This invention discloses a fault-tolerant control method, program, device, and storage medium for
underwater robots based on
physical information residual networks and
dynamic control allocation, belonging to the technical field of
underwater robot control methods. First, a generalized dynamic model is constructed, incorporating a
diagonal matrix of thruster health and an external lumped disturbance term. Then, a fully connected neural network is used to estimate the total
system disturbance. Next, a composite control law is designed based on a non-singular terminal sliding surface, and the virtual total
control force required to
resist faults is calculated. Finally, the control allocation is transformed into a constrained quadratic
programming optimization problem. A thruster health-aware weighting mechanism and relaxation variables are introduced into the optimization objective function, and the thrust of each thruster is redistributed through an optimization
algorithm. When a fault occurs in the
underwater robot's propulsion
system, a graded degradation strategy is determined based on the relaxation variables in the optimization objective function. This ensures the
robot's normal navigation even when some thrusters are damaged.