Safe Three-Dimensional Assembly Line Design for Robots Based on Combined Multiobjective Approach
Round 1
Reviewer 1 Report
The proposed algorithm solves the problem of layout design of assembly line for robots. The performance of the proposed one was compared with other state-of-the-art approaches and the effectiveness of the proposed one is shown. The overall structure is well-written but the reviewer thinks more description is necessary. The reviewer has the following comments and questions.
- The reviewer thinks that technical breakthrough of the proposed method is not so clearly written. Please write more clearly which parts in the proposed method was difficult to solve in the former literature and how the proposed one could solve it with high technology level approach.
- The reviewer thinks that the authors need to write the reasons why they select NSGA-II and MOCell for comparison. The reviewer guesses that so many related approaches have been proposed in the former literature.
- The reviewer could not understand the importance of the obtained results. Even if we see Table 8 or Figure 6, the reviewer thinks that the readers of this paper could not understand the meaning of the obtained numbers, and how these are important from the viewpoint of application. More and more description is necessary.
- The reviewer would like to see what kind of pareto solutions are obtained with the proposed one. The reviewer would like to see the variety of the obtained solution with the proposed one.
- The reviewer thinks that, in order to discuss the scope and limitation of the proposed approach, more problems should be tested and compared each other.
- More quantitative description is necessary in the conclusion chapter. Contribution of this paper needs be written more clearly and more quantitatively.
Author Response
We thank the reviewers for the constructive comments and suggestions on our manuscript. Accordingly, we have carried out additional experiment and revised the manuscript carefully. The changes are marked in RED in the revised manuscript. The revised content is highlight in the article.
The detailed attachment. Thank you.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The study approaches pretty important for managers issue of layout planning, in this case there is an attempt to propose and validate model for design layout of robots for their safety. I see many shortcomings in this study.
- the study aims are not presented in a clear manner, also in the abstract
- the contribution to the science / knowledge is not presented in comprehensive way, the contribution is not discussed
- proposed model are not confronted to other models we know, the advantages for managers and plant designers are not specified
- effects / output of simulation / experiment are not presented clearly enough
Author Response
We thank the reviewers for the constructive comments and suggestions on our manuscript. Accordingly, we have carried out additional experiment and revised the manuscript carefully. The changes are marked in RED in the revised manuscript. The revised content is highlight in the article.
The detailed attachment. Thank you.
Point 1: The study aims are not presented in a clear manner, also in the abstract
Response 1: Section 1 and abstract in the article have been completely revised. It points out that few studies have considered the safe layout of application scenarios for assembly lines with robots. Those studies have not optimized the complete layout of workstations, machines, robots and have not designed a three-dimensional layout that highlight safety. The commonality of cited references has been summarized, the language introduced in Section 1 of the article has been condensed.
Point 2: The contribution to the science / knowledge is not presented in comprehensive way,
Response 2: Quantitative analysis is added on the basis of qualitative analysis to make the contributions of this article clear. Our contribution is shown as follows: The modelling rules for robots and irregular equipment are presented, a combined SE-NSGA2 method that is based on NSGA-II and the DE strategy is used to generate the initial optimal plan set. Consequently, we define the verification process, propose a quantitative safety indicator, and assess the cooperative assembly statuses of robots. Finally, 3D safety collision detection is performed to verify the safety and effectiveness of the layout scheme. Compared to state-of-the-art algorithms, our approach has superior performance concerning the convergence and distribution results. Our experimental and statistical results of optimal layout plan for assembly lines increase by 14.5%, and our approach can generate a safety layout to optimize economics and safety. Compared with the original NSGA-II method, the safety layouts increase by 20.63%.
Point 3: The proposed model are not confronted to other models we know, the advantages for managers and plant designers are not specified
Response 3: Many researchers have proposed layout design models [33], and a large number of researchers have proposed equal-area and unequal-area layout models, and a linear layout of sewing assembly line equipment of equal area[17] which lacks consideration of the layout of robot equipment in the assembly line. There are also some researchers who focus on the layout optimization of the robot cell [lim], however the model only uses the oblique grid for sequence pair method for the special scene of the robot cell which is not suitable for the assembly line layout. The safety assembly model (SLM) we proposed is different from the model which has been proposed from the modelling object to the optimization goal. Moreover, a single optimization goal cannot meet the complex assembly line layout demands. The two important indicators of the smallest logistics cost and the smallest floor space are considered to be multiple objectives for optimization, on which the assembly line safety layout optimization model is established.
Point 4: The effects / output of simulation / experiment are not presented clearly enough
Response 4: We add the comparison experiment that use the general layout model (GLM) [reference] and the safety layout model (SLM) to prove the performance between the SE-NSGA2 and other mainstream methods in the first experiment. The results in the table indicate that the SE-NSGA2 approach is superior to other methods concerning the number of optimal plans and diversity of plans.
The experiment that we add proves that safety performance of a safe assembly line layout is verified. The 3D scene is connected to the database in a data-driven manner to verify the feasibility and rationality of safe layouts and the effectiveness of safe layout plans. Because the coordinators of the centre point of the collision area are constantly changing, the collision point is continuously covered, which is not easy for readers to observe. Therefore, statistical experiments are done to draw the projected area of the ground as shown in Figure 6, and Figure 7 in which the number of collisions are shown. Overall, by calculating layout improvement index, the safety of the assembly line layout increases by 20.63%. Therefore, SE-NSGA2 has significant advantages in the multiobjective optimization of assembly line safety.
The experiment we add indicates that safety layouts are a prerequisite to guaranteeing economics optimizing. The schematic diagram of Pareto set is shown in Figure 8. It can be seen from Figure 8 that the distribution and diversity performance of SE-NSGA2 is better than that of in MOCell and NSGA-II methods.
Two experiments are designed to prove the performance of the SE-NSGA2. In the first experiment, the benchmark test function verifies that the proposed approach SE-NSGA2 has excellent convergence and distribution performance. In the second experiment, the case study verifies the SE-NSGA2 can generate the diversity of safe and useful layout plans to obtain an optimum between economics and safety. Our experimental and statistical results of optimal layout plan for assembly lines increase by 14.5%, and the safety performance of assembly line layout increased by 20.63%.
Author Response File: 
Author Response.docx
Round 2
Reviewer 1 Report
The reviewer thinks that all the comment are clearly answered from the authors, and the draft are revised correctly.
The reviewer judges that this can be accepted.
Reviewer 2 Report
I have found authors' improvements as interesting, substantial and addressing hitherto comments well enough. I particularly appreciate study aims improvement, results discussion, contribution brought by algorithm. In my opinion this study deserves to be published.
