Anchor Chain Optimization Design of a Catenary Anchor Leg Mooring System Based on Adaptive Sampling
Round 1
Reviewer 1 Report
TITLE: ANCHOR CHAIN OPTIMIZATION DESIGN OF A CATENARY ANCHOR LEG MOORING SYSTEM BASED ON ADAPTATIVE SAMPLING
GENERAL COMMENTS
The subject of this paper is very interesting and that should be of interest to Journal of Marine Science and Engineering mdpi readers. I think the authors have tried to put their findings into context and my comments/suggestions are only for minor points.
MINOR POINTS/COMMENTS
An initial/preliminary section (list of all parameters (with units) and acronyms of the paper) before the introduction’s section is recommended.
[line 45] Which authors? You or Félix-González et al. ?
[line 188] Formatting style.
[line 290] Formatting style.
ENGLISH LANGUAGE AND STYLE
English language and style are fine/minor spell check required.
OVERALL RECOMMENDATION
Accept with minor changes.
Comments for author File: 
Comments.pdf
Author Response
1.An initial/preliminary section (list of all parameters (with units) and acronyms of the paper) before the introductions section is recommended.
Author reply:Thanks for the reviewer's suggestions. The initial/preliminary section will be added. See the following for the revision details:
|
Symbol |
Unit |
|
(ï¿¥) |
Yuan |
|
(m) |
Buoyancy offset distance |
|
(mm) |
Anchor diameter |
|
PA (°) |
Pretension angle |
|
Tv (N) |
Vertical force |
|
T |
Anchor chain tension safe factor (the ratio of maximum chain tension and actual tension) |
|
Dm |
fatigue damage factor |
2.[line 45] Which authors? You or Félix-González et al. ?
Author reply:Thanks for the reviewer's suggestions, the author is Félix-González et al. Corresponding contents have been revised in the paper on line45. The revised content is as follows:
“Felix-Gonzalez et al. [1] established a fully symmetrical and bilaterally symmetric two-dimensional static equivalent mooring system model. The root mean square error of equivalent model displacement and root mean square error of numerical model displacement are taken as objective functions, and the genetic algorithm is used to optimize.”
3.[line 188] Formatting style.
Author reply:Thanks for the reviewer's suggestions, corresponding contents have been revised in the paper on line188.
Please see the attachment
4.[line 290] Formatting style.
Author reply:Thanks for the reviewer's suggestions, corresponding contents have been revised in the paper on line 290.
Adaptive Sampling Optimization
5. English language and style are fine/minor spell check required
Author reply: Thanks for reviewer's advice, some grammar and words have been modified and marked in the paper
Author Response File: 
Author Response.docx
Reviewer 2 Report
The problem described by the authors of the article is relevant. The solutions proposed are not new. But even in this solution, the authors described weakly. The mathematical model should contain more restrictions. Layers in a neural network are not justified. Why are there so many of them and will the error be minimal? Is it necessary to use a neural network? The authors poorly analyze the obtained indicators. The conclusions do not contain all the tasks set and solved in the right form.
Author Response
The problem described by the authors of the article is relevant. The solutions proposed are not new. But even in this solution, the authors described weakly. The mathematical model should contain more restrictions. Layers in a neural network are not justified. Why are there so many of them and will the error be minimal? Is it necessary to use a neural network? The authors poorly analyze the obtained indicators. The conclusions do not contain all the tasks set and solved in the right form.
Author reply:
Thank you for the reviewer's comments. I divide the reviewer's comments into three parts and reply one by one.
(1) The problem described by the authors of the article is relevant. The solutions proposed are not new. But even in this solution, the authors described weakly. The mathematical model should contain more restrictions.
Author reply:
The work of the paper is to develop an optimization design framework, which takes the minimum cost of the catenary mooring system (CALM) as the optimization goal, and the diameter and tension Angle of the anchor chain in CALM as the design variables. The program framework uses RBF to build an approximate model, and uses genetic algorithm to search for global optimization of the proxy model. Then, based on the global optimization results, sequential quadratic programming is carried out to search for local optimization results. In the optimization process, we introduce the adaptive sampling method to improve the optimization effect significantly.
