Machine Learning Model of Dimensionless Numbers to Predict Flow Patterns and Droplet Characteristics for Two-Phase Digital Flows
Round 1
Reviewer 1 Report
- Information cited in Table titled as “Nomenclature” can be moved to the end of paper as appendix.
- Methodology used for the study is acceptable but yet authors have not applied more recent machine learning algorithms or deep learning algorithms.
- The authors have not added any challenges they faced in their methodology.
- Implications for future research may also be included in the conclusion at the end.
- Limitations of the study are also missing.
- The authors need to add some related work.
Author Response
Dear Reviewer:
Thank you very much for reviewing on our manuscript entitled “Machine learning model of dimensionless numbers to predict flow patterns and droplet characteristics for two-phase digital flows” (applsci-1201429). Your comments are very valuable and helpful for us to improve our paper. We are responding to the comments carefully and seriously point by point as following.
Please see the attachment.
Yours Sincerely,
Z.L Wang
Corresponding author
Name: Zhiliang Wang
E-mail: [email protected]
Author Response File: Author Response.docx
Reviewer 2 Report
In this investigation, the authors tried to use machine learning to build the algorithm that could automatically identify, judge and predict flow patterns and droplet characteristics, so that the empirical judgment was transferred to be an intelligent process.
The obtained results are promising and reasonable. In addition, the paper’s subject could be interesting for readers of journal. Therefore, I recommend this paper for publication in this journal but before that, I have a few comments on the text that should be addressed before publication:
Comments:
1)Figure 1 in page 7 should be changed to Figure 3. Please correct it.
2)Table 1 in page 9 should be changed to Table 4. Please correct it.
3)The data in table 2 in page 6 have overlapping and are not legible
4)How many of data (in %) have been used for training and testing?
5)How did you evaluate the accuracy of your predictions?
6)Is your proposed method in this study applicable to gas-water-oil three-phase flow?
7) In recent years, it has been proved that artificial intelligence (AI) is a powerful tool for predicting flow pattern and volume fraction of multiphase flows. I highly recommend the authors to add some references in this manuscript in this regard, it would be useful for the readers of journal to get familiar with recent researches in this field. I recommend the others to add all the following references, which are the newest references in this field:
[1] Zhang, Y., Azman, A.N., Xu, K.W., Kang, C. and Kim, H.B., 2020. Two-phase flow regime identification based on the liquid-phase velocity information and machine learning. Experiments in Fluids, 61(10), pp.1-16..
[2] Lin, Z., Liu, X., Lao, L. and Liu, H., 2020. Prediction of two-phase flow patterns in upward inclined pipes via deep learning. Energy, 210, p.118541..
[3] Evaluation of flow pattern recognition and void fraction measurement in two phase flow independent of oil pipeline’s scale layer thickness. Alexandria Engineering Journal, doi.org/10.1016/j.aej.2020.11.043
[4] Roshani., 2020. Application of GMDH neural network technique to improve measuring precision of a simplified photon attenuation based two-phase flowmeter. Flow Measurement and Instrumentation, 75, p.101804..
[5] Combination of X-ray tube and GMDH neural network as a nondestructive and potential technique for measuring characteristics of gas-oil–water three phase flows. Measurement, 168, p.108427. doi.org/10.1016/j.measurement.2020.108427
Author Response
Dear Reviewer:
Thanks for your efforts on reviewing our manuscript entitled “Machine learning model of dimensionless numbers to predict flow patterns and droplet characteristics for two-phase digital flows” (applsci-1201429). Your professional comments are valuable and helpful for us to improve our paper. We are very glad to response the comments point by point.
Please see the attachment.
Yours Sincerely
Z.L Wang
Corresponding author
Name: Zhiliang Wang
E-mail: [email protected]
Author Response File: Author Response.docx
Round 2
Reviewer 2 Report
All the comments have been addressed correctly and the paper is ready for publication in the present form.