Data-driven ship inspection planning based on evolutionary game

Port state control (PSC) inspection is the safety net to catch substandard ships and safeguard maritime safety. Identifying and selecting high-risk foreign ships is crucial for PSC authorities to alleviate inspection pressure. In this context, this paper proposes a data-driven evolutionary game-based ship inspection priority planning (EG-SIPP) approach to identify highrisk foreign ships and allocate inspection resources. Firstly, evolutionary game (EG) is used to assign stable and fair inspection priority coefficient to each visiting foreign ship. Then, under the EG framework, obtaining the final allocated inspection priority coefficients is the solution to the replicator dynamics, which is solved by equilibrium optimizer (EO) algorithm. By leveraging inspection records from the ports under the Tokyo MoU, the proposed EG-SIPP is validated and compared with other ship selection schemes. Numerical analysis demonstrates that, subject to certain inspection resources, our method can detect over 45% more deficiencies on average compared with the currently used ship risk profile (SRP) selection scheme.