and very helpful for revising and improving our paper. We have revised the manuscript accordingly，and our point-by-point responses are presented as fllows：
Q1. The paper contains many abbreviations that are deciphered on the first reading. Nevertheless, for the convenience of readers, I consider it appropriate to collect all the abbreviations and give their transcripts at the end of the paper.
Response: Thank you for your suggestion. As suggested by reviewer, we have added the suggested content to the manuscript on page 27.
Q2. I suggest that the authors supplement the Introduction section by giving clear statements of the purpose and objectives of their research, and also provide a description of the structure of the paper at the end of the section.
Response: Thank you for your suggestion. As suggested by reviewer, we have added the suggested content to the manuscript on Introduction (Page 2,3).
Q3. In my opinion, the authors should explain the choice of the Deep Deterministic Policy Gradient (DDPG) algorithm. It is possible to give in the Introduction section its advantages and disadvantages in application to the problem solved in the paper with other machine learning algorithms.
Response: Thank you for your suggestion. The advantages and disadvantages of DDPG algorithm compared with other machine learning algorithms are introduced in the manuscript (page 3) by reference [25,26,27,28,29], and its advantages are analyzed.
Q4. In some figures, for example, Figures 2, 7, 8 and 20, some inscriptions are difficult to read. This needs to be corrected.
Response: Thank you for your suggestion. As suggested by reviewer, we improved the quality of Figure 2, 7, 8 and 20 in the manuscript.
Q5. In my opinion, in the Conclusion section, the scientific achievements of the authors obtained as a result of the presented study should have been more clearly formulated.
Response: Thank you for your suggestion. As suggested by reviewer, I revised the conclusion according to the scientific nature of the study and summarized it according to the main points to make it clearer (page 26).
Q6. Do the authors of the paper have plans for further research? I propose to describe them at the end of the paper.
Response: Thank you for your suggestion. As suggested by reviewer, we summarized the current work and analyzed the future research, and summarized the future outlook in the last part of the conclusion (Page 26).
Thank you for your careful review. We really appreciate your efforts in reviewing our manuscript during this unprecedented and challenging time. We wish good health to you, your family, and community. Your careful review has helped to make our study clearer and more comprehensive.
Reviewer 2 Report
The authors provided a manuscript focused on automatizing the circuit breakers manufacturing process by implementing digital twin technology. The manuscript is quite extensive and provides detailed information. Nevertheless, I noticed some issues to be improved:
The quality of figure 7 should be improved. Some fonts are too small and hardly readable.
The reference for table 1 is missing.
Lines 206-261 spaces between values and units are missing.
The title of Figure 6 states that it is a dual robot arm, but actually, it shows two separate robots, and it is clearly seen from all provided content, therefore, the inaccurate definition must be improved.
Author Response
Thank you for your precious comments and advice. Those comments are all valuable and very helpful for revising and improving our paper. We have revised the manuscript accordingly，and our point-by-point responses are presented as fllows：
Q1. The quality of figure 7 should be improved. Some fonts are too small and hardly readable.
Response: Thank you for your suggestion. According to the reviewer's suggestion, we improved the quality of Figure 7 in the manuscript (page 8).
Q2. The reference for table 1 is missing.
Response: Thank you for your suggestion. However, Table 1 shows the parameters of robots. Different models of robots are different. It is difficult to have a reference. So we are sorry for not having a reference.
Q3. Lines 206-261 spaces between values and units are missing.
Response: Thank you for your suggestion. As suggested by reviewer, we have revised the proposed contents of the manuscript.
Q4. The title of Figure 6 states that it is a dual robot arm, but actually, it shows two separate robots, and it is clearly seen from all provided content, therefore, the inaccurate definition must be improved.
Response: Thank you for your suggestion. As suggested by reviewer, we have revised the proposed contents of the manuscript.
Thank you for your careful review. We really appreciate your efforts in reviewing our manuscript during this unprecedented and challenging time. We wish good health to you, your family, and community. Your careful review has helped to make our study clearer and more comprehensive.
Reviewer 3 Report
The authors proposed a digital twin (DT) framework to realize flexible manufacturing by multi-robot cooperative cell for Circuit breakers (CBs). The proposed DT system illustrates a kinematic control model of the collaboration robot. The topic is the interest in the current industrial problems and for various manufacturing applications. The author's attempt is well appreciated.
There exist numerous pieces of literature on human-robot collaboration and DT, it is recommended to expand the introduction.
Bilberg, Arne, and Ali Ahmad Malik. "Digital twin driven human–robot collaborative assembly." CIRP annals 68.1 (2019): 499-502.
Inkulu, Anil Kumar, MVA Raju Bahubalendruni, and Ashok Dara. "Challenges and opportunities in human robot collaboration context of Industry 4.0-a state of the art review." Industrial Robot: the international journal of robotics research and application 49.2 (2022): 226-239.
It is recommended to use a exploded view for figure 1.
Figure 3, give subtitles (a) (b) for the two illustrations.
The framework in figure 7 consists of the physical model for the robot, and how the physical entities (like parts, etc.,) are built in the virtual space. How the feedback mechanism is constructed.?
Improve the quality of figure 7. And give the appropriate connections.
Fig 20, 21 give the captions for subfigures.
