High-Dimensional Mapping Entropy Method and Its Application in the Fault Diagnosis of Reciprocating Compressors

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The authors discuss High-Dimensional Mapping Entropy Method and Its Applica- 2 tion to Fault Diagnosis of Reciprocating Compressors. The paper is concise. However, I have some concerns and questions for the authors. The following comments should be addressed to improve the paper presentation:

1.      The main aim of this work along with the innovation is missing.

2.      It would be beneficial to explicitly state the research problem or objective to provide a clearer context for readers. Elaborate a bit more on the motivation for the research.

 

3.      Conclusion section need to be rewritten as there is no explanation on the main advantages of the proposed methods in this domain, and the main limitations, or other merits of them. The comparison tasks mainly with the state of the art as well as future directions are completely not clear and useful for the readers and future researchers in this domain.

4.      It is advisable for the authors to provide quantifiable explanations demonstrating why their proposed model outperforms others.

5.      What about sensitivity analysis of the proposed models?? What are your suggestions and ideas about this task?

6.      Limited suggestions for future work in the last section and underwhelm, need to be revised, these need to be clearly exploited.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

Please see the attachment

Comments for author File: Comments.pdf

Comments on the Quality of English Language

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

In this work, the authors establish a high-dimensional mapping entropy method, which they claim that improve the stability of complex signals description and the accuracy of data separability. They consider the characteristics of traditional sample entropy feature extraction methods. And proposed a mapping method in a high dimensional space based on kernel function pattern recognition. A detailed study of the algorithms is also presented.  The authors claim that application to simulated signals shows a reduced parameter sensitivity and enhancement of the entropy smoothness. Their findings demonstrate that the suggested approach can effectively extract the characteristics of the signal and accurately distinguish the effects caused by different faults.

 

The work is interesting and provides a novel method, with attractive possible applications. In my opinion the description of the parameters and the general structure of the paper is detailed and adequate.  

 

Please consider the following comments prior to paper publication:

 

1.     Try to improve figure 2. Maybe make it bigger, especially the plot, since as it is now is nearly impossible to read the text and the information on the axes.

2.     Lines 422-427. Can you discuss with more detail the uncertainties calculation?

3.     I’m not sure if photos in figure 9 provide any useful information. Consider removing it.

4.     Please clarify: In my opinion a major contribution of your work would be to predict the wear or failure of the system (machine) from an early (temporal) stage. However, I fail to see any related comments especially in the conclusions section.

Comments on the Quality of English Language

Please perform a general check of the text for typos.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 4 Report

Comments and Suggestions for Authors

The presented work is interesting. Some critical observations need to be included in the revised manuscript.

1. The abstract should be more specific. Add the background of the HDME method. Also, point out the main objectives.

2. The literature review is inconsistent and needs critical observations regarding the limitations of available methods.

3. Point-wise objectives in the last paragraph of the Introduction may enhance the readability of this manuscript.

4. Give the citations for all Equations mentioned in section 2. 

5. I don't find any reference citations in section 3.1.1.

6.  Empirical studies have shown that setting r to be within the range of 0.15SD-0.25SD yields satisfactory results. How you can say it?

7.  In Figure 2, the graph is not clear. enlarge it. 

8. I found negative data in Figure 6a but in normalized data, it was positive, how?

9. Add future scope in conclusion.

At last, I will suggest making a schematic diagram to show the entire research accomplished in this paper. 

Comments on the Quality of English Language

Moderate corrections are required. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 5 Report

Comments and Suggestions for Authors

The authors explored the effectiveness of feature extraction of fault diagnosis for petrochemical machinery and equipment using high-dimensional mapping entropy (HDME) based on kernel function pattern recognition. They used HDME to improve the stability of signal complexity description and the accuracy of data separability.  They also studied the multi-scale high-dimensional mapping entropy (MHDME) and refined composite multi-scale high-dimensional mapping entropy (RCMHDME) algorithms.  
The correlation is derived based on the obtained data. The paper shows some interesting results and outputs. It is definitely useful to the research community to explore additional impacts in the area. The paper is suitable for publication after incorporating the comments given.

