Finite-Time Prescribed Performance Tracking Control for Unmanned Helicopter System Using Neural Network

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

With respect to the manuscript, I was invited to review. This is my opinion below:

 

This article could represent a valuable addition in investigating a finite-time tracking controller for the UH system with performance constraints, model uncertainties and external perturbations. A novel prescribed performance function is designed to preset the tracking errors within  prescribed boundaries, so that the transient tracking performance and steady-state accuracy can be reasonably constrained.

The authors made a very good introduction to describe their idea, make a good simulation work.  Besides, the quality of the writing manuscript was written well. So, finally, I recommend accepting the manuscript.

 

 

I want to thank the authors for this valuable work.

 

Best Regards

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

This paper approaches the problem of tracking control for unmanned helicopter system using neural networks.

The paper has an accentuated theoretical character.

In the reviewer opinion the content of the paper could be improved if the authors add more details concerning the neural network component. Thus, the neural network component claimed in the title as being one of the main contributions of the paper is very poorly represented in the text. Thus, the authors refer 6 times to the RBFNN component, namely: 3 times when presenting the RBFNN general concept, once in Fig.1 when presenting the "overview of the control architecture", once in a mathematical model as a "lump function F", and last in Algorithm 1, as a calling procedure. Nothing about how this NN is trained, which are the training input and output variables, how these variables are collected etc etc etc

The reviewer encourages the authors to rethink the paper through the view point of this comment.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

The paper investigates an improved composite finite-time tracking control scheme for an unmanned helicopter system. The control scheme aims to cover performance constraints, model uncertainties and external perturbations. A continuous adaptive law is developed to deal with neural network approximate errors and thus improve the system robustness.

The paper is well written and structured, although there is a bit too much math there with all the theorems and proofs. It would be of interest to the researchers in this field of work and has good merits for publication. Still, some minor comments need to be properly addressed before publication is recommended:

1) The quality of English language is generally good, but there are a few places where corrections are needed. Just as an example, in the conclusions, line 611: “…an improved finite-time tracking controller are investigated…” (“are” should be “is”). Lines 622-624: “t can be observed from the simulations that compared with the existing control schemes, the control method in this paper can guarantee more accurate and faster tracking with prescribed performance.” The sentence should be reformulated for better comprehension. This is also related to the selection of words. For instance, why do you say “the control method in this paper can guarantee…”? If this is so, then write simply “the control method proposed in this paper guarantees…” Also, in line 142, you may easily find a better option for the word “described”. In line 147, “mode modified” is confusing. Etc.

2) The literature review is generally fine. However, a vast majority of the literature cover a specific geographic region. I would suggest to pay attention to thus fact. Also, one may put the research into a broader context by mentioning works providing methods for suitable selection of drone for various tasks:

Gül, A., Cakmak, E., & Karakas, A. (2024). Drone selection for forest surveillance and fire detection using interval valued neutrosophic edas method. Facta Universitatis-Series Mechanical Engineering, doi: 10.22190/FUME231028008G

3) It is not advisable to use Equation Editor in the text, as it has been done after Eq. (1). One may easily notice that those terms are not in the same line with the text, but moved somewhat upwards, which does not look nice. Furthermore, some letters are written using italic font, while others use normal font.

4) In lines 154-158, the authors introduce certain assumptions. The conclusions should include limitations of the work presented and should also mentioned how those assumptions affect the developed controller. What would be the effect if one or some of the assumptions are not met.

5) In some of the diagrams, the font size is too small for good readability. This is particularly related to the legends. The units should be placed into brackets []. Check for instance Fig. 3 – for vertical axes the unit is put into parenthesis, but for horizontal axis, a slash is used. Some figures could and should be larger.

Comments on the Quality of English Language

As per comment 1 for authors. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

No more comments.