Digital twin-enabled collision early warning system for marine piling: Application to a wharf project in China

The safety and effectiveness of marine piling construction are hindered by the display of imprecise spatial in-formation and the potential for collisions due to the complexity of pile positions and attitudes. Digital twin (DT) can solve the above problems in piling construction because of their inherent three-dimensionality and real-time feedback. The present study proposes a system that utilizes the DT framework to construct a collision early warning system intended for marine piling. A five-dimensional model is used to introduce the overall architecture. The main twin objects are piles. To maximize the effectiveness of DT, the five-dimensional model is composed of four independently maintainable development modules. Consequently, a prototype of the system is created. The core of the system comprises an algorithm for pile positioning and an algorithm for collision early warning, especially for complex pile groups. Two distinct implementations are identified: one involves con-trolling the virtual with the real, while the other involves controlling the real with the virtual. Field experiments are conducted with the aim of establishing a benchmark for collision early warning during the construction process. The prototype of the system is capable of producing a simulated environment through a dual-layer mapping approach, which involves pile-boat mapping and early-warning feedback mapping. The presented system in a practical wharf project showcases both the capacity for three-dimensional visualization of collision warning and the ability to provide feedback for boat control. The research enables more intuitive and effective pile positioning.

Automated summary

This study proposes a method using digital twin technology to construct a collision early warning system for marine piling. The system utilizes a five-dimensional model and four independently maintainable development modules to maximize its effectiveness. The pile positioning algorithm and collision early warning algorithm are capable of providing warnings for complex pile groups.