Research on Sintering Machine Axle Fault Detection Based on Wheel Swing Characteristics

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

In this manuscript, the authors propose a fault detection method based on YOLOv9 target detection algorithm and frame difference method for sintering machine trolley wheel swing. The effectiveness of the proposed method is validated through a series of experiments.

There are some concerns that need to be addressed as follows:

1. Figures 3 and 7 are not clear.

2. Lack of experimental comparisons.

3. The analysis and discussion of the experimental results are not sufficient.

4. The English writing is not satisfactory, and the writing quality of this manuscript needs to be greatly improved.

Comments on the Quality of English Language

Extensive editing of English language are required.

Author Response

1.First of all, we thank the reviewers for their valuable comments on our paper, which helped us to further improve the article. According to the problems you pointed out, we have revised the manuscript, and in the resubmitted manuscript, the blue font with strikethrough is the deleted content, and the red font is the revised content. For your review, we have also provided a version of the revised, unmarked version. 

2.Please see the attachment for specific responses to comments

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

This submission reports use of YOLOv4 for the status monitoring of sintering machines. The status monitoring is an important engineering problem, and the proposed methodology may contribute to the advancement in the relevant fields. The required major revions are

1.     YOLOv4 is used throughout the manuscript. Since YOLOv4 is the name of the algorithm, it would be better to emphasize the algorithm itself.

2.     The axle detection is used as the status identification. It is recommended to compare the results with previously suggested methodologies, for example some vibration-measurement based method.

3.     Figures 1 and 2 are hard to correlate to each other. It is recommended to show correlation between the two figures.

4.     Figure 3 shows YOLGv4 algorithm. It is recommended to delete previously presented results, and shows only the newly proposed algorithm, 

5.     Figure 4, Wheel 0.97? what is the meaning of 0.97?

6.     Figure 9 is not required in the submission. Please emphasize only the academic contribution.

Author Response

1.First of all, we thank the reviewers for their valuable comments on our paper, which helped us to further improve the article. According to the problems you pointed out, we have revised the manuscript, and in the resubmitted manuscript, the blue font with strikethrough is the deleted content, and the red font is the revised content. For your review, we have also provided a version of the revised, unmarked version. 

2.Please see the attachment for specific responses to comments

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

Please see attached file

Comments for author File: Comments.pdf

Comments on the Quality of English Language

Author Response

1.First of all, we thank the reviewers for their valuable comments on our paper, which helped us to further improve the article. According to the problems you pointed out, we have revised the manuscript, and in the resubmitted manuscript, the blue font with strikethrough is the deleted content, and the red font is the revised content. For your review, we have also provided a version of the revised, unmarked version. 

2.Please see the attachment for specific responses to comments

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

This manuscript can be accepted.

Comments on the Quality of English Language

 Moderate editing of English language required.

Reviewer 2 Report

Comments and Suggestions for Authors

The reviewer comments were addressed with relevant revisions.