grasshopper optimization algorithm

Opposition-based learning (OBL) is an effective approach to improve the performance of meta-heuristic optimization algorithms that are commonly used to solve complex engineering problems. In this paper, an opposite learning strategy is presented to combine with the Grasshopper Optimization Algorithm (GOA). In this proposed algorithm (OGOA), the solutions generated by the GOA algorithm are sorted and divided into good and bad solutions, then the bad solutions are selected to generate new solutions using opposition-based learning. To verify the performance of the proposed algorithm, some benchmark mathematical functions were tested. In addition, the performance of the OGOA algorithm was evaluated by implementing an optimal design of a real-scale reinforced concrete bridge. To identify the effective parameters in the design of structural components of reinforced concrete bridges, sensitivity analysis has been performed. In addition, the total cost of materials in the foundation columns and bridge deck was defined as an objective function. Also, the dimensions of sections and longitudinal steel bars are selected as design variables. The simulation results show the stability and robustness of the proposed OGOA method compared to the standard GOA. Also, the proposed OGOA is an efficient method for the optimal design of columns and decks of reinforced concrete bridges.