IAROA: An Enhanced Attraction-Repulsion Optimisation Algorithm Fusing Multiple Strategies for Mechanical Optimisation Design.

Abstract

Attraction-Repulsion Optimisation Algorithm (AROA) is a newly proposed metaheuristic algorithm for solving global optimisation problems, which simulates the equilibrium relating to the attraction and repulsion phenomenon that occurs in the natural world, and aims to achieve a good balance between the development exploration phases. Although AROA has a more significant performance compared to other classical algorithms on complex realistic constrained issues, it still has drawbacks in terms of diversity of solutions, convergence precision, and susceptibility to local stagnation. To further improve the global optimisation search and application ability of the AROA algorithm, this work puts forward an Improved Attraction-Repulsion Optimisation Algorithm based on multiple strategies, denoted as IAROA. Firstly, the elite dynamic opposite (EDO) learning strategy is used in the initialisation phase to enrich the information of the initial solution and obtain high-quality candidate solutions. Secondly, the dimension learning-based hunting (DLH) exploration tactics is imported to increase the candidate solution diversity and enhance the trade-off between local and global exploration. Next, the pheromone adjustment strategy (PAS) is used for some of the solutions according to the threshold value, which extends the search range of the algorithm and also accelerates the convergence process of the algorithm. Finally, the introduction of the Cauchy distribution inverse cumulative perturbation strategy (CDICP) improves the local search ability of the algorithm, avoids falling into the local optimum, and improves the convergence and accuracy of the algorithm. To validate the performance of IAROA, algorithms are solved by optimisation with the original AROA and 13 classical highly cited algorithms on the CEC2017 test functions, among six engineering design problems of varying complexity. The experimental results indicate that the proposed IAROA algorithm is superior in terms of optimisation precision, solution stability, convergence, and applicability and effectiveness on different problems, and is highly competitive in solving complex engineering design problems with constraints.