Skip to content
Open access

Adaptive Neural Network-Based Event-Triggered Consensus Tracking for Multiple Euler–Lagrange Systems With Actuator Failures

2026 · IEEE Transactions on Automation Science and Engineering · Vol 23, pp. 18449-18460 · 0 citations · 45 references

TL;DR

This paper develops a novel event-triggered adaptive NN FTC strategy within a cohesive framework, where a nonlinear disturbance observer is inherently integrated into the event-based adaptive control architecture, providing practitioners with intuitive parameter tuning predicated on analytically derived boundedness conditions.

Abstract

This article investigates the event-triggered adaptive fault-tolerant control (FTC) problem for multiple Euler–Lagrange systems (MELSs) suffered from parameter uncertainties, actuator failures, unknown perturbations, and limited network bandwidth. The parameter uncertainties are modeled by unknown nonlinear dynamics, which are approximated by an estimation approach based on neural networks (NNs). Thereupon a nonlinear disturbance observer is devised to cope with the whole perturbations composed of unknown external disturbances, approximation errors, and actuator bias faults. Then, we establish an event triggering mechanism on control signals to dispatch triggering moments, guaranteeing that control commands are only activated when certain specially appointed events occur. After that, an event-triggered FTC algorithm based on adaptive NNs is put forward, which makes all closed-loop signals bounded and eventually allows all followers’ states to track the leader’s state. Finally, the effectiveness of the proposed event-triggered adaptive NN FTC policy is verified through an example on multiple manipulators and a comparative experiment. Note to Practitioners—For MELSs such as multi-manipulator platforms and autonomous formations, guaranteeing reliable cooperative tracking while solving actuator failures and resource constraints is essential to system safety and operational efficiency. Existing adaptive FTC methods can handle actuator failures, but they are often affected by continuous signal transmission and cannot simultaneously compensate for lumped disturbances and actuator failures under limited network bandwidth. To address these challenges, this paper develops a novel event-triggered adaptive NN FTC strategy within a cohesive framework, where a nonlinear disturbance observer is inherently integrated into the event-based adaptive control architecture. This control framework provides practitioners with intuitive parameter tuning predicated on analytically derived boundedness conditions, facilitating straightforward practical implementation. Furthermore, it can be extended to other industrial nonlinear systems, such as autonomous aerial vehicles and autonomous ground vehicles, offering reliable dynamic performance across diverse practical application scenarios.

Read PDF

Similar papers

Open access Nov 2026

Dynamic Event‐Triggered Optimal Control for Unknown Nonlinear Systems Under Control Input Saturation

An optimal constrained event‐triggered control (OCETC) scheme is developed, which samples the state and updates the control input when the triggering condition is violated, and a dynamic triggering rule with an additional term is defined by introducing a dynamical variable, significantly reducing computational burden.

Shen-Ao Lu, Meng Wang, Huai-Cheng Yan et al. · 0 citations
Open access Nov 2026

Event-Based Robust Reinforcement Learning Course Tracking for MSVs with Actuator Faults

This paper investigates the robust course control for marine surface vehicles (MSVs) by using reinforcement learning and a dynamic event-triggered mechanism under rudder faults. A fault-tolerant optimized tracking control scheme is designed based on reinforcement learning. Firstly, a general actuator fault model is est...

Xiao-Yang Gao, Li-Rong Kou, Da-Kuan Song et al. · 0 citations
Open access Oct 2026

Reinforcement Learning-Based Switching Event-Triggered Control for MWMR Under Asymmetric Actuator Saturation

This paper investigates the optimal tracking control problem for a Mecanum-wheeled mobile robot subject to asymmetric actuator saturation. Within the command-filtered backstepping framework, a switching event-triggered control strategy based on reinforcement learning is proposed. First, a compensation system incorporat...

Jie Bai, Yong-Hua Peng, Yun-Fa Wu · 0 citations
Open access 2026

Adaptive Event-Triggered Consensus Tracking Control for Multiple Output-Constrained Euler–Lagrange Systems With Coarse Information

This paper is devoted to the event-triggered consensus tracking control for multiple Euler-lagrange (EL) systems with output constraint. Remarkably, both output constraint and event-triggered sampling of control input are considered in the paper but one of them is neglected in most related works. Moreover, coarse infor...

Jian Li, Xiao-Neng Wang · 0 citations
Open access 2026

Adaptive Bipartite Consensus for Nonlinear High-Order MASs With Actuator Faults via Asynchronous Event Triggering

This paper addresses leader-following bipartite consensus for high-order nonlinear multi-agent systems (MASs) with unknown nonlinearities, actuator faults, disturbances, and intermittent communication. A gauge transformation is introduced to convert the problem over a structurally balanced signed graph into a leader-fo...

Deng-Hao Pang, Bo Li, Ju H. Park et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.