Underwater robot self-adaptive regional dynamic positioning control method based on RBF neural network

Abstract

The invention relates to an underwater robot self-adaptive regional dynamic positioning control method based on a RBF neural network. The underwater robot self-adaptive regional dynamic positioning control method belongs to the field of underwater robot dynamic positioning control. The underwater robot self-adaptive regional dynamic positioning control method comprises the steps of: establishing asix-degree-of-freedom spatial motion model of an AUV, and constructing a target region and an region control system error dynamic equation; adopting the RBF neural network to carry out online approximation on an unknown vector, and adopting a sliding mode control item to compensate for an approximation error; performing online adjustment on network weight, a radial basis function center and variance; adopting a sliding mode switching gain online adjustment mode based on an exponential to avoid high-frequency buffeting of a control system caused by overlarge sliding mode switching gain; and performing dynamic positioning control on the AUV by means of a neural sliding mode region controller, so that the position and attitude vectors eta are converged into the target region. The underwaterrobot self-adaptive regional dynamic positioning control method solves the AUV dynamic positioning control problem under the influence of factors such as external interference and measurement precision of an underwater sensor, improves the dynamic positioning precision, and can still be quickly converged into the target region when the properties of the AUV change.

Description

technical field [0001] The invention relates to an adaptive area dynamic positioning control method of an underwater robot based on a RBF neural network, belonging to the field of dynamic positioning control of the underwater robot. Background technique [0002] With the dwindling land resources, the pace of human development of the ocean is getting faster and faster. Autonomous underwater vehicle (AUV: Autonomous Underwater Vehicle) is currently the only carrier that can detect and develop in the deep sea without human beings, and has been highly valued by researchers at home and abroad. Since the AUV works in a complex marine environment, its dynamic positioning control needs to consider the influence of system nonlinearity and external environmental uncertainties such as wind, waves, and currents; It is also difficult to obtain higher position, attitude detection and control accuracy. The above two points will seriously affect the AUV underwater dynamic positioning cont...

AI Technical Summary

Problems solved by technology

In the above-mentioned typical area control methods, the control target is mostly defined as the boundary of the target area in the actual operation process, which will cause the position and attitude of the AUV to converge to the boundary of the target area, and the thruster motor will frequently switch forward and reverse. , which will increase system energy consumption and reduce thruster performance and life

Images