Adaptive stabilization of strict-feedback nonlinear systems using the fully actuated system approach and neural network approximation

This paper studies the adaptive stabilization of a class of strict-feedback systems (SFSs) with unknown nonlinearities and bounded matched disturbances. Using the fully actuated system (FAS) approach, the strict-feedback system is transformed into a high-order form with a single lumped unknown nonlinear term and a bounded disturbance, which leads to a more compact controller design. An Radial basis function (RBF) neural network (NN) is used to approximate the lumped unknown nonlinearity online, while a smooth robust term is introduced to compensate for the approximation error and the external disturbance. An adaptive controller is then developed based on this formulation. Lyapunov analysis shows that the transformed state and the neural network weight-estimation error are uniformly ultimately bounded. The original system states ultimately enter and remain within a neighborhood of the origin, while the neural network weight estimate and the control input remain bounded. The proposed method is further compared with an adaptive RBF neural network backstepping controller in a numerical example and an resistor-inductor-capacitor (RLC) circuit. In both cases, the proposed method achieves lower root-mean-square error, steady-state root-mean-square error, and control effort.

Authors

Institutions

Publication Details

Journal
Measurement and Control
Published
2026-11-21
DOI
https://doi.org/10.1177/00202940261511863
Primary Topic
Adaptive Control of Nonlinear Systems
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Adaptive stabilization of strict-feedback nonlinear systems using the fully actuated system approach and neural network approximation

Da‐Ke Gu, Yindong Liu, Yuxin Deng
Measurement and Control
Adaptive Control of Nonlinear Systems
article

Adaptive stabilization of strict-feedback nonlinear systems using the fully actuated system approach and neural network approximation

Da‐Ke Gu, Yindong Liu, Yuxin Deng
article en

Abstract

This paper studies the adaptive stabilization of a class of strict-feedback systems (SFSs) with unknown nonlinearities and bounded matched disturbances. Using the fully actuated system (FAS) approach, the strict-feedback system is transformed into a high-order form with a single lumped unknown nonlinear term and a bounded disturbance, which leads to a more compact controller design. An Radial basis function (RBF) neural network (NN) is used to approximate the lumped unknown nonlinearity online, while a smooth robust term is introduced to compensate for the approximation error and the external disturbance. An adaptive controller is then developed based on this formulation. Lyapunov analysis shows that the transformed state and the neural network weight-estimation error are uniformly ultimately bounded. The original system states ultimately enter and remain within a neighborhood of the origin, while the neural network weight estimate and the control input remain bounded. The proposed method is further compared with an adaptive RBF neural network backstepping controller in a numerical example and an resistor-inductor-capacitor (RLC) circuit. In both cases, the proposed method achieves lower root-mean-square error, steady-state root-mean-square error, and control effort.

Measurement and Control
Northeast Electric Power University (CN)
Adaptive Control of Nonlinear Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon