Abstract: The arithmetic optimization algorithm(AOA) has slow convergence speed and low convergence accuracy,and is easy to fall into local extremum.In order to solve these problems,an adaptive grouping fusion improved arithmetic optimization algorithm(AG-AOA) is proposed.Firstly,Halton sequence is used to initialize individual positions to improve the diversity of algorithm at the initial iteration stage.Then,an adaptive grouping strategy is introduced to group the population,and the adaptive individuals are divided into dominant group,equilibrium group and inferior group according to the fitness value.Finally,the teaching and learning optimization strategy,elite reverse learning strategy and oscillating disturbance operator are used to update the position of each group of individuals to improve the searching ability of AOA and reduce the influence of local extreme points on the algorithm.The performance of AG-AOA is validated using test suites containing problems of wide varieties of complexities.Various analyses are conducted,including benchmark function,Wilcoxon ranksum test for statistical significance and part of CEC2014 test function.Finally,AG-AOA is applied to two practical engineering optimization problems,the obtained results are then analysed and compared and with other metaheuristics algorithms to show the superiority of the proposed AG-AOA.

Key words: Arithmetic optimization algorithm, Halton sequence, Adaptive grouping, Teaching and learning optimization, Elite reverse learning, Oscillating disturbance operator