Modeling Liquid Thermal Conductivity of Low-GWP Refrigerants Using Neural Networks
Round 1
Reviewer 1 Report
Please see the attached file.
Comments for author File: Comments.pdf
Author Response
Reviewer 1
The authors determined the liquid thermal conductivity of seven low-GWP-based refrigerants using neural networks in which a feed-forward network algorithm with five key input parameters. The work is interesting, and it aligns with the scope of Applied Sciences. This reviewer suggests the authors to revise their paper considering the following suggestions:
The authors would like to thank the Reviewer for the appreciations. The manuscript was carefully revised and modified in agreement with the Reviewer' comments. Please note that the new sentences are in red in the new version of the manuscript. Figures and tables that have been modified or added also show their captions in red.
In the abstract, change “low-impact refrigerants” to “low-GWP based refrigerants” Further highlight the novelty of the work in the last paragraph of the introduction section. Figure 3 seems unnecessary to me. Authors may delete it.
In agreement with the Reviewer comment, the following changes were performed in the revised manuscript:
- “low-impact refrigerants” was replaced with “low-GWP based refrigerants” in the Abstract;
- the novelty of the proposed study was highlighted in the Introduction section;
- Figure 3 was removed from the manuscript.
In the last sentence of the conclusions section, the authors claimed that “In all cases, it was found that the network had better results when compared 363 with other techniques to estimate the liquid thermal conductivity used in the literature.” Provide more evidence to support the claim.
The following explanations to support the abovementioned claim were added in the Conclusion section of the modified manuscript:
It was found that the network ensured better results when compared with the following techniques to estimate the liquid thermal conductivity available in the literature: the correlation proposed by Tomassetti et al. [22] and the models used in REFPROP 10.0 [9]. The correlation gave an absolute average relative deviation of 2.585% for the complete dataset. Instead, the software provided an absolute average relative deviation of 3.820% for 6 refrigerants.
Remove Reference #32.
Reference [32] was removed from the new version of the manuscript.
Cite more relevant studies, including the following papers:
- Uddin, B.B. Saha, An overview of environment-friendly refrigerants for domestic air conditioning applications, energies, Vol. 15, 8082, https://doi.org/10.3390/en15218082, 31 October 2022.
- K Uddin, et al., Low GWP Refrigerants for Energy Conservation and Environmental Sustainability, Chapter 15 in Advances in Solar Energy Research, pp. 485-517, DOI: https://doi.org/10.1007/978-981-13-3302-6, Springer, 2019.
The abovementioned studies were cited in the Introduction section of the revised manuscript (references [6,7]).
Reviewer 2 Report
The manuscript presents a neural network approach to determine liquid thermal conductivity. The work presented is systematically conducted. Though some gaps remain that should be addressed.
Abstract should contain significance of the problem.
Novelty should be highlighted in abstract and introduction.
Literature review should be improved. Studies reported by others for property estimation using neural networks should be critically evaluated.
Fig 4 should be explained in more detail.
Why is ANN approach selected instead of others? It should be clearly justified. The following references would be helpful
https://doi.org/10.1016/j.compind.2020.103200
https://doi.org/10.1016/j.fuel.2022.125409
The limitations of the study should be mentioned.
English should be thoroughly checked.
Single line paragraphs should be avoided.
Author Response
Reviewer 2
The manuscript presents a neural network approach to determine liquid thermal conductivity. The work presented is systematically conducted. Though some gaps remain that should be addressed.
The authors would like to thank the Reviewer for the time and efforts dedicated to the paper revision. The manuscript was carefully revised and modified in agreement with the Reviewer' comments. Please note that the new sentences are in red in the new version of the manuscript. Figures and tables that have been modified or added also show their captions in red.
Abstract should contain significance of the problem.
Additional details about the importance of developing accurate models to calculate the liquid thermal conductivity of refrigerants were reported in the Abstract of the revised manuscript.
Novelty should be highlighted in abstract and introduction.
The novelty of the study was highlighted in the Abstract and Introduction section of the modified manuscript.
Literature review should be improved. Studies reported by others for property estimation using neural networks should be critically evaluated.
Additional comments and citations (references [29-31]) to show that neural networks can be considered reliable models to calculate the thermophysical properties of fluids were added in the Introduction section of the modified manuscript.
Fig 4 should be explained in more detail.
The following comments for Figure 4, that corresponds to Figure 3 in the new version of the manuscript, have been reported:
It is evident that the network can accurately reproduce the behavior of liquid thermal conductivity of this refrigerant as a function of the temperature. However, higher deviations can be seen at some specific temperatures. From an in-depth analysis of the results, it was found that this outcome could be due to the different temperature and pressure behaviors of the experimental point provided by the two sources [39,40] presenting λL data for R1336mzz(E).
Why is ANN approach selected instead of others? It should be clearly justified. The following references would be helpful
https://doi.org/10.1016/j.compind.2020.103200
https://doi.org/10.1016/j.fuel.2022.125409
The mentioned studies were cited in the Introduction section of the revised manuscript to show the importance of using neural networks for calculating the thermophysical properties of fluids.
The limitations of the study should be mentioned.
The limitations of the present study were explained in the Conclusion section of the modified manuscript, as follows:
Finally, it is worth remarking that the proposed neural network is more complex than many correlations available in the literature; therefore, it should be used only when high accuracy is required. In addition, it is not ensured that the proposed network could provide accurate values for the liquid thermal conductivity of low GWP refrigerants that were not considered in its development.
English should be thoroughly checked.
English quality was carefully checked by also using Grammarly software, and grammar typos were corrected in the new version of the manuscript.
Single line paragraphs should be avoided
Single-line paragraphs were removed in the revised manuscript.
Round 2
Reviewer 1 Report
I am satisfied with the revised manuscript.