The detailed mathematical constraint information is as follows：
The constraint conditions are further refined as follows. It can be seen that the derivation of each constraint almost depends on a large amount of numerical calculation work. Since the calculation of these parameters is not the focus of this paper, the paper lists the constraints for the main variables.
Please see the attachment.
(2) Layers in a neural network are not justified. Why are there so many of them and will the error be minimal? Is it necessary to use a neural network?
Author reply:
Thanks for the reviewer's comments. In the paper, RBF approximate model was used, which took Gaussian function as radial function and built mathematical model through linear superposition. It is a three-layer network structure (input layer, hidden layer and output layer). The increase in the number of neurons in the middle layer will increase the nonlinearity of the model and make the approximation more accurate [1]. The focus of the paper is to explore the fast optimization of mooring chain. On the basis of accurate prediction of the approximate model, the optimization was carried out. The adaptive sampling method is introduced in the optimization process to further solve the problem that all variables are within the constraint range when the optimal solution is obtained, so as to minimize the number of sample points in the whole process. The experimental data in this problem comes from the field experimental data of a project in Bohai, China. Because the RBF approximate model has strong nonlinear fitting ability and simple learning rules, it is easy to implement by computer.
[1] Irie Bunpei, Miyake Sei. Capabilities of three-layered perceptrons. In: IEEE international conference on neural networks; 1988. p. 218.
(3) The authors poorly analyze the obtained indicators. The conclusions do not contain all the tasks set and solved in the right form.
Author reply:
This paper proposes a rapid optimization design framework for CALM mooring chain, and compares the optimization results with commercial software to verify the accuracy of the framework. At the same time, in order to satisfy the constraint conditions of the design variables in the optimization results, the adaptive sampling method was introduced in the optimization process to ensure the accuracy of the constraint variables and the optimization results. Figure 1 shows the results of the optimization program and the commercial software, except for fatigue damage Dm, the errors of other variables are all less than 2% in two optimization process. In order to solve this problem, adaptive sampling is introduced after the first optimization. Table 2 shows that the fatigue damage error decreases obviously, and the optimization results of quadratic function satisfy the constraint conditions.
The conclusion is modified as follows:
In this paper, a fast optimization framework of mooring anchor chain is established. The optimization framework is to use RBF to construct the approximate model, and then use genetic algorithm to carry out global optimization of the proxy model. In order to reduce the fatigue damage error, adaptive sampling is carried out on the basis of the global optimal solution and the sequential quadratic programming algorithm is used to carry out local optimization. Compared with the results calculated by AWQA, all variables satisfy the constraint conditions, and more accurate optimization results are obtained. At the same time, the adaptive sampling method is added to the optimization program to reduce the calculation time and the number of sample points, and improve the accuracy of the approximate model. By comparing different types of adaptive functions, the quadratic function is determined to be suitable for anchor chain optimization.
Author Response File: Author Response.docx
Reviewer 3 Report
The paper is interesting and regarding a serious topic, but should be improuved with a short analisys and a panoramic of main dimensions of ships involved and, if possible, a quick reference of main accodents (if possible) related to lack of mooring systems, in order to explain better the avantages of the system.
Author Response
Reviewer #3
GENERAL COMMENTS
The paper is interesting and regarding a serious topic, but should be improved with a short analysis and a panoramic of main dimensions of ships involved and, if possible, a quick reference of main accodents(if possible) related to lack of mooring systems, in order to explain better the advantages of the system.
Author reply：
Thanks for the reviewer's suggestions. The following content will be added in the second chapter Problem description：
“The mooring ship in this study is a 300,000 ton large oil tanker with a scale of 320 meters long, 60 meters wide and 30.5 meters height. Considering that ballast draft and full load draft are typical loading conditions of mooring, CALM can replace the wharfs to transfer crude oil from tanker to shore by pipelines. CALM has advantages of less investment compared to wharfs. However, it is complicated and tedious to choose the scheme with good mooring performance and economy, which brings challenges to mooring design. This study is to establish a program to quickly obtain an optimal mooring scheme to solve this problem.”
Author Response File: Author Response.docx
Round 2
Reviewer 2 Report
corrections done
Reviewer 3 Report
Writing that a supplementary description required is "tedious" is nt exactly a "politically correct" answer, it sounds a bit like "I have no time to fulfill your silly requests..!! ".. but , serioulsy, the overall result of the paper is interesting and well described.
