NDT Method for Line Laser Welding Based on Deep Learning and One-Dimensional Time-Series Data
Round 1
Reviewer 1 Report
There are some weaknesses through the manuscript which need improvement. Therefore, the submitted manuscript cannot be accepted for publication in this form, but it has a chance of acceptance after a major revision. My comments and suggestions are as follows:
1- Abstract gives information on the main feature of the performed study, but a couple of sentences about background of the study must be added.
2- Authors must clarify necessity of the performed research. Research questions, aims and objectives of the study must be clearly mentioned in introduction.
3- The literature study must be enriched. In this respect, authors must read and refer to the following papers: (a) https://doi.org/10.1016/j.jmrt.2021.07.004 (b) https://doi.org/10.1016/j.conbuildmat.2021.123622 and other relevant research works.
4- Researchers must refer to experimental practices available in literature with all details.
5- The main reference of all figure must be mentioned. All figures must be illustrated in a high quality, and usually captions of images are smaller than text font size.
6- The main reference of each formula must be cited. Moreover, each parameters in equations must be introduced. Please double check this issue.
7- Standard deviation in the presented curves must be discussed. In addition, error in calculation must be considered and discussed.
8- In its language layer, the manuscript should be considered for English language editing. There are sentences which have to be rewritten.
9- The conclusion must be more than just a summary of the manuscript. List of references must be updated based on the proposed papers. Please provide all changes by red color in the revised version.
Author Response
Please see the attachment.
Author Response File: 
Author Response.docx
Reviewer 2 Report
In this manuscript, the authors proposed a non-destructive method for testing weld defects in joint contours in order to solve the problems of low sampling rate and low recognition accuracy of traditional weld defect detection methods. The current method uses the image coding in laser sensors and learning algorithms to make the classification of defects.
In reviewer's opinion, the paper can be recommended for publication in Journal of Applied sciences with addressing the reviewer's comments listed below:
- The two first section introduction and related works can be combined in a one section introduction
- Section 3 the type of welding process should be precised because some welding defects are generally specific on each type.
- analyzing the figure 6 it seems that the light images a and c corresponding to Burr and porosity defects are similar the same for b and d how is the method to differentiate between these similar defects?
- How it is possible to characterize the dimension and the position of each defect using this method?
- Authors should specify the advantage of their technic compared to a new NDT technics used to control welding such as phased array ultrasonic testing.
- The present NDT technic can be used to detect defects deeper in material or just for surface defects. If No is it possible to extend this technic to be able for this type of defects?
- The last section is conclusion not results. Authors should specify the advantage of their technic compared to new NDT technics.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
The paper has been improved and corresponding modifications have been conducted. In my opinion, the current version can be considered for publication.
