A Review on AI for Smart Manufacturing: Deep Learning Challenges and Solutions
Round 1
Reviewer 1 Report
The Authors categorize AI techniques with a focus on deep learning into three main areas significant for fully automated industrial AI systems: data quality, data secrecy, and AI safety. Moreover, the Authors present the state of the art of methods and techniques applicable for deep learning in smart manufacturing.
The authors describe the problems associated with the lack of data sampling and storing infrastructures, the short development time expected by the users, changing working conditions, and the cost of data pre-processing and labeling. However, they do not consider issues connected to data quality and completeness and data difficult to measure. Deep learning models are highly dependent on the underlying data. So, data quality and completeness is essential for a deep learning model. The Authors should even mention these problems in the Introduction.
Drawbacks:
1. Lack of work structure in the Introduction
2. Lack to indicate development trends that would allow minimizing the identified research gaps
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 2 Report
The paper ''A Review on AI for Smart Manufacturing: Deep Learning Challenges and Solutions'' is within the scope of the journal and sound interesting.
1. The major concern of this review is the failure to provide a clear understanding of the state-of-the-art Deep learning models implemented in the smart manufacturing. There need to the paper to cover the section of different DL models theory with the tabulated application.
2. Another major concern is the study did not base the logical facts and discussion on the basis of popular data base such as scopus, WoS, PubMed, etc. The author did not summarizes the details of the reviewed papers, including the types of models, data span, time scale, input and output parameters, performance criteria used, and the best models identified.
3. Furthermore, recommendations for possible future research directions to improve the accuracy and the operation of the smart industries and enhance the related knowledge are outlined.
4. There are no advanced deep machine learning models were developed. Those are existed models, however, probably not introduced for this engineering problem. Revise the title as per proper.
5. In the introduction section, you have explained the problem nicely, but you did not give credit for machine leaning to solve this problem.? I see no problem statement clearly presented as well.
6. All methodology diagrams are not well presented and visualized. You need to redraw figures in a way clear for readers.
7. Present quantitative figures of the published article in the abtsrat By looking at the abstract section, this section does not really present an abstract. You should follow those elements, i. problem statement or research motivation, ii. Main research aim, iii. Research results, general finding.
8. How many year did you cover the reviewed
9. The Table 1. (List of review articles on deep learning in smart manufacturing) is wrongly presented
10. The paper is busy explaining the Neural network while the deep learning was claimed to be done.
11. There is no clear objective and research significant, the paper need significant improvement
12. Figure 11(a and b) should be written in the captions
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 2 Report
The authors tried their best to address my concerns but need significant checks regarding English and typos.