Next Article in Journal
Stability Analysis of Mixed Traffic Flow Considering Personal Space under the Connected and Automated Environment
Previous Article in Journal
Investigation of the Beam Quality of a Compact Non-Chain Pulsed DF Laser with a Confocal Positive Branch Unstable Resonator
 
 
Article
Peer-Review Record

Reactor Temperature Prediction Method Based on CPSO-RBF-BP Neural Network

Appl. Sci. 2023, 13(5), 3230; https://doi.org/10.3390/app13053230
by Xiaowei Tang 1, Bing Xu 1,* and Zichen Xu 2
Reviewer 1:
Reviewer 2: Anonymous
Reviewer 3:
Reviewer 4:
Reviewer 5:
Appl. Sci. 2023, 13(5), 3230; https://doi.org/10.3390/app13053230
Submission received: 30 January 2023 / Revised: 25 February 2023 / Accepted: 25 February 2023 / Published: 2 March 2023
(This article belongs to the Special Issue Intelligent Control in Industrial Processes)

Round 1

Reviewer 1 Report

 

Type of manuscript: Article

Title: Reactor temperature prediction method based on CPSO-RBF-BP neural network

Special Issue: Intelligent Control in Industrial Processes

Authors: Xiaowei Tang 1, ZICHEN XU *2 and Bing Xu

 The authors address the optimization of the neural network model RBF-BP using a chaotic particle swarm algorithm for predicting the temperature of a reactor based on the theoretical foundations established by the scientists' research mentioned above. The initial weights and thresholds of the neural network RBF-BP are adjusted using the chaotic particle swarm algorithm, which successfully prevents the neural network from falling into local optimal solutions and improves the convergence speed to achieve the goal of improving the accuracy of reactor temperature prediction.

Therefore, I recommend the publication of the manuscript in MDPI Applied Sciences. However, I would like the authors to address some points that may increase the readability of the paper:

 Major point

1.      1.-The author should give a detailed discussion of the results

2.      2.- Figure 11 needs a better explanation.

Minor point

     3.-How are the weights of the network fed or reprogrammed with the chaotic particle swarm algorithm?

        4.- On page 5 the following is not clear:

with the third category containing three methods: chaotic iterations on the particles; chaotic iterations on the solutions. In this  article, the last example of the third category is utilized primarily to execute chaotic iteration on  the ideal particles of the particle swarm.

      5.- What does the chaotic particle swarm represent in the RBF-BP neural networks.

        6.-  In Figure 3, it is not clear which is the BP neural network and which is the RBF neural

            network.

Author Response

We sincerely hope that this revision has addressed all your comments and suggestions.   We sincerely thank the reviewers for their enthusiastic work and hope that the revision can be approved.

  Thank you again for your comments and suggestions!

Author Response File: Author Response.pdf

Reviewer 2 Report

* Abstract should contain some details of the improvement obtained in terms of percentage. 

* The last paragraph of the introduction should usually briefly touch upon the research gap, the novelties of the work, and the organizational structure of the manuscript. 

* Critical citations are missing for PSO. Cite 

-> Eberhart, Russell, and James Kennedy. "Particle swarm optimization." In Proceedings of the IEEE international conference on neural networks, vol. 4, pp. 1942-1948. 1995.

-> Shankar, Rajendran, Narayanan Ganesh, Robert Čep, Rama Chandran Narayanan, Subham Pal, and Kanak Kalita. "Hybridized particle swarm—gravitational search algorithm for process optimization." Processes 10, no. 3 (2022): 616.

* For equation (1) to (5) citations are missing. Cite

-> Dey, Kumaresh, Kanak Kalita, and Shankar Chakraborty. "Prediction performance analysis of neural network models for an electrical discharge turning process." International Journal on Interactive Design and Manufacturing (IJIDeM) (2022): 1-19.

-> Kumar, M., Lenka Čepová, M. Raja, Allam Balaram, and Muniyandy Elangovan. "Evaluation of the Quality of Practical Teaching of Agricultural Higher Vocational Courses Based on BP Neural Network." Applied Sciences 13, no. 2 (2023): 1180.

* In Table 1 the Reactor temperature data sample is provided. But since it is only a section of the data used, the author should report the statistical features of the dataset. 

* Label and describe the two parts of 'Figure 6. Enterprise site reactor'

* Figure 8. BP neural network model prediction result is meaningless now. Plot Actual values versus BP predicted value.

* Same for Figures 9 and 10. 

* Citations are not in MDPI format. Follow ACS style.

Author Response

We sincerely hope that this revision has addressed all your comments and suggestions. We sincerely thank the reviewers for their enthusiastic work and hope that the revision can be approved. Thank you again for your comments and suggestions.

Thank you again for taking the time to review our manuscript!

Author Response File: Author Response.pdf

Reviewer 3 Report

Overall a good manuscript. The main revision parts should be on writing and formatting, especially some of the figure/section titles do not match the related contents. Besides, some mathematical expressions need to be standardized.

