Fault Diagnosis Method for an Underwater Thruster, Based on Load Feature Extraction

Round 1

Reviewer 1 Report

The issues related to the diagnostics of underwater thrusters is very important and up to date, therefore the topic taken up by the authors is interesting. However, the text presented requires some corrections.

1. There is no information on comparing the effectiveness of the proposed method to other methods.

2. The chapter "Conclusions" must be further developed - it is worth for the authors of the text to present their achievements in more detail, present the advantages of the developed method and propose possible further research.

3. It is a good practice to number all the mathematical equations in the article, not just some of them.

4. It would be worth checking the effectiveness of the proposed method in practical conditions on a real object.

Author Response

Please see the attachment

Author Response File: Author Response.docx

Reviewer 2 Report

This paper is quite well-written and detailed methodology design can be observed. The potentials of current work in underwater fault diagnosis are evident. In my opinion, this paper can be considered for publication if the following comments are addressed:

1. Abstract - Simulation results of current study should be explained.

2. There are many variable, symbols, vectors and etc are introduced in current work. It will be good if authors can summarize them using a nomenclature table. 

3. Figure 1 - Please provide the full definition of PMSM in the figure for the sake of clarity.

4. Shedding failure first has been mentioned in Line 208 but it was not considered one of the fault type in current study. Can authors clarify on this issue?

5. How does the relationship between fault types and changes of fault characteristic parameters in Table 1 are determined? Is this only based on the hypothesis of authors? Any materials or sources to support this relationship?

6. The meanings of y and C_n in Equation (14) are not defined.

7. Meanings of H, h and n in Table 3 are not defined.

8. It is not clear how the fault characteristics parameters of thrusters in Table 4 and Table 6 are determined? Please provide further clarification on this issue. Also, Table 5 is missing. 

9. Most of the results are presented qualitatively. It will be good if some results can be presented quantitatively in table form.

10. Line 434 - How to ensure the values of n = 45 can achieve proper tradeoff between the accuracy and speed of parameter estimation? What are the procedures or justification used to obtain n = 45?

11. What are the limitations and future works of current study. Please elaborate.

12. Some minor linguistic issues such as typo or missing full stop are found throughout the manuscript. Please proofread the manuscript again to rectify these issues. 

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 3 Report

My comments are as follows:

1) Numbering of formula in the whole manuscript should be corrected. For example, line 199 in page 5, line 277 in page 7, etc. have not numbering.

2) Why SVM not other machine learning approaches like Random Forest in “Application-specific clustering in wireless sensor networks using combined fuzzy firefly algorithm and random forest. Expert Systems with Applications, 2022: 210, 118365” or ensemble learning methods in “SI‐EDTL: Swarm intelligence ensemble deep transfer learning for multiple vehicle detection in UAV images. Concurrency and Computation: Practice and Experience, 2022: 34(5), e6726.” ? Please discuss about the suggested methods in Introduction, and mention your reasons in selecting SVM.

3) Figure 2 should be revised. Why you used red color?

4) The whole manuscript should be corrected in term of grammatical errors and punctuations.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 3 Report

The revised manuscript is satisfactory, and can be accepted.

Author Response

Thank you very much for your attention and the referee’s evaluation and comments on our manuscript.