A Representation Generation Approach of Transmission Gear Based on Conditional Generative Adversarial Network

Round 1

Reviewer 1 Report

This paper considers the gear reliability challenge of vehicle transmission and develops a representation generation approach based on the generative adversarial network to advance the performance of reliability evaluation as a classification problem. The major comments are as follows:

1. It seems equations (1)-(4) are for the background of generative adversarial networks. Then, suitable reference should be good enough for the discussion here.
2. Two algorithms are provided in the paper. It would be better if the authors can discuss the stability and convergence of the new algorithms.
3. There are some typos and language problem in the paper. For example, in page 7, sentence after equation (6), “The details of our CGAN-based model is in Algorithm ??.” should be “… Algorithm 1”.

Author Response

Thanks for your comments and we have provided a point-by-point response. If you need any further information regarding our paper, please feel free to contact me.

Author Response File: Author Response.pdf

Reviewer 2 Report

Dear Authors, the manuscript is clear, and well-written overall. The manuscript has sufficient originality, and undertaken problem is of practical nature. Although the results presented in the manuscript seem promising and overall approach is contributing to the body of the literature, I encourage the authors to please consider the attached file suggestions to improvise the presented work more prior to its publication. Thanks

Comments for author File: Comments.pdf

Author Response

Thanks for your comments and we have provided a point-by-point response. If you need any further information regarding our paper, please feel free to contact me.

Author Response File: Author Response.pdf

Reviewer 3 Report

Minor changes / typos:

but can be estimated -> but it can be estimated

by the precise of modelling -> by the precision of modelling

And we,after collecting the consent of relevant companies and collecting the data of gear teeth ->
And we, after collecting the consent of relevant companies and the data of gear teeth

ie -> , i.e.,
https://www.merriam-webster.com/dictionary/i.e.

Please check equation (2). One bracket ] is missing.

with the real data. Distribution. -> with the real data distribution.

The details of our CGAN-based model is in Algorithm ??. -> The details of our CGAN-based model is in Algorithm 1.

in the formula Equation 12. -> in (12).

The details are shown in Algorithm ??. -> The details are shown in Algorithm 2.

transmission.In future work -> transmission. In future work

Format:

acromyms are used before definition, for example, in abstract (CGAN, ...)

some acronyms are defined several times (CGAN, WL)

Please avoid the use of "we", "us".
For example, in abstract, "we design" -> it is designed

The quality of Fig. 3 should be improved.

 

General comments:

Output layer of the generator and input layer of the discriminator both contain 212 neurons, manipulated by the size of gear parameters. Other sizes of the generator are {128, 1024, 256} and that of the discriminator are {256, 1024, 128}.
Please, justify these numbers (all powers of 2).

Also, please justify the chosen distribution.

Please, highlight the scientific contributions of the paper compared to [1]

1. Li, J.; He, H.; Li, L.; Chen, G. A Novel Generative Model with Bounded-GAN for Reliability Classification of Gear Safety. IEEE Transactions on Industrial Electronics 2019.

The state of the art in the introduction should be improved.

Author Response

Thanks for your comments and we have provided a point-by-point response. If you need any further information regarding our paper, please feel free to contact me.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Dear Authors, the paper is well organized and clear now. My all  concerns have been addressed. In my opinion, the paper is ready for publication in the present form. I acknowledge and congratulate the authors for their significant efforts and the time they spent on the revision of the Manuscript. Great work!.

Reviewer 3 Report

Please, check equation (1). One bracket ] is missing.

Dear Authors, the paper is ready to be published in my opinion.

All my concerns have been addressed.

The revision of the Manuscript is very professional.

Great job. Congratulations!