A5053456237- Fault Detection and Control Systems
- EEG and Brain-Computer Interfaces
- Model Reduction and Neural Networks
- Gaze Tracking and Assistive Technology
- Adaptive Dynamic Programming Control
- Robot Manipulation and Learning
- Iterative Learning Control Systems
- Stability and Controllability of Differential Equations
- Adaptive Control of Nonlinear Systems
- Neural Networks and Applications
- Anomaly Detection Techniques and Applications
- Blind Source Separation Techniques
- Numerical methods for differential equations
- Linguistics and Cultural Studies
- Fuzzy Logic and Control Systems
- Distributed Control Multi-Agent Systems
- Human-Automation Interaction and Safety
- Reinforcement Learning in Robotics
- Non-Invasive Vital Sign Monitoring
- Human Pose and Action Recognition
- Soft Robotics and Applications
- Advanced Control Systems Optimization
- Context-Aware Activity Recognition Systems
- Advanced Chemical Sensor Technologies
- Functional Brain Connectivity Studies
University of Electronic Science and Technology of China
2023-2025
University of Rhode Island
2019-2023
This article investigates the problem of small fault detection (sFD) for discrete-time nonlinear systems with uncertain dynamics. The faults are considered to be "small" in sense that system trajectories faulty mode always remain close those normal mode, and magnitude can smaller than system's A novel adaptive dynamics learning-based sFD framework is proposed. Specifically, an learning approach using radial basis function neural networks (RBF NNs) first developed achieve locally accurate...
This letter presents a radial basis function neural network (RBF NN) based methodology to investigate the dynamics modeling and fault detection (FD) problems for soft robots. Finite element method (FEM) is first used derive mathematical model describe of trunk robot. An adaptive approach then designed on this FEM by incorporating model-reduction RBF NN techniques. capable achieving accurate identification robot's highly-nonlinear dynamics, with identified knowledge being obtained stored in...
This letter investigates the fault detection (FD) problem of a class uncertain distributed parameter systems modeled by nonlinear parabolic partial differential equations (PDEs). A novel FD scheme is proposed with neural network-based adaptive dynamics learning approach. Specifically, based on Galerkin method, finite dimensional ordinary equation (ODE) system first derived to capture dominant PDE system. An approach using radial basis function networks (RBF NN) then developed achieve locally...
This brief addresses the optimal consensus control problem of a class nonlinear leader-follower multi-agent systems (MASs), where dynamics and states leader are unknown. A distributed Kreisselmeiers Regressor Extension Mixing (KREM)-based scheme is developed. Specifically, parameter estimation-based observer first proposed, which can estimate not only dynamic parameters but also for each agent. allows to transform into an tracking leader's state. To solve optimization problem, only-critic...
Brain-computer interfaces (BCIs) have gained significant attention in rehabilitation research as a critical step investigating neural remodeling techniques. However, most existing methods usually overlook the randomness and diversity of motion artifacts, thereby lacking desired generalization ability denoising precision, which limits their practical application. To address these limitations, we propose Dynamic Evaluation Denoising Network (DED-Net) that incorporates an evaluation model with...
This paper investigates the tracking control problem of an unstable wave equation with boundary uncertainties. The under consideration has a negative damper (unstable) at uncontrolled and uncertain nonlinear dynamics controlled boundary. A novel scheme is proposed by incorporating backstepping method adaptive neural networks (NN). Specifically, radial basis function (RBF) NN model first developed to approximate/counteract system boundary-feedback observer then designed such estimate overall...