Addressing the challenge of obtaining global optimal solutions for steel gate optimization problems, this study introduces an active target particle swarm optimization (APSO) algorithm for the optimization design of emersed plane steel gates. APSO incorporates an active target individual into the conventional particle swarm optimization (PSO) population and integrates it into the algorithm’s iterative update mechanism. This enhancement bolsters the algorithm’s capability to escape local optima and enhances its global optimization performance. Furthermore, the APSO algorithm employs a comprehensive learning factor in place of multiple individual learning factors used in traditional PSO, thereby improving the convergence rate and stability. Under constraints imposed by steel structure strength requirements, the APSO algorithm optimizes key structural parameters, including those of the main beam, side columns, panel, and secondary beams, with the objective of minimizing the total weight of the gate. After optimization, finite element analysis (FEA) is conducted using ABAQUS to verify the strength integrity of the main beam based on the optimized design parameters. Findings indicate that the APSO algorithm effectively optimizes the design of emersed plane steel gates, yielding improved structural dimensions. Specifically, the optimized gate design achieves a 15.38% reduction in total weight compared to previous literature examples, while stringent strength checks confirm compliance with allowable stress limits.