Digital twin model updating method for drilling rig hoisting system in offshore platform

The increasing demands for deep and ultra-deep drilling expose drilling rig hoisting systems in offshore platforms to heightened efficiency and safety challenges under complex conditions, necessitating more effective lifecycle management. While digital twins serve as a key tool for managing the lifecycle of such complex equipment and supporting hoisting operations in offshore environments, existing models fail to precisely represent dynamic behaviors and parameter evolutions under these conditions. A system state-based digital twin modeling and updating method for the drilling rig hoisting system in offshore platforms is proposed. First, a multi-domain unified modeling language constructs a mechanical-electrical-control coupled digital twin model, ensuring consistent representation between virtual and physical counterparts. Secondly, a state identification method combining second-order Markov chains and finite state machines delineates operational states and transition relationships, accurately capturing multi-condition behaviors. Finally, a parameter updating strategy based on state-sensitivity rules, incorporating extended Kalman filtering and particle swarm optimization, improves parameter accuracy and model consistency. Experimental results demonstrate that the method enables precise modeling and parameter updating across operational states, with state identification errors below 5% and parameter errors reduced by over 30% post-update, providing reliable digital support for the drilling rig's full-lifecycle management in offshore platforms.