A High-Confidence Intelligent Measurement Method for Aero-Engine Oil Debris Based on Improved Variational Mode Decomposition Denoising

Round 1

Reviewer 1 Report

This paper proposes a new method for the electromagnetic measurement of metal debris in aviation engine oil systems, including the improved VMD (Variational mode decomposition) denoising algorithm, DSS-LSTM (Deep Scattering Spectrum-LSTM) waveform recognition method, and multi-window fusion detection method, providing new ideas for low accuracy caused by noise interference and weak signal of electromagnetic debris sensor. This paper verifies the method's effectiveness through simulation and oil system measurement experiments. This paper may contain some publishable ideas. But it also needs to make some major modifications. Some detailed comments are listed as follows, which will help to improve the quality of the manuscript.

1. The importance of the design carried out in this manuscript can be explained better than other important studies published in this field. I recommend the authors to review other recently developed works in the section of introduction.

2. In Introduction, some recent related work on the machine learning models should be strengthened, several recent investigations are recommended for the author’s references, i.e., "10.1016/j.triboint.2022.107945"; " 10.1016/j.ast.2023.108325"; "10.1016/j.ijfatigue.2022.107342".

3. A large number of investigations have studied the machine learning by combining many algorithms respectively, for instance, swarm intelligence algorithm, gradient algorithm and so on. Some articles are given below but not limited to these. Relative to these methods, what is the strengths of the BO algorithm. i.e., " 10.1007/s00603-021-02747-x "; " 10.1016/j.ijfatigue.2022.106812 "; " 10.1016/j.ijfatigue.2022.106842 ".

4. The readability and presentation of the study should be further improved. The paper suffers from language problems. The paper should be proofread by a native speaker or a proofreading agent.

5. Some mathematical notations and presentations are not rigorous/clear enough to correctly understand the contents of the paper. It is suggested to check all the definitions of variables and redefine the missing information when preparing the submission of the paper.

6. The Conclusion Section needs a major revision, and it is recommended that the authors add a summary of what new discoveries have been made in the field through this study, and indicate what possible results these discoveries are likely to produce.

 

7. The authors are suggested to check and modify the full text carefully.

Author Response

    I appreciate your response and the feedback. In response to each comment from the reviewer, I have carefully revised my manuscript (aerospace-2561701). You will find my detailed explanations and the corresponding revisions I have made based on the reviewer's suggestions in the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

This paper is of high interest in retrieving data from debris in oil under high noise. The method presented are impressive in science and results. 

A few points from the reviewers site :

For a non professional reader,  this paper is extremely complex and hard to understand. The methodology explanations are filling more than 2/3  of the whole paper, while the experimental section is sparse. It is very honarable that the authors are mentioning this weekness and the need to underfit the methods with cases from the real field.

The significance of the recordings remains unclear, as in real applications always debris threshold is  carried in the oil.  A time series of a test oil combined with competitive measurements like IR, XRF and electrostatic sensing would be helpful. Even more, if such an oil is tested till failure.It would be of high benefit to see, wether the method proposed in the paper is effective for predictive reactive maintenance or if other methods are more sensitive in that case.

It would be benefitial to add the theory of stationar and non-stationare signal processing as a competitive method.

While reading, the reviewer had the vision to put some of the methodology explanation into an Appendix Section. This would liberate the main text from this burden.

Comments for author File: Comments.pdf

Sentences are somehow too long and have to be checked (see attachement)

Abbreviations should be explained in the course  of the text.

Author Response

    I appreciate your response and the feedback. In response to each comment from the reviewer, I have carefully revised my manuscript (aerospace-2561701). You will find my detailed explanations and the corresponding revisions I have made based on the reviewer's suggestions in the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Authors have addressed the problems appropriately, the manuscript is suitable for publication in current form.

Reviewer 2 Report

Thank you for the revision