Underwater Manipulator Backlash Lag Compensation Algorithm Based on RBF Neural Network

Underwater manipulator has had a significant impact in the fields of marine resource exploration, deep-sea environmental monitoring, and marine scientific research. The research on underwater manipulator has gradually deepened, and the accuracy requirements are getting higher and higher. Aiming at the backlash lag caused by the gap between the gears in the production process of the manipulator, a control algorithm to compensate the backlash lag of the underwater manipulator is proposed. Using RBF neural network to approximate the uncertainty term caused by the backlash lag of the manipulator. Using Lyapunov bounded stability theory, it is proved that the system is feasible and stable. The adaptive control is used to compensate for the influence of external interference and model uncertainty, so as to enhance the adaptability and control accuracy of the underwater manipulator in a complex underwater environment. The simulation experiment of the controller designed in this paper is carried out to simulate the actual environment of the underwater manipulator working under water, and good results are obtained.