Comments for author File: Comments.doc

Author Response

We sincerely hope that this revised manuscript has addressed all your comments and suggestions. We appreciated for reviewers’ warm work earnestly,and hope that the correction will meet with approval.Once again,thank you very much for your comments and suggestions.

Thanks again for taking the time to review our manuscript!

Author Response File: Author Response.pdf

Reviewer 4 Report

Comment 1: The readability and presentation of the work should be improved.
Comment 2: Authors should clearly emphasize the contribution of this work in relation to the existing solutions in the literature, including supported simulation verification.
Comment 3: The introduction could be updated with recent reviews dedicated to application of CPSO-RBF-BP neural network

Comment 4:In abstract the authors must highlight the motivation of the study.

Comment 5:What software was used for simulation?

Comment 6: The method of the solution should be written in more detail.

Comment 7:English language needs some improvement throughout the paper.

Comment 8: The author should mention to this work more carefully and should update  some of the listed references in his paper in order to add a powerful for the paper. To help the author in this direction. I suggest the following references. A numerical performance of the novel fractional water pollution model through the Levenberg-Marquardt backpropagation method. IoT technology enabled stochastic computing paradigm for numerical simulation of heterogeneous mosquito model. A computational supervised neural network procedure for the fractional SIQ mathematical model.Numerical performances through artificial neural networks for solving the vector-borne disease with lifelong immunity.A mathematical model of coronavirus transmission by using the heuristic computing neural networks.

Comment 9: A real application of the considered problem with the different mentioned effects should be mentioned and discussed.

Author Response

We sincerely hope that this revised manuscript has addressed all your comments and suggestions. We appreciated for reviewers’ warm work earnestly,and hope that the correction will meet with approval.Once again,thank you very much for your comments and suggestions.

Thanks again for taking the time to review our manuscript!

Author Response File: Author Response.pdf

Reviewer 5 Report

 

1.          This abstract is better to add the result in numbers. The abstract should state briefly the purpose of the research, the principal results and major conclusions. An abstract is often presented separately from the article, so it must be able to stand alone.

2.      Please underscore the scientific value added/contributions of your paper in your abstract and introduction and address your debate shortly in the abstract.

3.      What has been studied Introduction should be clearly stated research questions and targets first.

4.      The introduction is better separated into 2 sections. 1. Introduction and 2 Related works.

5. Comparative analyses need to be conducted and specific contribution needs to be done.

6.      Basically, you should enhance your findings, limitations, underscore the scientific value added of your paper, and/or the applicability of your contributions/shortages and future study in this session.

 

 

 

Author Response

We sincerely hope that this revised manuscript has addressed all your comments and suggestions. We appreciated for reviewers’ warm work earnestly,and hope that the correction will meet with approval.Once again,thank you very much for your comments and suggestions.

Thanks again for taking the time to review our manuscript!

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

The revised paper can be accepted. 

Author Response

Thank you very much for your second review of our paper.We have revised the language part of the full text.

We sincerely hope that this revised manuscript has addressed all your comments and suggestions. We appreciated for reviewers’ warm work earnestly,and hope that the correction will meet with approval.Once again,thank you very much for your comments and suggestions.

 

Thanks again for taking the time to review our manuscript!

Author Response File: Author Response.pdf

Reviewer 4 Report

Manuscript ID: applsci-2203197 and Title: Reactor temperature prediction method basedon CPSO-RBF-BP neural network

1-The introduction could be updated with recent reviews dedicated to applicationof CPSO-RBF-BP neural network.

 

2- English language needs some improvement throughout the paper.

 

3. The author should mention to this work more carefully and should update someof the listed references in his paper in order to add a powerful for the paper. To help the author in this direction. I suggest the following references. A numerical performance of the novel fractional water pollution model through theLevenberg-Marquardt backpropagation method. IoT technology enabled stochastic computingparadigm for numerical simulation of heterogeneous mosquito model. A computational supervised neural network procedure for the fractional SIQ mathematical model.Numerical performances through artificial neural networks for solving the vector-borne disease withlifelong immunity.A mathematical model of coronavirus transmission by using the heuristiccomputing neural networks.

 

Author Response

 

Thank you very much for your second review of our paper.

We sincerely hope that this revised manuscript has addressed all your comments and suggestions. We appreciated for reviewers’ warm work earnestly,and hope that the correction will meet with approval.Once again,thank you very much for your comments and suggestions.

Thanks again for taking the time to review our manuscript!

Author Response File: Author Response.pdf

Reviewer 5 Report

----------

Author Response

Thank you very much for your second review of our paper.We have revised the whole paper in terms of language.

We sincerely hope that this revised manuscript has addressed all your comments and suggestions. We appreciated for reviewers’ warm work earnestly,and hope that the correction will meet with approval.Once again,thank you very much for your comments and suggestions.

Thanks again for taking the time to review our manuscript!

Author Response File: Author Response.pdf

Back to TopTop