Next Article in Journal
Visualization Technology and Deep-Learning for Multilingual Spam Message Detection
Next Article in Special Issue
Applying a Neural Network to Predict Surface Roughness and Machining Accuracy in the Milling of SUS304
Previous Article in Journal
Assessment of the Current for a Non-Linear Power Inductor Including Temperature in DC-DC Converters
Previous Article in Special Issue
Establishing a Real-Time Multi-Step Ahead Forecasting Model of Unbalance Fault in a Rotor-Bearing System
 
 
Article
Peer-Review Record

Investigation of Machine Learning Methods for Predictive Maintenance of the Ultra-High-Pressure Reactor in a Polyethylene-Vinyl Acetate Production Process

Electronics 2023, 12(3), 580; https://doi.org/10.3390/electronics12030580
by Shih-Jie Pan 1, Meng-Lin Tsai 1, Cheng-Liang Chen 1,*, Po Ting Lin 2,* and Hao-Yeh Lee 3
Reviewer 1:
Reviewer 2: Anonymous
Reviewer 3:
Electronics 2023, 12(3), 580; https://doi.org/10.3390/electronics12030580
Submission received: 31 December 2022 / Revised: 19 January 2023 / Accepted: 20 January 2023 / Published: 24 January 2023
(This article belongs to the Special Issue Selected Papers from Advanced Robotics and Intelligent Systems 2021)

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.  

Back to TopTop