Tool Wear Monitoring Based on the Gray Wolf Optimized Variational Mode Decomposition Algorithm and Hilbert–Huang Transformation in Machining Stainless Steel

Round 1

Reviewer 1 Report

The manuscript in its current version may not interest readers enough. It should be enriched with photos of the tested tools and the test stand.

Additional comments:

1. It needs to be clarified from the title and the abstract what kind of tools the manuscript is about. It should be emphasized that these are cutting tools for steel processing and not, for example, cutting tools for mining.

2. Keywords are too general. They will need help finding this manuscript.

3. At the beginning of the introduction, some example photos of the cutting tools the research applies should be shown. Also, it would be good to show the construction of such tools, showing that two parts (tip and body) are made of different materials.

4. There should be introductory paragraphs between the main sections 2 and 3 and subsections 2.1 and 2.1.1 etc. It should not be allowed when the titles of main sections and subsections are immediately after each other. In addition, section 2 needs to correct the numbering of subsections.

5. Should Figure 1 not be with reference?

6. It would be good to show the diagram of the test stand and its photo.

7. When giving the frequency value in Hz, the value should be separated from the unit by a space (applies to the entire manuscript).

8. In section 3, it would be worth showing these tools after research.

9. Diagrams are missing units. The amplitude of what? If they are on the diagram, they are behind / or in (). It should be unified.

10. Figures 10-12 - what is this coloured scale?

11. 70% of the references come from the authors from the same country as the authors. There should be more references by authors from other countries.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

The papers presents an algorithm for tool wear monitoring using the Hilbert-Huang transformation, gray wolf optimization and variational mode decomposition. The overall approach and experimental findings are interesting. I have yet the following reservations,

1. The discussion on state of the art should include the following relevant papers,

a. "Intelligent tool wear monitoring and multi-step prediction based on deep learning model" by Cheng et al.

b. "A systematic review on machine learning methods for root cause analysis towards zero-defect manufacturing" by Papageorgiou et al.

c. "A Switching Hidden Semi-Markov Model for Degradation Process and Its Application to Time-Varying Tool Wear Monitoring" by Liu et al.

d. "Deep multi-sensorial data analysis for production monitoring in hard metal industry" by Kotsiopoulos et al.

2. Please clarify on the use of the microscope as shown in Figure 3. It is used in laboratory to assess the degradation of the cutting end-effector, or it is integrated in the machining process?

3. Please provide experimental comparison with other methods. I would like to see to types of experiments added. Type I should be on other methods for tool wear monitoring, if needed you could use standard benchmarks available for a fair comparison. Type II should be on use the computer spectral features with typical ML methods for wear state classification.

4. Please clarify on whether you plan to make the generated dataset publicly available, as this would certainly help for reproduction of the experiments and follow up research.

The manuscript is easy to follow, I would however recommend a proofread and there are a few typos spotted.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Thanks to the authors for the reply. After revision, I accept the manuscript for publication.

Minor editing of English language required

Reviewer 2 Report

The authors have convincingly addressed my comments, nothing more to add.

The paper is easy to follow, a final proofread is needed.