Enhanced Beetle Antennae Algorithm for Chemical Dynamic Optimization Problems’ Non-Fixed Points Discrete Solution
Round 1
Reviewer 1 Report
The idea of the manuscript (Beetle Antennae Algorithm for Chemical Dynamic Optimization) is interested.
A statistical comparison with 5 algorithms (PSO, BAS, WOA, ALO AND HBSO) was achieved on 10 benchmarking functions.
1- I have a concern about the performance of the introduced EBSO algorithm (Figs 7 to 16) which seems to be too perfect:
From an algorithmic point of view, what makes the EBSO always better than other known optimizers (such as PSO and WOA)?
This concern is motivated by the fact that the manuscript does not clearly explain if these is a set of mechanism helping in escaping local optima (especially for many-objective problems).
2- Due to the stochastic aspect of the optimization algorithms, the computed values should be taken using an average number of runs
(20-50 average number for each value). It is not mentioned in the manuscript if the values are taken as averages or not.
3-Moreover, the contribution of the used optimization approach should be justified. I recommend to refer to the following references (https://www.doi.org/10.1007/s10732-020-09445-x, https://doi.org/10.1016/j.asoc.2020.106078, https://www.doi.org/10.1109/IWCMC.2018.8450372 and https://doi.org/10.1016/j.engappai.2020.103666) clearly explaining the need of optimization approach to resolve complex real-world problems like yours.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 2 Report
The authors performed optimization investigations for several chemical engineering problems
using the beetle antenna optimization (EBSO). The paper presents interesting results. I have
the following comments:
· What is the difference between the EBSO and the general genetic algorithm?
· Is that possible to compare the current algorithm with physics informed neural
network algorithm? Do the authors have any estimation about the robustness of the
two algorithms?
· If we decrease the time step, would the zigzag nature of Figure 18 will disappear?
· The authors must provide figures to show how their method is compared to other
methods mentioned in the manuscript. For example, they must provide a figure that
compares their method's results with IKBCA, IKEA, VSACS,SACA, IACA,
MOARA, and AEPF methods. This will help the reader understand better the
behaviour of the newly developed algorithm, and also it will provide a tool to verify
the conclusions made by the authors.
·
· The authors should improve the writing of the manuscript. For example, there are
many grammatical mistakes, such as “Apply” in the abstract need to change to “ We Apply. "
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 2 Report
The authors have done an excellent job of revising the manuscript.