A Compound Fault Labeling and Diagnosis Method Based on Flight Data and BIT Record of UAV

Round 1

Reviewer 1 Report

Undoubtedly, in the process of UAV flight test, there are plenty of compound faults existing, which could be composed of concurrent single faults or over-limit states alarmed by BIT equipment. In this article Authors compound fault labeling and diagnosis method based on actual flight data and BIT record of UAV during flight test phase is proposed, through labeling the flight data with compound fault modes corresponding to concurrent single faults recorded by BIT system, and upgrading the original diagnosis model based on GBDT and FCNN, to XGBoost, LightGBM and modified CNN. The article deals with an interesting and current issue.

My comments on the article:

- As part of the Introduction, I propose to extend the background to also refer to modern UAV control methods, such as through BCI technology. For example, I propose to refer to the article: The Use of Brain-Computer Interface to Control Unmanned Aerial Vehicle, Automation 2019: Progress In Automation, Robotics And Measurement Techniques, Advances in Intelligent Systems and Computing, Springer from 2019. Additionally, this will update the bibliography of the article.

- I suggest introducing axis descriptions in accordance with the measurement units to all graphics.

- The quotation in lines 55 and 74 should be corrected - I do not understand the quotation at the beginning of the sentence.

- Fig. 8 is not fully legible. I suggest dividing it into segments - enlarge graphics / change scale.

- I propose to extend the Conslusions to include plans for the future.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

-Correct English for example
"2.4. Didgnosis model based on LightGBM" Line 212 
Figure 2, 5, 8 - add arrows + labels what is what?

-paper should be interesting;;; 
-please add block diagram of the proposed method/research ;;;;
-please add colorful image of measurements (optionally, if any);;; + arrows what is what;;;;
-please add sentences about future analysis;;;
-Figures should have better quality;;;;
-please add arrows to photos what is what;;; 
-formulas and fonts should be formatted;;;;
-fonts in figures should be bigger;;;;
-references should be 2018-2021 Web of Science about 50% or more ;; 30-40 at least.;;;;
-is there possibility to use the proposed methods for other problems?  ;;;;

for example thermal imaging, 

Fault diagnosis of electric impact drills using thermal imaging, Measurement, Volume 171, 2021, 
https://doi.org/10.1016/j.measurement.2020.108815

-Conclusion: point out what are you done;;;;

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

-some photos of application of the proposed method can be added for example drones, camera of drone etc.