The authors are recommended to search and expand the literature with these keywords. “Challenges and opportunities in human-robot collaboration”; “Challenges and opportunities on AR/VR technologies” “ar vr for HRI”.
Author Response
Thank you for your precious comments and advice. Those comments are all valuable and very helpful for revising and improving our paper. We have revised the manuscript accordingly，and our point-by-point responses are presented as fllows：
Q1. There exist numerous pieces of literature on human-robot collaboration and DT, it is recommended to expand the introduction.
Response: Thank you for your suggestion. As suggested by reviewer, we added the suggested content in the introduction (pages 1,2).
Q2. It is recommended to use a exploded view for figure 1.
Response:Thank you for your suggestion. As suggested by reviewer, we revised Figure 1 in the manuscript (page 4).
Q3. Figure 3, give subtitles (a) (b) for the two illustrations.
Response: Thank you for your suggestion. As suggested by reviewer, we revised Figure 3 in the manuscript (page 5).
Q4. The framework in figure 7 consists of the physical model for the robot, and how the physical entities (like parts, etc.,) are built in the virtual space. How the feedback mechanism is constructed.?
Response:The feedback mechanism of the system framework is as follows: Firstly, physical unit data is obtained from external devices and the virtual model is assigned the attributes of physical entities. Secondly, data is transferred to the workstation, then data is processed by the workstation to build a digital twin system, including algorithm optimization, robot kinematics control, model data optimization and so on. Finally, data transmission in the DT system is operated by data communication mechanism to DT system visualization service. To sum up, the feedback mechanism is realized through the data interaction between the physical unit and the virtual unit (page 7).
Q5. Improve the quality of figure 7. And give the appropriate connections.
Response: Thank you for your suggestion. According to the reviewer's suggestion, we have improved the quality of Figure 7 in the manuscript and provided appropriate connections(page 8).
Q6. Fig 20, 21 give the captions for subfigures.
Response: Thank you for your suggestion. As suggested by reviewer, we have made corresponding improvements to the manuscript (page 21).
Thank you for your careful review. We really appreciate your efforts in reviewing our manuscript during this unprecedented and challenging time. We wish good health to you, your family, and community. Your careful review has helped to make our study clearer and more comprehensive.
Reviewer 4 Report
1. Survey of existing literature is not sufficient. It would useful to include in the Introduction of the paper some discussion on other possible real applications of the obtained results and at the end of the literature, the weakness of previous research has to be highlighted.
2. Some abbreviations need to check when writing for the first time, like DT, PLC, DDPG, LOD and FPS.
3. Some notations in equations have not been defined, see eq. 6.
4. What are the main contributions of the paper compared with other previous related works? What is the new in your study? The contribution is not clearly indicated. The author highlighted the conclusion at the end of Section 1, not a contribution. The contribution has to be stated in points.
5. A brief description of the structure of the paper should be added at the end of the introduction section.
6. References [19] are not cited in the text.
7. The cost functions and their behaviors with respect to iteration are not addressed at all.
8. The conclusion has to be extended with future work.
Author Response
Thank you for your precious comments and advice. Those comments are all valuable and very helpful for revising and improving our paper. We have revised the manuscript accordingly，and our point-by-point responses are presented as fllows：
Q1. Survey of existing literature is not sufficient. It would useful to include in the Introduction of the paper some discussion on other possible real applications of the obtained results and at the end of the literature, the weakness of previous research has to be highlighted.
Response: Thank you for your suggestion. As suggested by reviewer, we have added the literature reading survey, and put forward our views and summarized in combination with the weakness of previous research. We put the changes on pages 2 and 3 of the manuscript and highlight them.
Q2. Some abbreviations need to check when writing for the first time, like DT, PLC, DDPG, LOD and FPS.
Response: Thank you for your suggestion. As suggested by reviewer, we have modified the corresponding part and give their transcripts at the end of the manuscript.
Q3. Some notations in equations have not been defined, see eq. 6.
Response: Thank you for your suggestion. As suggested by reviewer, we have modified the corresponding part in the manuscript (Page 10).
Q4. What are the main contributions of the paper compared with other previous related works? What is the new in your study? The contribution is not clearly indicated. The author highlighted the conclusion at the end of Section 1, not a contribution. The contribution has to be stated in points.
Response: Thank you for your suggestion. According to your suggestion, we summarized the contributions in points and explained the contributions made (Page 3).
Q5. A brief description of the structure of the paper should be added at the end of the introduction section.
Response: Thank you for your suggestion. As suggested by reviewer, we have modified the corresponding part in the manuscript (Page 3).
Q6. References [19] are not cited in the text.
Response: Thank you for your suggestion. As suggested by reviewer, we have modified the corresponding part in the manuscript (Page 2).
Q7.The cost functions and their behaviors with respect to iteration are not addressed at all.
Response: Thank you for your suggestion. As suggested by reviewer, we have modified the corresponding part in the manuscript (Page 14,15).
Q8. The conclusion has to be extended with future work.
Response: Thank you for your suggestion. As suggested by reviewer, we summarized the current work and analyzed the future research, and summarized the future outlook in the last part of the conclusion (Page 26).
Thank you for your careful review. We really appreciate your efforts in reviewing our manuscript during this unprecedented and challenging time. We wish good health to you, your family, and community. Your careful review has helped to make our study clearer and more comprehensive.