Comments:

1. The literature review is not up-to-date and inadequate. Authors must give the detailed survey and background of the study for better understanding of readers.
2. Please also provide the clear motivation of the study in the last paragraph of the introduction section.

3. Are the equations (1-7) derived by authors? If not, it has been taken from other sources, please give the reference.

4. In Fig. 2, Flowchart of feature extraction for HDME, some parts are not clearly visible. Redraw it clearly.

5. Add all the assumptions taken in the study.

6. In some figures (Fig. 3, 4, 5,7), legends and axis labels are not clearly visible. Increase the font size for legends and axis labels.

7. What are the limitations of the studied method?

8. The authors chose a particular value for technical parameters of the 2D12-70 reciprocating compressor. Why do you choose these values? Any reason?  Can you vary these parameter values to explore additional impacts of these parameters in your study?

Comments on the Quality of English Language

Minor edition is required. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 6 Report

Comments and Suggestions for Authors

The introduction starts with this line - Nowadays, reciprocating compressors are extensively utilized - but the papers are not updated. The cited papers must be from 2023 and 2022.

Initial discussion on the theory part can be slimmed.

Fig 3, 4, 7 - do increase the resolution.

Comparison with the latest manuscripts are missing - it should be included to justify the proposed work.

 

Comments on the Quality of English Language

it is fine.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 7 Report

Comments and Suggestions for Authors

* high-dimensional mapping entropy (HDME) is new method or already existing one?

* How Sample Entropy solves the issue of self-similarity?

* How select an appropriate high-dimensional mapping kernel function?

* How author verify the verify the kernel function's validity?

* In parameter  embedding dimension m, the similarity tolerance r and the time delay λ how this affect the HDME value?

* line 365 & 383 rrepeate Refined Composite Multi-Scale High-Dimensional Mapping Entropy (RCMHDME)

* 

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 8 Report

Comments and Suggestions for Authors

The effectiveness of feature extraction is a critical aspect of fault diagnosis for petrochemical machinery and equipment. This study establishes high-dimensional mapping entropy (HDME) to improve the stability of signal complexity description and the accuracy of data separability. HDME addresses the characteristics of traditional sample entropy feature extraction methods in terms of parameter sensitivity and insufficient noise suppression. A mapping theory of high dimensional space based on kernel function pattern recognition is proposed, which reassembles the sample vector after phase space reconstruction of time series. The multi-scale high-dimensional mapping entropy (MHDME) and refined composite multi-scale high-dimensional mapping entropy (RCMHDME) algorithms are further studied based on the idea of refined composite multi-scale. Application to simulated signals shows that the suggested methods reduce parameter sensitivity and enhance the entropy smoothness. The development of a methodology to identify faults through MHDME is proposed. This approach integrates signal preprocessing and intelligent preference techniques to achieve pattern recognition of reciprocating compressor bearings in various wear conditions. Moreover, the identification findings demonstrate that the suggested approach can effectively extract the characteristics of the signal and accurately distinguish the effects caused by different faults. The authors must address my following suggestions

1.      A comparison with base-line deep research is required.

2.      Results presented must be compared with published research values.

3.      Authors are suggested to cite and discuss the recent machine learning based approach.

Wang, H., et al.: An improved bearing fault detection strategy based on artificial bee colony algorithm. CAAI Trans. Intell. Technol. 7( 4), 570– 581 (2022). https://doi.org/10.1049/cit2.12105

4.      Comparison with base-line deep learning model is also required.

5.      The complexity analysis for the proposed research must be presented.

Comments on the Quality of English Language

Moderate corrections are required.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

 

Accept in present form

Reviewer 4 Report

Comments and Suggestions for Authors

Satisfactory revision. Accept the submission. 

Comments on the Quality of English Language

Minor editing is required

Reviewer 8 Report

Comments and Suggestions for Authors

The authors have addressed all the suggestions, i will suggest the acceptance of this manuscript.