Predicting Wall Pressure in Shock Wave/Boundary Layer Interactions with Convolutional Neural Networks

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Comments for author File: Comments.docx

Author Response

The authors would like to thank the reviewer for his/her constructive comments and suggestions, which have been very beneficial for improving the paper.

Reviewer 2 Report

Comments and Suggestions for Authors

 

The authors present an interesting and useful non-invasive novel method to predict wall pressure in shock wave/boundary layer interactions by using convolutional neural networks. The manuscript reads well with only minor language errors to be corrected and some technical deficiencies to be addressed. Improving suggestions are as follows:

01.   Line 60: Write “Bertrand et al. [11] investigate” instead of “Bertrand et al [11] investigates”. Do similarly in all other places.

02.   L64: Write “Li and Tan [12] employ” instead of “Li et al [12] employs”.

03.   L90: Better to write “artificial neural network (ANN)” instead of simply “ANN”.

04.   L90: Write “Yu and Hesthaven [15]” instead of “Yu et al [15]”.

05.   L111: Write “Rozov and Breitsamter [21]” instead of “Rozov et al [21]”.

06.   Lines 80-136: For easier reading, it would be good to break this long paragraph into two shorter ones.

07.   Page 7: Use different lining to improve the clarity of Fig. 4 and provide a clearer description of its contents.

08.   L217: To clarify the “0 to -5 degrees”, it would be good to indicate the angle of attack in Figure 2a.

09.   L271: Better to write in full “2.3 Characteristics of the shock wave/boundary layer interaction”.

10.   L273: Better to write “boundary layer interaction”.

11.   Page 10: Improve the clarity of Figure 7.

12.   Page 14: Improve the clarity of Figure 11.

13.   Lines 420-422: Rephrase these two sentences, to complete them.

14.   L436-443: Improve this paragraph.

15.   Page 15: Indicate the plots (a), (b), (c) and (d) in Figure 13.

16.   Page 16: Improve the clarity of Figure 14.

17.  L507-555: References should be listed complete, correctly and according to the Journal standards.

18.   Remove the indicators [C], [D] and [J] from the listing of references.

19.   Add all authors in references [2], [3] and [4]. The “et al.” is not proper.

20.   L518-519: Provide more details for ref. [6].

 

Comments on the Quality of English Language

Only minor language errors, as indicated above.

Author Response

We would like to thank the reviewer for his/her constructive comments and suggestions, which have been very beneficial for improving the paper. The manuscript has been revised carefully based on your feedback. We have addressed the comments raised by the reviewers, and the amendments are highlighted in yellow in the revised manuscript.

Reviewer 3 Report

Comments and Suggestions for Authors

This paper introduces a data-driven methodology that leverages non-contact schlieren imaging to predict wall pressure within the flow field, a technique that holds promise for informing the optimized design of variable-geometry systems. A sophisticated deep learning framework, predicated on Convolutional Neural Networks (CNN), has been engineered to anticipate alterations in wall pressure stemming from high-speed shock wave/boundary layer interactions. This paper suggested that augmenting the training set with additional samples and refining the network architecture will be a worthwhile endeavor in subsequent research initiatives. However, there has some problems to be solved:

(1) This paper uses CNN to predict wall pressure in shock wave/boundary layer interactions. However, this paper does not show the training complexity of the applied CNN.

(2) Some discussions about CNN are missing, including more advanced ResNet, HCGNet and ConNeXt. This paper should discuss and cite them.

 

Reference:

[1] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.

[2] Yang C, An Z, Zhu H, et al. Gated convolutional networks with hybrid connectivity for image classification[C]//Proceedings of the AAAI conference on artificial intelligence. 2020, 34(07): 12581-12588.

[3] Liu Z, Mao H, Wu C Y, et al. A convnet for the 2020s[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2022: 11976-11986.

 

Author Response

We would like to thank the reviewer for his/her constructive comments and suggestions, which have been very beneficial for improving the paper. The manuscript has been revised carefully based on your feedback. We have addressed the comments raised by the reviewers, and the amendments are highlighted in yellow in the revised manuscript.