Research on Real-Time Monitoring and Performance Optimization of Suspension System in Maglev Train
Round 1
Reviewer 1 Report
Dear Authors,
The analysis is about an interesting and actual issue.
I find the paper well organized and lecture is proper of a scientific paper
Perhaps, some sections are too long and certainly the conclusions are poor. I recommend rewriting them by better emphasizing the objective results of the analysis carried out, highlighting well the contribution provided and its limitations.
Author Response
Dear reviewer:
Thank you very much for your review comments. Based on your suggestions, we have updated the manuscript. More details are in the PDF.
Yours Sincerely
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Mentions of the residual fluctuations (para 1, page 10, Fig 6, Fig 7b, Fig 9, and what should be Fig 11) should have units of measurement included.
Fig 10 is listed twice and line 394 should be Fig 11.
Author Response
Dear reviewer:
Thank you very much for your review comments. Based on your suggestions, we have updated the manuscript. More details are in the PDF.
Yours Sincerely
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 introduction part should discuss the previous literature in deeper way rather than just mentioning them. the novelty of the research is not clear compared to other publication that deal with the same problem.
2- the experimental part should give more information about the system. for example, where the numbers/parameters that presented in equation 29 and 30 come from? So, the experimental part need to be expanded.
3- Conclusion part is very short and does not summaries the main findings sufficiently. The limitations of the proposed method has not been discussed.
Author Response
Please see the attachment.
Author Response File: 
Author Response.docx
Reviewer 2 Report
The paper proposed a data-driven approach to optimize the performance for maglev train controller through evaluating the residual signals. The authors have explained the system structure clearly. However, the results doesn't strongly support the arguments of the authors. In Figure 10 and table 1, only the peak and dead time/adjust time are presented. As the core of the algorithm, the residual signals are not used to evaluate the results. The peak of the gap is not significantly reduced during the optimzation process. The review of literatures is not sufficient.
There are still some points in the text need to be further explained and modified:
page 1 row 33: "improve the life cycle" is not correct English, can be modified as "reduce the life cycle costs"
page 2 row 53, 68, and page 6 195 - 202: The description about the degraded situations is not clear. The performance evalaution and classification of degradation explained in section 3.3 should be presented earlier.
page 2 row 89, "based on data-driven" is not correct English, can be modified as "based on data-driven approaches"
page 3 row 101: Should "T" be "The"? page 6 row 221: "... the residual generator constructed in 4.2", please change 4.2 to 3.2
page 6 section 3.3: the thresholds and the three degration levels are not used in this article. page 7 row 249: the parameters used for optimization in equation (13) should be explained.
page 7 row 253: why the input u(k) are also included in the cost function in equation (14)? please explain it.
page 8 row 309: what' the meaning "the suspension gap can track the given value"?
in Figure 8 and 9, the color for "with degration" and "without degration" should be consistent.
page 11 row 365: the text should be removed page 11 row 368: please describe the stop condition
page 12 row 378: please explain the meaning "sucked to death" (dead time).
Author Response
Response to Reviewer Comments
Point 1: As the core of the algorithm, the residual signals are not used to evaluate the results. The peak of the gap is not significantly reduced during the optimzation process. The review of literatures is not sufficient.
Response 1: We have renewed the introduction and the conclusion. Peak value is only one part in the optimization. And the residual signals are used to evaluate the results.
Point 2: page 1 row 33: "improve the life cycle" is not correct English, can be modified as "reduce the life cycle costs"
Response 2: We have modified.
Point 3: page 2 row 53, 68, and page 6 195 - 202: The description about the degraded situations is not clear. The performance evaluation and classification of degradation explained in section 3.3 should be presented earlier.
Response 3: We have updated the description of the performance evaluation and classification sections. This article does not make specific performance evaluation and classification, so detailed data cannot be provided to support performance classification.
Point 4: page 2 row 89, "based on data-driven" is not correct English, can be modified as "based on data-driven approaches"
Response 4: We have modified.
Point 5: page 3 row 101: Should "T" be "The"? page 6 row 221: "... the residual generator constructed in 4.2", please change 4.2 to 3.2
Response 5: We have modified.
Point 6: the thresholds and the three degration levels are not used in this article. page 7 row 249: the parameters used for optimization in equation (13) should be explained.
Response 6: the thresholds and the three levels are used in other article, this paper only gives a simple threshold setting scheme. The parameters in equation (13) can be found in [21].
Point 7: page 7 row 253: why the input u(k) are also included in the cost function in equation (14)? please explain it.
Response 7: This is the expression of the linear quadratic index. More information is shown in [35].
Point 8: page 8 row 309: what' the meaning "the suspension gap can track the given value"?
Response 8: We have modified.
Point 9: in Figure 8 and 9, the color for "with degration" and "without degration" should be consistent.
Response 9: Thanks for your guidance. But in my opinion, different colors can distinguish between normal operation and degration.
Point 10: page 11 row 365: the text should be removed page 11 row 368: please describe the stop condition.
Response 10: We have updated the manuscript.
Point 11: page 12 row 378: please explain the meaning "sucked to death" (dead time).
Response 11: We have updated the manuscript.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
I could not see any improvement in both the literature review and the conclusion parts.
so I will give same feedback for point 1 and point 3 in my last report. As the author response has not make any improvement in these two part of the paper.
Point 1: The introduction part should discuss the previous literature in deeper way rather than just mentioning them. the novelty of the research is not clear compared to other publication that deal with the same problem.
Point 3: Conclusion part is very short and does not summaries the main findings sufficiently. The limitations of the proposed method has not been discussed.
Author Response
Dear reviewer：
Due to my operation error, the revised file was not sent to you last time. We apologize for the inconvenience caused.
Point 1: The introduction part should discuss the previous literature in deeper way rather than just mentioning them. the novelty of the research is not clear compared to other publication that deal with the same problem.
Response 1: We have renewed the introduction.
Point 2: the experimental part should give more information about the system. for example, where the numbers/parameters that presented in equation 29 and 30 come from? So, the experimental part need to be expanded.
Response 2: Parameters that presented in equation 29 are converted by PID controller. Parameters that presented in equation 30 are obtained through identification. Specific steps are shown in [43].
Point 3: Conclusion part is very short and does not summaries the main findings sufficiently. The limitations of the proposed method has not been discussed.
Response 3: We have revised the conclusion.
Author Response File: Author Response.pdf
Reviewer 2 Report
The authors has responsed to mosted of the concerned questions. However, for the point 9:
I still think it is meaning full to use blue color for "without degration" and to use orange color for "with degration" in Fig. 9. Then it is consistent with Fig. 8.
I recommend to accept the manuscript with minor revision.
Author Response
Dear reviewer：
We have updated the figure according to your comments.
Author Response File: Author Response.pdf
