A Novel Evolutionary Algorithm Inspired by Beans Dispersal

Abstract Inspired by the transmission of beans in nature, a novel evolutionary algorithm-Bean Optimization Algorithm (BOA) is proposed in this paper. BOA is mainly based on the normal distribution which is an important continuous probability distribution of quantitative phenomena. Through simulating the self-adaptive phenomena of plant, BOA is designed for solving continuous optimization problems. We also analyze the global convergence of BOA by using the Solis and Wets’ research results. The conclusion is that BOA can converge to the global optimization solution with probability one. In order to validate its effectiveness, BOA is tested against benchmark functions. And its performance is also compared with that of particle swarm optimization (PSO) algorithm. The experimental results show that BOA has competitive performance to PSO in terms of accuracy and convergence speed on the explored tests and stands out as a promising alternative to existing optimization methods for engineering designs or applications.