Engineering

Statistics

Tower crane

Stability (learning theory)

Computer science

Randomness

Simulation

Mathematics

Tower

Structural engineering

Machine learning

Automation in Construction

Unsafe hoisting behaviors are the fuse of tower crane overturning safety accident. However, the hoisting operation has a certain degree of randomness and invisibility, and it is extremely dangerous to carry out the experiment on the construction site, which makes the research on the relevant regularity very scarce. To simulate different hoisting behaviors as realistically as possible and analyze their dynamic effects on the tower crane, a digital twin (DT) framework of human–machine interaction construction activities is constructed based on the scale model in this study. Through experimental study, the stability change law of the tower crane with the incremental dynamic load is obtained based on the collapse probability level function. Experiment results show that tilt hoisting is the most dangerous behavior causing the tower crane instability. Tower crane foundation and masts are the most vulnerable components to be disturbed by unsafe hoisting behaviors, which can be used as key areas for sensor deployment. This paper can support the detection of the dangerous parts of the tower crane structure, and the monitoring system design for unsafe hoisting behaviors will be carried out in the future.

Digital twin: Stability analysis for tower crane hoisting safety with a scale model