基于 RBF 神经网络的自主水下航行器模型预测路径跟踪控制

Linyu Guo; Jian Gao; Huifeng Jiao; Yunxuan Song; Yimin Chen; Guang Pan

doi:10.1051/jnwpu/20234150871

基于 RBF 神经网络的自主水下航行器模型预测路径跟踪控制

Translated title of the contribution: Model predictive path following control of underwater vehicle based on RBF neural network

Linyu Guo, Jian Gao, Huifeng Jiao, Yunxuan Song, Yimin Chen, Guang Pan

School of Marine Science and Technology

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

A model prediction controller (MPC) based on radial basis function (RBF) neural network is designed to counter the model uncertainty and multiple constraints of the autonomous underwater vehicle (AUV). On this basis of path following control with MPC, the RBF neural network is trained online with real-time measurement data to compensate for the AUV′s model uncertainty, thus suppressing the interference of model uncertainty on the MPC and reducing its overshoot and tracking error. Simulation results show that the path following algorithm based on RBF-MPC has better transient and steady-state performance compared with the classical MPC algorithm.

Translated title of the contribution	Model predictive path following control of underwater vehicle based on RBF neural network
Original language	Chinese (Traditional)
Pages (from-to)	871-877
Number of pages	7
Journal	Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University
Volume	41
Issue number	5
DOIs	https://doi.org/10.1051/jnwpu/20234150871
State	Published - Oct 2023

Access to Document

10.1051/jnwpu/20234150871

Cite this

@article{8848fbd4f4e741b6bf5437aeac817b8b,

title = "基于 RBF 神经网络的自主水下航行器模型预测路径跟踪控制",

abstract = "A model prediction controller (MPC) based on radial basis function (RBF) neural network is designed to counter the model uncertainty and multiple constraints of the autonomous underwater vehicle (AUV). On this basis of path following control with MPC, the RBF neural network is trained online with real-time measurement data to compensate for the AUV′s model uncertainty, thus suppressing the interference of model uncertainty on the MPC and reducing its overshoot and tracking error. Simulation results show that the path following algorithm based on RBF-MPC has better transient and steady-state performance compared with the classical MPC algorithm.",

keywords = "autonomous underwater vehicle, model predictive control, path following, radial basis function neural network",

author = "Linyu Guo and Jian Gao and Huifeng Jiao and Yunxuan Song and Yimin Chen and Guang Pan",

note = "Publisher Copyright: {\textcopyright}2023 Journal of Northwestern Polytechnical University.",

year = "2023",

month = oct,

doi = "10.1051/jnwpu/20234150871",

language = "繁体中文",

volume = "41",

pages = "871--877",

journal = "Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University",

issn = "1000-2758",

publisher = "Northwestern Polytechnical University",

number = "5",

}

TY - JOUR

T1 - 基于 RBF 神经网络的自主水下航行器模型预测路径跟踪控制

AU - Guo, Linyu

AU - Gao, Jian

AU - Jiao, Huifeng

AU - Song, Yunxuan

AU - Chen, Yimin

AU - Pan, Guang

PY - 2023/10

Y1 - 2023/10

N2 - A model prediction controller (MPC) based on radial basis function (RBF) neural network is designed to counter the model uncertainty and multiple constraints of the autonomous underwater vehicle (AUV). On this basis of path following control with MPC, the RBF neural network is trained online with real-time measurement data to compensate for the AUV′s model uncertainty, thus suppressing the interference of model uncertainty on the MPC and reducing its overshoot and tracking error. Simulation results show that the path following algorithm based on RBF-MPC has better transient and steady-state performance compared with the classical MPC algorithm.

AB - A model prediction controller (MPC) based on radial basis function (RBF) neural network is designed to counter the model uncertainty and multiple constraints of the autonomous underwater vehicle (AUV). On this basis of path following control with MPC, the RBF neural network is trained online with real-time measurement data to compensate for the AUV′s model uncertainty, thus suppressing the interference of model uncertainty on the MPC and reducing its overshoot and tracking error. Simulation results show that the path following algorithm based on RBF-MPC has better transient and steady-state performance compared with the classical MPC algorithm.

KW - autonomous underwater vehicle

KW - model predictive control

KW - path following

KW - radial basis function neural network

UR - http://www.scopus.com/inward/record.url?scp=85177594483&partnerID=8YFLogxK

U2 - 10.1051/jnwpu/20234150871

DO - 10.1051/jnwpu/20234150871

M3 - 文章

AN - SCOPUS:85177594483

SN - 1000-2758

VL - 41

SP - 871

EP - 877

JO - Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University

JF - Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University

IS - 5

ER -

基于 RBF 神经网络的自主水下航行器模型预测路径跟踪控制

Abstract

Access to Document

Other files and links

Fingerprint

Cite this