Neural Network-Based Automated Assessment of Fatigue Damage in Mechanical Structures
Round 1
Reviewer 1 Report
This is a quite interesting paper offering an automated method of real-time assessment of fatigue damage using neural networks models. Ultrasonic testing signals are used to identify the onset of fatigue damage in the test specimens. Furthermore, optical images from a confocal microscope and a digital microscope, measure the surface topography and the crack tip opening displacement (CTOD) to define three levels (i.e., low, medium, and high) of damage risk.
The current paper is in line with a recent publication by the same authors, titled “Classification of fatigue crack damage in polycrystalline alloy structures using convolutional neural networks”, published in Engineering Failure Analysis 119 (2021) 104908, https://doi.org/10.1016/j.engfailanal.2020.104908 but both papers are pertinent; and convolutional neural networks are considered more advanced types of neural networks.
The current paper is well written, but still there are some details that can be ameliorated.
See attached a list of comments and suggestions for improving the manuscript (PDF titled "machines-1032018-review").
Comments for author File: 
Comments.pdf
Author Response
Comments of Reviewer 1 have been addressed in the attached file. Responses to the comments of Reviewer 1 are highlighted in blue. Please see the attached file
For comment 14 " This paragraph mentioning Figures 16 (a) and (b), should be placed after Figure 15 (and not before Figure 15, which is the present situation).
The response of comment 14 is: the latex formats organize the location of the figures.
Author Response File: Author Response.pdf
Reviewer 2 Report
- Fig. 1b - dimensions given in the Fig. 1b are in mm? Please enter information in the drawing caption.
- Please explain all abbreviations and markings at work, e.g. ANN, and others.
- Page 10 - above Fig. 8 should be ... after reaching CCL ...
- Fig. 10 - in the caption under Fig. 10 please enter a), b), c) and d). The same in Fig. 16.
- It is good practice to place a table containing information on basic mechanical properties of base material as the yield strength, tensile strength, etc.
- It would also be worthwhile to quote the following papers: 1) Lesiuk G., Szata M., Rozumek D., Marciniak Z., Correia J., De Jesus A. Energy response of S355 and 41Cr4 steel during fatigue crack growth process, The Journal of Strain Analysis for Engineering Design, Vol. 53, No. 8, 2018, pp. 663–675
Author Response
Comments of Reviewer 2 have been addressed in the attached file including the new reference [4] suggested by Reviewer 2. Responses to the comments of Reviewer 2 are highlighted in red. Please see the attached file.
Author Response File: Author Response.pdf
