Unmanned-ship speed and uncertainty estimation system and design method

Abstract

The invention relates to an unmanned-ship speed and uncertainty estimation system and a design method. According to the system, an echo state network can be applied to speed estimation of an unmannedship, the echo state network is utilized to approximate model uncertainty and environment disturbance to enable the system to obtain target speed observation values, and also approximate unknown dynamics generated by the uncertainty of model parameters, non-modeling of fluid dynamics, external interference caused by wind waves and ocean currents and the like, and the state observation problem containing the model uncertainty and the unknown environment disturbance is effectively solved. Introduction of the echo state network overcomes the problems of slow convergence, proneness of falling intolocal minimums, complicated training processes and the like brought by traditional neural networks based on a learning algorithm of gradient descending. According to the system, the neural network with a low-frequency learning link is adopted to approximate system uncertainty, high-frequency oscillation which may be caused by a high-gain learning rate is effectively filtered out, and steady stateobservation on a system with unknown dynamics is realized.

Description

technical field [0001] The invention relates to a speed and uncertainty estimation system and a design method applicable to the field of unmanned ships, in particular to a state observer system and a design method of an unmanned ship. Background technique [0002] As an important tool for human protection and development of the ocean, surface unmanned ships have the advantages of being unmanned, miniaturized, and intelligent, and play an important role in the fields of marine hydrological monitoring, pollution tracking, seabed resource exploration, regional search and rescue, etc. , so it is of great significance to study the motion control of unmanned ships. In various motion control schemes of unmanned ships, the position information and velocity information as state variables need to be known. In the actual motion control process, the position information of the unmanned ship can be directly obtained by the global navigation satellite system, but the speed information ca...

AI Technical Summary

Problems solved by technology

[0005] However, from two aspects of unmanned ship speed and uncertainty estimation, the existing technology has the following deficiencies: First, the speed information in the existing unmanned ship control technology is mostly obtained through direct differentiation of position and attitude information, and there are certain errors. Especially not conducive to precise control of small unmanned ships

Second, in some unmanned ship control algorithms, interference factors such as wind, wave and current need to be known, which increases the difficulty of actual engineering implementation and control errors

Images