Performance Comparison of Particle Swarm Optimization, Differential Evolution and Artificial Bee Colony Algorithms for Fuzzy Modelling of Nonlinear Systems

Abstract

This paper presents the results of the nonlinear system modelling approach based on the use of fuzzy rules optimized by different population based optimization algorithms. Fuzzy rule based models with different number of the rules are used to describe the some nonlinear systems in the literature. Firstly, parameters of the fuzzy models are determined by the artificial bee colony (ABC) algorithm. To demonstrate the efficiency of the ABC algorithm, its modelling ability is compared with the other two powerful population based algorithms, particle swarm optimization (PSO) and differential evolution algorithm (DEA). Simulation results show that a successful model performance with good description ability in the modelling of nonlinear or complex systems can be obtained by using one of the population based algorithms in design of the fuzzy rule based models.

The Performance of Binary Artificial Bee Colony (BABC) in Structure Selection of Polynomial NARX and NARMAX Models

“…The performance of ABC is compared with another swarm-inspired optimization algorithm, the BPSO [37] with the experiment design focusing on solution quality and convergence consistency. This work is motivated by previous works [38], [39] that suggest that the ABC algorithm is capable of outperforming PSO in terms of local and global optimization problems.…”

ABC and DE Algorithms based Fuzzy Modeling of Flight Data for Speed and Fuel Computation

“…In this process called mutation, the differences between solution elements are weighted and added to another solution element to obtain solution diversity. The general form of such an operation can be given as follows 16,40 :…”

“…Thus, using the flight parameters generated by the model when necessary, more confident and accurate decisions can be made for flight safety. One of the fast and most effective methods that can be used for this purpose is the fuzzy modeling approach 11,16,17,41 .…”

“…Figure 1. Fuzzy model structure used in the study For modeling the multi-input multi-output system, the fuzzy model structure presented by Bagis is preferred 11,16,17,41 . In this model structure called as "singleton model", the reasoning procedure is provided by multiplying the weighted input membership functions and the output singleton values.…”

“…Parameters of the fuzzy models are optimized by using artificial bee colony (ABC) and differential evolution (DE) algorithms. Several successful fuzzy modeling studies based on the use of artificial intelligence algorithms are available in the literature [8][9][10][11][12][13][14][15][16][17] . Genetic algorithm is used to obtain Takagi-Sugeno type fuzzy model structure in the study presented by Siarry and Guely 8 .…”