An improved adaptive human learning algorithm for engineering optimization

Human learning Optimization (HLO) is an emergent promising meta-heuristic algorithm which uses the random learning operator, the individual learning operator, and the social learning operator to search out the optimal solution of problems based on a simplified human learning model. To enhance the search performance, a new improved adaptive human learning optimization algorithm (IAHLO) is proposed in this paper, in which a novel adaptive strategy is developed to dynamically tune the control parameter of the random learning operator so that IAHLO can efficiently fasten the convergence at the beginning of iteration, develop the diversity at the middle of searching process to better explore the solution space, and perform the accurate local search at the end of search to find the optima. The presented IAHLO is applied to solve well-known engineering optimization problems and its results are compared with those of the standard HLO, adaptive HLO variants, and other metaheuristics to evaluate its performance. The comparison results show that IAHLO outperforms the other algorithms and achieves the best results on the engineering problems as the improved adaptive mechanism possesses the advantages of the linearly increasing and decreasing strategies and avoids their disadvantages.