Sea-rail intermodal container terminals facilitate shared yards, allowing sea-rail intermodal containers to be stored in blocks at port and railway container terminals, and containers to be transferred between different yard blocks. There are significant differences in the operation of equipment and block utilization between different storage systems. To effectively utilize space resources at sea-rail intermodal container terminals, the joint optimization of block allocation and transfer is determined by considering import and export container flows based on shared yards. An integer nonlinear programming model is developed to minimize the total transshipment costs. Based on the characteristics of the problem, a co-evolutionary genetic algorithm is designed to adaptively balance population diversity and global convergence by incorporating Q-learning principles to obtain solutions. Various numerical experiments are conducted to verify the effectiveness of the model and the algorithm. The results show that the proposed algorithm has better convergence accuracy. Compared with the other three traditional storage forms, the proposed shared and transferred form can effectively balance the transfer cost and handling efficiency, resulting in an average reduction of 15.17%, 11.96%, and 15.09% in the total handling cost. Finally, a sensitivity analysis to multiple unit costs is performed to verify the universality of the algorithm. © 2024 Science Press. All rights reserved.
