Aims:
Different chaotic APSO-based algorithms are developed to deal with high non-linear
optimization problems. Then, considering the difficulty of the problem, an adaptation of these algorithms
is presented to enhance the algorithm.
Background: :
Particle swarm optimization (PSO) is a population-based stochastic optimization technique
suitable for global optimization with no need for direct evaluation of gradients. The method
mimics the social behavior of flocks of birds and swarms of insects and satisfies the five axioms of
swarm intelligence, namely proximity, quality, diverse response, stability, and adaptability. There are
some advantages to using the PSO consisting of easy implementation and a smaller number of parameters
to be adjusted; however, it is known that the original PSO had difficulties in controlling the balance
between exploration and exploitation. In order to improve this character of the PSO, recently, an
improved PSO algorithm, called the accelerated PSO (APSO), was proposed, and preliminary studies
show that the APSO can perform superiorly.
Objective:
This paper presents several chaos-enhanced accelerated particle swarm optimization methods
for high non-linear optimization problems.
Method:
Some modifications to the APSO-based algorithms are performed to enhance their performance.
Then, the algorithms are employed to find the optimal parameters of the various types of hysteretic
Bouc-Wen models. The problems are solved by the standard PSO, APSO, different CAPSO,
and adaptive CAPSO, and the results provide the most useful method.
Result:
Seven different chaotic maps have been investigated to tune the main parameter of the APSO.
The main advantage of the CAPSO is that there is a fewer number of parameters compared with other
PSO variants. In CAPSO, there is only one parameter to be tuned using chaos theory.
Conclusion:
To adapt the new algorithm for susceptible parameter identification algorithm, two series
of Bouc-Wen model parameters containing standard and modified Bouc-Wen models are used. Performances
are assessed on the basis of the best fitness values and the statistical results of the new approaches
from 20 runs with different seeds. Simulation results show that the CAPSO method with
Gauss/mouse, Liebovitch, Tent, and Sinusoidal maps performs satisfactorily.
Other:
The sub-optimization mechanism is added to these methods to enhance the performance of the
algorithm.