The continuity and reliability of a ship’s power supply system directly affect the safety and economic efficiency of its operations. Timely reconfiguration of the power supply network in the event of a failure can minimize losses and enhance the ship’s survivability. To address the problem of power supply network fault reconfiguration in ships, an adaptive hybrid genetic particle swarm optimization (AHGPSO) algorithm is proposed. The algorithm incorporates the Circle chaotic map to introduce chaos into the initial population and includes crossover and mutation strategies from the genetic algorithm. These improve the global convergence accuracy and effectively mitigates the inherent defect of the basic PSO algorithm’s tendency to fall into local optima. The algorithm nonlinearly adjusts the inertia weight and two acceleration factors as the iterations progress, using larger values in the early stages and smaller values in the later stages, thereby increasing the convergence speed. Simulation examples and comparisons with the unimproved PSO algorithm verify the effectiveness and superiority of the proposed algorithm in addressing the ship power supply network fault reconfiguration problem, from multiple performances including speed, accuracy, and stability.