Research on Synthesis of Multi-Layer Intelligent System for Optimal and Safe Control of Marine Autonomous Object
Round 1
Reviewer 1 Report
The relevance of the article is determined by the following fact. The wide introduction of modern methods and means of complex automation of ship motion control provides the reduction of operational costs and accident rate. This is due to the exclusion of subjective factors from the process of ship control. One of the promising approaches in the development of complex control systems, which include automatic ship motion control systems, is the use of complex approach with the application of computer modeling methods. Since computer models of complex systems should be built on the modular principles of multilevel hierarchy, the authors used this approach to develop a multilevel intelligent system of optimal and safe control of a marine autonomous object.
In the course of their research, they decomposed the ship motion control process into several levels. This approach allowed them to choose the most appropriate control methods to achieve the goal at each level. At the highest level, related to the calculation of the optimal ship route, the authors proposed to use the evolutionary programming. The next level of control is related to ensuring the safety of ship traffic. To solve this problem, the authors proposed to use three scientific methods. The first one is a dynamic programming with neural state constraints. The second one is an ant colony optimization. The third one is the fuzzy control method. At the next level of decomposition, the problem of providing optimal reliable control of ship motion is considered. To solve this problem, the authors propose to use two methods: LMI and predictive line-of-sight method. At the lowest level of control, a block diagram of switching-based multi-operational ship motion controller was developed (Fig.18).
Provided theoretical methods and control algorithms were subjected to computer modeling. The obtained results should show the readers the effectiveness of the developed multilevel intelligent system of optimal and safe control of marine autonomous object.
The scientific novelty of the article is based on the development of a number of alternative methods at different stages of the ship motion control process. Thanks to this, the developers of ship control systems will be able to reasonably choose the most effective methods for each level, allowing to reduce operational costs and accident rate.
The practical significance of the paper is that most of the proposed control methods were used to create a block diagram of switching-based multi-operational ship motion controller.
Remarks.
1. It is obvious that the proposed methods largely depend on the decomposition of the ship control process into hierarchical levels. However, the article lacks justification of such decomposition. It is necessary to add material justifying this hierarchical structure of the control process.
2. Movement to the port of destination is carried out according to predetermined ship routes. At the same time, the issues of reducing operational costs for cargo delivery have already been solved when these routes are chosen. However, the issues of building an optimal route may arise in a situation when another ship is in distress. In this case, the ship motion control system may face the task of laying a route with minimum length.
The relevance of optimal path computation should be changed.
3. The authors proposed three methods to improve traffic safety: dynamic programming, ant colony optimization and fuzzy control. Computer simulations were performed to evaluate the effectiveness of each method. Figures 3 and 4 show the simulation of ship motion when dynamic programming is used. Figures 6 and 7 are for the case when ant colony optimization is used. Figures 9 and 10 are for the case when fuzzy programming is used. The analysis of these figures shows that they propose different routes for the ship movement. In this case, it is quite difficult to determine which of the given method is the most efficient.
Authors should analyze these figures and conclude on the feasibility of the most effective control method.
4. The block diagram of the multi-operational ship motion controller presented in the paper does not use the developed methods that allow to increase the efficiency of ship control at the two upper levels. In this case, the question arises about the feasibility of the hierarchical structure of the control system chosen by the authors, starting from the selection of the optimal path of motion and ending with the direct control of the ship.
5. In the developed block diagram of the multi-operational ship motion controller, the authors propose to use two methods simultaneously: LMI and predictive line-of-sight method. However, it was said earlier that the predictive line-of-sight method provides lower accuracy values than the LMI. The following question arises: why should two methods be used in the ship motion control system, when LMI method single-handedly provides optimal ship motion.
The style of the English language is good, does not require significant editing.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 2 Report
The current paper presents the synthesis of a marine autonomous surface ship’s group multilayer control system using modern control theory methods. The theory is validated using simulations.
Comments to authors:
- Please add more details of how the theory from the first sections is applied in the results section.
- The authors can add the steps of implementing the backpropagation algorithm. The theoretical part can be better detailed. The steps will be to the benefit of the readers, maybe they’ll help the readers to implement the proposed backpropagation algorithm.
- Define and detail all the parameters used.
- Add both the advantages and the disadvantages of the proposed method, in the current version of the paper only the advantages are presented. And which method is better to be used?
- Add the measurement units labels for abscissa and ordinate for all the figures from the paper. the figures don’t have the same format, for example some of them have the background with, some of them have the background grey
- The state of the art it is poor regarding representative papers, maybe the author could add the following publications:
o Hybrid Data-Driven Fuzzy Active Disturbance Rejection Control for Tower Crane Systems, European Journal of Control, vol. 58, pp. 373-387-11, 2021.
o Enhanced P-type Control: Indirect Adaptive Learning from Set-point Updates, IEEE Transactions on Automatic Control, DOI: 10.1109/TAC.2022.3154347, 2022.
- Please add more comments regarding the obtained results.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
Please see the comments in the uploaded file.
Comments for author File: Comments.pdf
Minor editing of English language required.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 2 Report
The authors answered to all my concerns. From my point of view the paper has been significantly improved and can be accepted to be published in Electronics Journal.
Reviewer 3 Report
The comments have been considered.
Minor editing of English language required.