Generation of Controller of an Underwater Robot for Constant Altitude Cruising by Self-Training

Suto, Taku; Ura, Tamaki

doi:10.2534/jjasnaoe1968.1993.174_917

Search citation statements

Order By: Relevance

Paper Sections

Select...

Robust Controller Design Based On Neural Network1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

Publication Types

Select...

Article1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the nonlinear approximation ability of RBFNN, the following assumptions can be made [29][30][31][32][33]:…”

Section: Robust Controller Design Based On Neural Networkmentioning

confidence: 99%

Adaptive neural network vibration suppression control of flexible joints space manipulator based on H∞ theory

You¹,

Zhang²,

Shen³

et al. 2023

J. vibroeng.

View full text Add to dashboard Cite

Considering the control problems caused by uncertainties such as inaccurate modeling, external disturbance and joint flexibility, a neural network control method based on H∞ is proposed. By establishing the dynamic model of the free-floating space robot with flexible joints, according to its dynamic characteristics, it is split into a slow subsystem model representing the rigid characteristics and a fast subsystem model representing the flexible characteristics. Based on the H∞ robust control theory, a robust controller based on neural network is designed to realize the decoupling control of the rigid dynamic model, The designed weight adaptive learning rate can ensure the online and real-time adjustment of parameters. Based on Lyapunov theory, it is proved that the designed controller can ensure that the L2 gain of the system is less than the given index. A feedback controller based on velocity differential is designed to compensate the angle error caused by joint flexibility. The experimental simulation results verify that the proposed control method is effective and has good engineering application value.

show abstract

“…According to the nonlinear approximation ability of RBFNN, the following assumptions can be made [29][30][31][32][33]:…”

Section: Robust Controller Design Based On Neural Networkmentioning

confidence: 99%

Adaptive neural network vibration suppression control of flexible joints space manipulator based on H∞ theory

You¹,

Zhang²,

Shen³

et al. 2023

J. vibroeng.

View full text Add to dashboard Cite

show abstract

Generation of Controller of an Underwater Robot for Constant Altitude Cruising by Self-Training

Cited by 1 publication

References 2 publications

Adaptive neural network vibration suppression control of flexible joints space manipulator based on H∞ theory

Adaptive neural network vibration suppression control of flexible joints space manipulator based on H∞ theory

Contact Info

Product

Resources

About