Opposition-based ant colony optimization with all-dimension neighborhood search for engineering design

Abstract

The ant colony optimization algorithm is a classical swarm intelligence algorithm, but it cannot be used for continuous class optimization problems. A continuous ant colony optimization algorithm (ACOR) is proposed to overcome this difficulty. Still, some problems exist, such as quickly falling into local optimum, slow convergence speed, and low convergence accuracy. To solve these problems, this paper proposes a modified version of ACOR called ADNOLACO. There is an opposition-based learning mechanism introduced into ACOR to effectively improve the convergence speed of ACOR. All-dimension neighborhood mechanism is also introduced into ACOR to further enhance the ability of ACOR to avoid getting trapped in the local optimum. To strongly demonstrate these core advantages of ADNOLACO, with the 30 benchmark functions of IEEE CEC2017 as the basis, a detailed analysis of ADNOLACO and ACOR is not only qualitatively performed, but also a comparison experiment is conducted between ADNOLACO and its peers. The results fully proved that ADNOLACO has accelerated the convergence speed and improved the convergence accuracy. The ability to find a balance between local and globally optimal solutions is improved. Also, to show that ADNOLACO has some practical value in real applications, it deals with four engineering problems. The simulation results also illustrate that ADNOLACO can improve the accuracy of the computational results. Therefore, it can be demonstrated that the proposed ADNOLACO is a promising and excellent algorithm based on the results.