Investigation of Machine Learning Methods for Predictive Maintenance of the Ultra-High-Pressure Reactor in a Polyethylene-Vinyl Acetate Production Process
Round 1
Reviewer 1 Report
Well written.
Please add how your reported results could be reproducible for your readers.
Author Response
Thank you so much for your valuable suggestions and comments. In the attached response sheet we have properly addressed all the comments raised by you, which significantly helped a lot to improve the quality of manuscript.
Author Response File: Author Response.pdf
Reviewer 2 Report
In this study, the authors assessed different machine-learning models for predictive Maintenance of the Ultra-High-Pressure Reactor in A Polyethylene-Vinyl Acetate Production Process. Although the results seem promising, some major points should be addressed as follows:
1. There must have some external validation data to evaluate the performance of model on unseen data.
2. How did the authors conduct hyperparameter tuning of their models?
3. Uncertainties of models should be reported.
4. The authors should compare their performance to previously published works on the same problem/data.
5. The model can be improved using some ensemble architectures (i.e. bagging, stacking).
6. More discussions should be added in terms of the limitations and challenges of this problem.
7. Machine learning is well-known and has been used in previous studies i.e., PMID: 34989149, PMID: 33848577. Thus, the authors are suggested to refer to more works in this description to attract a broader readership.
8. Overall, English writing and presentation style should be improved.
9. Quality of figures should be improved.
10. Source codes should be provided for replicating the study.
11. Model explanation/interpretation should be conducted.
Author Response
Thank you so much for your valuable suggestions and comments. In the attached response sheet we have properly addressed all the comments raised by you, which significantly helped a lot to improve the quality of manuscript.
Author Response File: Author Response.pdf
Reviewer 3 Report
The study “ Investigation of Machine Learning Methods for Predictive Maintenance of the Ultra-High-Pressure Reactor in A Polyethylene-Vinyl Acetate Production Process.” This study is an interesting one using AI for predictive maintenance. Few suggestions are there for further improvement:
1. The abstract should be more precise.
2. Include quantitative as well as qualitative results in the abstract as well as in the conclusion.
3. The list of nomenclature should be included.
4. The first section of the introduction may be aligned with global causes like SDGs or net-zero targets.
5. The state of the art should also have some critical remarks.
6. The connection between the literature review and the objective of the study should be improved. Overall, the state of the art is well-written, just check it for the flow of language.
7. What was the reason for choosing 14 ML methods? Kindly justify it.
8. The hyperparameters optimization could further improve the results. How do authors justify not using it?
9. In a few places, the text is not cited properly.
10. The following studies on machine learning may be included to improve the impact and visibility of the study. You may use 10.1016/j.ijhydene.2022.04.093, 10.1016/j.ssci.2021.105529, 10.3390/batteries9010013.
11. The results should be compared with contemporary work.
12. The conclusion should be more precise and it should be point-wise for better understanding.
Overall, it is a well-written article and compact article. It may be considered after major revision.
Author Response
Thank you so much for your valuable suggestions and comments. In the attached response sheet we have properly addressed all the comments raised by you, which significantly helped a lot to improve the quality of manuscript.
Author Response File: Author Response.pdf
Round 2
Reviewer 2 Report
My previous comments have been addressed.
Reviewer 3 Report
The authors have done well in revising the manuscript. It may be accepted.