Next Article in Journal
Multi-Objective Optimal D-PMU Placement for Fast, Reliable and High-Precision Observations of Active Distribution Networks
Next Article in Special Issue
Tool for Predicting College Student Career Decisions: An Enhanced Support Vector Machine Framework
Previous Article in Journal
Coupled Models in Electromagnetic and Energy Conversion Systems from Smart Theories Paradigm to That of Complex Events: A Review
Previous Article in Special Issue
Session-Enhanced Graph Neural Network Recommendation Model (SE-GNNRM)
 
 
Article
Peer-Review Record

Performance Prediction of Rolling Bearing Using EEMD and WCDPSO-KELM Methods

Appl. Sci. 2022, 12(9), 4676; https://doi.org/10.3390/app12094676
by Xiumei Li 1,* and Huimin Zhao 2,3
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Appl. Sci. 2022, 12(9), 4676; https://doi.org/10.3390/app12094676
Submission received: 3 April 2022 / Revised: 28 April 2022 / Accepted: 4 May 2022 / Published: 6 May 2022
(This article belongs to the Special Issue Soft Computing Application to Engineering Design)

Round 1

Reviewer 1 Report

- Linguistically, needs to be reworked - both in terms of spelling and grammar. Reference should be included only after a blank.
- Abbreviations are sometimes not sufficiently explained (LSSVM, SVD, EEMD).
- Some equations are not structured in a uniform way (see equations 3-5).
- Functionality of the KELM is not described, only its optimization.
- Figure 2 and 3: Source reference to the picture is missing. This is certainly not self-made.
- Figure 2: The figure looks rather unprofessional with the arrows.
- Figure 4 and 5: What do a), b) and c) stand for? Which test runs are evaluated here?
o Please make direct comparison of the different feature indicators in one figure.
- The structure of the paper is poor. Why is the EEMD not explained until chapter 5.2.3? The classical structure of a paper (Introducion, Methods, Results, Discussion, Conclusion) is not followed.
- Chapter 5.3: Why are the parameters set like this here? Seems arbitrary to me at first glance, with no visible justification.
- It is not at all clear to me how and on what is being trained. What is the goal here that the trained algorithm is supposed to fulfill?
- I am missing the comparison of the WCDPSO-KELM to other ML methods.
- I do not see the described verification of the algorithm (see end of chapter 5), because no alternatives to the WCDPSO-KELM are presented.
- The paper seems very listlessly written, without a clear goal of the method presented here.
- The necessary basics of rolling bearing technology are missing, there is no visible reference to the example rolling bearing

Comments for author File: Comments.pdf

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

- Do an English review.
- There are several situations where space is required between words or quotations.
- The list of references needs to be adjusted. Some are out of standard.
- Suggestion of some related works:
    - https://doi.org/10.3390/en13133481
    - https://doi.org/10.1007/s00500-016-2217-8
- Citations need to be adjusted to the journal's standard.
- At the beginning of the section must have a preamble.
- All acronyms must be defined in the text.
- Equation 8 is out of bounds.
- Figures with repeated images could optimize.
- Restructure the article. Chapter 4 is too short.
- Rearrange the tables.
- Make a brief comparison with the results of methods with the same purpose.
- Improve how emulated bearing degradation.
- Regarding the results, there is no concrete statistical analysis.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 3 Report

Title:

  • The title is grammatically not correct. Please revise and improve.

 

Abstract:

  • The abstract needs a careful revision from the language.
  • More specific information about the conducted research should be presented.
  • The end of the abstract remains rather general. Please present more specific take-home messages.

 

Keywords:

  • The selection of the keywords is appropriate.

 

Comments:

  • The first part of the introduction contains a lot of language mistakes. Please revise the entire manuscript carefully. In the current stage, it does not reach an acceptable level and the readability greatly suffers from that.
  • The entire introduction should be improved.
  • A better introduction into AI and machine learning approaches in tribology should be presented. In this regard, you may refer to: “The use of artificial intelligence in tribology—A perspective”
  • The novelty of the paper should be better worked out.
  • Section 2 reads rather long and should be shortened. In addition, more references should be included.
  • The sub-headings of the chapters included in section 3 are very similar. This is somehow confusing.
  • Figure 2 should be improved.
  • Figure 3 is a repetition of a part of Figure 2. Please avoid these duplications.
  • On which base have you selected the presented working conditions?
  • Please improve the caption of Figure 4. The same holds true for Figure 5 and Figure 6. Besides the caption, also the layout of all figures should be improved.
  • The same holds true for all subsequent figures.
  • The layout of Table 3 should be improved.
  • The is no scientific discussion in the manuscript. This aspect must be greatly extended to make the article publishable.

 

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Round 2

Reviewer 3 Report

Thank you very much for revising the article. The quality has certainly improved after the first round of revisions. 

 

  • Please replace "method" by "methods" in the title.
  • The captions still need some further improvement. 
  • Figure 5 and Figure 6 could be combined in one figure. 
  • The same holds true for Figure 7, Figure 8 and Figure 9.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Back to TopTop