Evolutionary game-based ship inspection planning considering ship competitive interactions

Abstract

Port state control (PSC) inspection is the safety net to catch substandard ships and safeguard maritime transport. Effectively identifying high-risk foreign ships is crucial for port authorities to maximize inspection efficiency due to the scarce inspection resources. This paper proposes a data-driven evolutionary game theory-based ship inspection priority planning (EGT-SIPP) optimization approach to identify high-risk ships among the large group of visiting foreign ships while taking the ship competitive interaction into consideration. First, a data-driven evolutionary game theory (EGT) framework is adopted to assign stable and fair inspection priority coefficient to each visiting foreign ship to a port. This framework is built on real ship inspection records, ensuring that the inspection priority planning reflects both strategic interactions and real-world conditions. Then, the equilibrium optimizer (EO) algorithm is employed to solve the single-objective optimization problem, which minimizes the changes in the allocated priority coefficients based on replicator dynamics (RD) under the EGT framework. By leveraging inspection records from the Tokyo memorandum of understanding (MoU), the proposed EGT-SIPP is validated and compared with other ship selection schemes. Simulation results demonstrate that, subject to limited inspection resources at different levels, our EO-solved EGT-SIPP model can detect over 16.04%, 47.20%, and 125.27% more deficiencies on average than the particle swarm optimization (PSO)-solved EGT-SIPP model, the genetic algorithm (GA)-solved EGT-SIPP model, and the currently used ship risk profile (SRP) selection scheme, respectively.