Fault Classification of Rotary Machinery Based on Smooth Local Subspace Projection Method and Permutation Entropy
Round 1
Reviewer 1 Report
@page { margin: 2cm } p { margin-bottom: 0.25cm; line-height: 115% } a:link { so-language: zxx }Abstract:
1. What does inherent broadband characteristic in line 14?
2. remove Both the principle and calculation formula have all been described as this sentence should be in introduction not abstract.
3. the last two sentences in abstract have the same meaning.
Introduction
1. define SOD in line 50 as it appeared for the first time in the text.
2. repeatedly can be replaced with multiple in line 62.
3. adding more references regarding existing technique on fault detection is im portant.
2. The theory ...
1. In Eq. 1 y_i is a vector; better to represent scalers as italic lowercase non bold, vectors as non-italic lowercase bold, matrices as non-italic uppercase bold in all equations.
2. line 98 add a reference for selection of theta
3. fix Eq. 13
4. Only report the weight matrix that you are going to use
5. There is no information regarding the data or experiment setting in pages 5 and 6 but several results have been reported. It is better to report and discuss all figures in results sections.
3. Numerical experiments
1. the noise level in simulated results are not very high, could you show the stability of your results by any performance metric considering several noise levels for one simulated data.
2. although figures shows a separate distinction after applying the proposed pipeline, it would be nice to use a simple classification method such as support vector machine (SVM) and check the performance before and after the noise reduction stage.
3. there is no comparison with other techniques for fault detection.
Author Response
Dear Reviewer,
Thank you so much for your letter and for reviewer’s comments concerning our manuscript entitled “Fault classification of rotary machinery based on smooth local subspace projection method and permutation entropy” (Manuscript ID: applsci-480679). These comments are all valuable and very helpful for revising and improving our paper, as well as the important and significant guidance to our research. We have studied the comments carefully and have made corrections, which we hope would meet with your approval. We have also revised and improved the English language and style of our manuscript. Revised portion are marked in red in the paper.
Please find our responses to your review report in the attached pdf.
Best Regards,
Lingjun Xiao
Author Response File: 
Author Response.pdf
Reviewer 2 Report
It is a well written paper with an interesting topic for Journal of Applied Sciences. Therefore, it is recommended to let the paper published provided that the authors will take into consideration the following remarks and will do a good English proofing:
1. Acronyms should also explained in the manuscript.
2. $2.3. Explain briefly the difference btw POD and SOD.
3. L.129, P.3: The explanation of the summation symbol <sigma> is not clear.
4. Table1: when the iterations should stop?
5. Eq.12: where do explain the operator of the numerator?
6. In Eq. 13 a superscript is missing. Please amend.
7. L.230, P.8: ‘select’ is redundant.
8. L.250-251, P.10: please rephrase.
9. The units of Figs.15-17 are not clear.
10. Fig.17 seems odd. Where do you refer to it?
11. L.327, P.14: “cannot clearly show the difference”
Author Response
Dear Reviewer,
Thank you so much for your letter and for reviewer’s comments concerning our manuscript entitled “Fault classification of rotary machinery based on smooth local subspace projection method and permutation entropy” (Manuscript ID: applsci-480679). These comments are all valuable and very helpful for revising and improving our paper, as well as the important and significant guidance to our research. We have studied the comments carefully and have made corrections, which we hope would meet with your approval. We have also revised and improved the English language and style of our manuscript. Revised portion are marked in red in the paper.
Please find our responses to your review report in the attached pdf.
Best Regards,
Lingjun Xiao
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Authors answered all my comments but I still would suggest another round of text proofreading.
Author Response
Dear Reviewer,
Thanks a lot for your review, and we have finished the text proofreading. Also we have enriched our literature review.
Attached please find the minor revised manuscript. Thanks again.
Best Regards,
Lingjun Xiao
Author Response File: 
Author Response.docx
Reviewer 2 Report
The term permutation entropy (PE) appears abbreviated before explained. Please amend.
It's not clear how you define the noise power when estimating SNR.
Author Response
Dear Reviewer,
Thanks a lot for your dedicated review, we have improved our manuscript according to your review report. Thanks again.
Best Regards,
Lingjun Xiao
Author Response File: Author Response.pdf
