A modified equilibrium optimizer using opposition-based learning and novel update rules

Equilibrium Optimizer (EO) is a newly developed physics-based metaheuristic algorithm that is based on control volume mass balance models, and has shown competitive performance with other state-of-the-art algorithms. However, the original EO has the disadvantages of a low exploitation ability, ease of falling into local optima, and an immature balance between exploration and exploitation. To address these shortcomings, this paper proposes a modified EO (m-EO) using opposition-based learning (OBL) and novel update rules that incorporates four main modifications: the definition of the concentrations of some particles based on OBL, a new nonlinear time control strategy, novel population update rules and a chaos-based strategy. Based on these modifications, the optimization precision and convergence speed of the original EO are greatly improved. The validity of m-EO is tested on 35 classical benchmark functions, 25 of which have variants belonging to multiple difficulty categories (Dim = 30, 100, 300, 500 and 1000). In addition, m-EO is used to solve three real-world engineering design problems. The experimental results and two different statistical tests demonstrate that the proposed m-EO shows higher performance than original EO and other state-of-the-art algorithms.