Modeling method and system of underwater robot-manipulator system based on neural network

Abstract

The invention provides a method and system for modeling an underwater robot-manipulator based on an identification neural network. The underwater robot-manipulator is composed of two parts, an underwater robot ship itself and a corresponding mechanical arm. The modeling process includes: firstly establishing a coordinate system , respectively define its generalized coordinate system and generalized control force; then establish the dynamic equation of the underwater robot to approximate the value of the function h(ζ,τ) through a single hidden layer feedforward neural network. In order to facilitate the convergence analysis, only the weight matrix W from the hidden layer to the output layer is I Update, let the weight matrix W i is a constant matrix. Finally, the verification method is also given. Through the modeling method of the underwater robot-manipulator system based on the neural network of the present invention: 1. The designed underwater robot includes a hull and a multi-link manipulator; 2. The designed identification neural network can effectively identify the dynamics of the underwater robot model; 3. The update law of the weight matrix of the identification neural network can ensure the convergence of the position error of the underwater robot.

Description

technical field [0001] The invention relates to the field of underwater robot and identification neural network modeling, in particular to a method for modeling an underwater robot-manipulator system based on an identification neural network. Background technique [0002] In recent years, with the deepening of ocean development, the application of underwater robots has gradually attracted the attention of various industries. Underwater Vehicle-Manipulator System (UVMS) is a kind of automatic equipment that can observe and operate autonomously under water. It has great potential in seabed scientific investigation, resource exploration, pipeline laying, offshore aquaculture, etc. Value. The UVMS system consists of two parts: the underwater robot ship itself and the underwater manipulator. The tasks that need to be performed are completed through the movements of the underwater robot ship itself and the underwater manipulator joints. [0003] The motion control of underwater ...

AI Technical Summary

Problems solved by technology

[0016] 1) The underwater robot can only include the robot body, but cannot complete the grasping action

[0017] 2) This method can only estimate the state information and thruster information of the underwater robot, and cannot provide the dynamic model of the underwater robot

[0023] 2) The underwater robot does not include the manipulator

Images