State Estimation of Membrane Water Content of PEMFC Based on GA-BP Neural Network
Round 1
Reviewer 1 Report
Dear Authors! Thank you for your article, submitted to "Sustainability". Undoubtedly, topics related to modelling and simulation of fuel cells, including PEFMC, remain actual. The present article provides quite interesting and useful results on estimation of water content in PEM. However, the article needs in serious corrections before the publication.
1. The references in the Introduction are randomly selected in context:
- Lines 29-31. Refs [1-2] are not about automotive power systems;
- Lines 31-32. Ref. [3] is not relevant;
- Lines 32-34. Ref. [4] is not related to proton conductivity;
- Lines 37-39. Refs. [6,8] is not related to "flooding" state;
- Lines 42-44. Ref. [11] is not relevant.
2. Line 48. Friede and Dotelli .. Line 52. Ref [12] - it is not Friede. It is Yang in the List of references with non relevant reference.
3. Authors should justify the presence of paragraph 2 (Dynamic model of PEFMC) built entirely from the literature data. Or exclude it from the text.
4. Please explain, how has the simulated model been verified?
5. Please clarify, what is the "Expection" line in Fig. 7?
Please check the spacing of the articles.
Author Response
Please see the attachment
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The authors have addressed the output performance of the proton exchange membrane fuel cell (PEMFC) under the influence of water content in the proton exchange membrane (PEM). For this purpose, two models namely GA-BP neural network and the LS-SVM have been employed. It is concluded that GA-BP neural network has higher estimation accuracy compared with the LS-SVM. The work is interesting and presented in a proper manner. However, before this work can be published, the following points should be carefully considered by the authors.
1. First, a rigorous grammatical check is required throughout the manuscript. There are mistakes at many places which can be identifies as, for example, line 43: to improve rather than to improving, etc.
- Line 64- 66: The authors mentioned that they estimated the water content in PEM through experiments and simulations. Hence, explain the experiment performed in detail.
- Equation numbers should be at proper places. In the manuscript, it displays on the next line left side after equations. Check for all equations once again.
- Line 154: It should be previous research instead of previous researches.
- Proper citation of work is needed in many places. For example, Lines 154-155.
- A schematic diagram will be very helpful to describe and understand various equations of the models.
- More explanation is needed for equation 23 and how the numerical values are adopted?
- Comment on the fluctuation observed for water content observed for LS-SVM in Figure 7.
- Line 447: Correct LS-VSM to LS-SVM.
- In conclusion, I recommend the authors to revise the manuscript in the light of above suggestions.
- I recommend a minor revision of the manuscript.
1 A rigorous grammatical check is required throughout the manuscript. There are mistakes at many places which can be identifies as, for example, line 43: to improve rather than to improving, etc.
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Reviewer 3 Report
Title: State Estimation of Membrane Water Content of PEMFC Based on GA-BP Neural Network
Recommendation: Minor revisions needed as noted.
The manuscript is well written and has very attractive ide. But, there are a few questionable points that the authors should try to more clearly address.
1. The research filled is not fully explained. The need for the current work, its application and usefulness needs to be explained in the end of introduction part.
2. Why GA-BP neural network is better than a LS-SVM-based analysis method?
3. What are the limitations of using the GA-BP neural network to estimate water content in the PEM of PEMFCs?
4. How do the results of this study compare with previous research on estimating water content in the PEM of PEMFCs?
5. How do the findings of this study contribute to the overall goal of improving the performance and extending the lifespan of PEMFCs?
6. How does this study address the potential trade-offs between accuracy and computational complexity in estimating water content in PEMFCs?
7. Carefully check the superscript and subscript as well as the “oC” throughout the manuscript. You should add space between digit and the unit.
8. Must need careful revision of the manuscript, for grammatical structural and typo mistakes.
9. Use the same format and style of references.
Normal, not very good.
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Reviewer 4 Report
The manuscript presents calculation of the membrane humidity and fuel cell performance. The paper shows important developments for fuel cells field, but a minor revision is necessary before publication.
Make clear how was obtained the equation 5.
Page 7 line 260 – verify the typing.
Figure 2 – present the current normalize by electrode area.
Figures 4, 5 and 6 – verify the unity. Present the voltage for unit cell. For stack voltage, how many units cell and how the connections were considered for this performance?
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Dear Authors! Thank you for submitting the revised version of your manuscript, and for your attention to my comments. The text of the manuscript has been improved.
Normal.
