RBF-PID Depth Control of Deep-sea Profiling Floats

In this study, we propose an adaptive proportional-integral-derivative (PID) depth control algorithm based on the radial basis function (RBF) neural network to solve the depth control of deep-sea self-supporting profiling floats. Firstly, we establish a kinematic model of the profiling float and verify the accuracy of the model based on the nonlinear characteristics of the relevant parameters. Secondly, we design a profiling float depth controller based on the RBF-PID algorithm considering the characteristics of the one-way controllability of the buoyancy drive system. A comparison of the simulation results with the incremental PID control results denotes that the RBF-PID control algorithm can improve the depth control accuracy and enhance the anti-interference ability of the floats.