Next Article in Journal
Theoretical Model of Self-Magnetic Flux Leakage and Its Application in Estimating the Depth Direction of a Fatigue Crack
Next Article in Special Issue
Bulk Solids Stacking Strategy of a Rectangular Ship Cabin
Previous Article in Journal
In Vitro Evaluation of a Non-Invasive Photoplethysmography Based Intracranial Pressure Sensor
Previous Article in Special Issue
Study on the Influence of Gear Spoke Hole Numbers on Meshing Noise
 
 
Article
Peer-Review Record

Networked Control System Based on PSO-RBF Neural Network Time-Delay Prediction Model

Appl. Sci. 2023, 13(1), 536; https://doi.org/10.3390/app13010536
by Dazhang You 1,*, Yiming Lei 1,*, Shan Liu 1, Yepeng Zhang 1 and Min Zhang 2
Reviewer 1:
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Appl. Sci. 2023, 13(1), 536; https://doi.org/10.3390/app13010536
Submission received: 21 November 2022 / Revised: 22 December 2022 / Accepted: 26 December 2022 / Published: 30 December 2022
(This article belongs to the Special Issue New Frontiers in Advanced Manufacturing)

Round 1

Reviewer 1 Report

This paper presents a Networked control system based on PSO-RBF neural network time-delay prediction model. From the technical aspects, the paper has enough contribution. However, there are some minor issues that need to be addressed:

1- In introduction, some credits to the recent works are suggested to enrich the literature like Solar energy, Volume 183, 1 May 2019, Pages 1-16; Engineering Review, 2021, 41 (2), 26-40; WSEAS TRANSACTIONS on SYSTEMS and CONTROL, 2020, 15 (37), 356-365; 2022 8th International Conference on Control, Decision and Information Technologies (CoDIT), DOI: 10.1109/CoDIT55151.2022.9804021;Protection and Control of Modern Power Systems, 2019, 5 (1), 1-17; International Journal of Control Systems and Robotics, 2019, 4, 115-123 ;ISA Transactions, 2016 (60), 333-347; ICIC Express Letters, 2017, 11 (4), 763-772; Mechanical Systems and Signal Processing, 2018 (100), 466–481; International Conference on Electrical Engineering and Software Applications, DOI: 10.1109/ICEESA.2013.6578380

2- In terms of theory, this reviewer needs to see more to justify that this work gives new contributions. The motivation of the study should be further emphasized. In particular, the main contributions of the results in this paper should be clearly demonstrated.

3- The unique features of the proposed study and the main advantages of the results over others must be clearly commented. And a comparison with existing results will be useful to demonstrate the usefulness of this paper. In particular, the advantages and contributions of this paper compared with others should be highlighted.

4- The proposed control strategy requires many design parameters, so, could you please show how to choose these parameters and the effect of them? This will give readers the insight of the physical meaning of your approach and is good for regeneration.

5- More physical interpretation and explanations are required to be discussed in the presented graphs.

6- Some related papers need to be added in the revision version and some outdated references can be removed.

All these comments are mandatory, and I expect positive answers to these comments and the revision of the paper accordingly.

Author Response

Please see the attachment!

Author Response File: Author Response.docx

Reviewer 2 Report

1. The authors are suggested to further emphasize new or novelty of this proposed method through theory part, in order to show the contributions of this method. What are the technical challenges in these extensions? What can we learn from this paper?

 2. What's the limitation of the proposed method?

3. Authors should provide some practical examples to show the effectiveness of the result.

4. There are some typos and grammatical errors. The authors should check carefully and correct seriously.

5. The reviewer want to know the convergence of the neural netwok. Please explain in detail.

Author Response

Please see the attachment!

Author Response File: Author Response.docx

Reviewer 3 Report

The paper deals with an actual scientific and practical problem of research and development of a controller for distributed control systems. 

A feature of the research is the delays associated with the use of network technologies.

The article uses a neural network to predict network delay.

The analysis of the learning algorithm of the neural network  was performed.

A numerical experiment was performed on the basis of the TrueTime platform.

The effectiveness of the proposed approach is compared with various types of linear control systems.

 

Remarks

 

1. There are many stylistic errors in the article (they are highlighted in the attached file).

2. The article uses a description of existing learning algorithms known since 2008. References to these algorithms and an analysis of why these algorithms were chosen should be added.

3. In the formulation of the problem, a model in the state space is used.

4. The example uses a transfer function.

5. From the article, the type of the control object is not entirely clear, since this largely explains the nature of the time delay.

Comments for author File: Comments.pdf

Author Response

Please see the attachment!

Author Response File: Author Response.docx

Round 2

Reviewer 3 Report

All the remarks are taken into acount by the authors.

Back to TopTop