Neural-network-based adaptive fault-tolerant vibration control of single-link flexible manipulator

2019 ◽  
Vol 42 (3) ◽  
pp. 430-438 ◽  
Author(s):  
Le Li ◽  
Jinkun Liu
Keyword(s):  
Neural Network ◽  
Dynamic Model ◽  
Fault Tolerant ◽  
Rbf Neural Network ◽  
Direct Method ◽  
Fault Tolerant Control ◽  
Flexible Manipulator ◽  
Actuator Failure ◽  
Single Link ◽  
Boundary Disturbance

This paper proposes an adaptive fault-tolerant control scheme for a single-link flexible manipulator with actuator failure and uncertain boundary disturbance. The dynamic model of the flexible manipulator as-described by partial differential equations (PDEs) is derived under Hamilton’s principle. The dynamic model is then used to design an adaptive fault-tolerant control (FTC) scheme which tracks the given angle and regulates vibration in the case of actuator failure. The boundary disturbance is compensated by a radial basis function (RBF) neural network. The whole closed-loop system is proven asymptotically stable by Lyapunov direct method and LaSalle’s invariance principle. Simulation results indicate that the proposed controller is superior to the traditional PD controller.

scholarly journals Optimization of Urban Rail Automatic Train Operation System Based on RBF Neural Network Adaptive Terminal Sliding Mode Fault Tolerant Control

2021 ◽  
Vol 4 (3) ◽  
pp. 51
Author(s):  
Junxia Yang ◽  
Youpeng Zhang ◽  
Yuxiang Jin
Keyword(s):  
Neural Network ◽  
Control Algorithm ◽  
Fault Tolerant ◽  
Sliding Mode ◽  
Rbf Neural Network ◽  
Fault Tolerant Control ◽  
Control Input ◽  
Terminal Sliding Mode ◽  
Train Operation ◽  
Automatic Train Operation

Aiming at the problem of the large tracking error of the desired curve for the automatic train operation (ATO) control strategy, an ATO control algorithm based on RBF neural network adaptive terminal sliding mode fault-tolerant control (ATSM-FTC-RBFNN) is proposed to realize the accurate tracking control of train operation curve. On the one hand, considering the state delay of trains in operation, a nonlinear dynamic model is established based on the mechanism of motion mechanics. Then, the terminal sliding mode control principle is used to design the ATO control algorithm, and the adaptive mechanism is introduced to enhance the adaptability of the system. On the other hand, RBFNN is used to adaptively approximate and compensate the additional resistance disturbance to the model so that ATO control with larger disturbance can be realized with smaller switching gain, and the tracking performance and anti-interference ability of the system can be enhanced. Finally, considering the actuator failure and the control input limitation, the fault-tolerant mechanism is introduced to further enhance the fault-tolerant performance of the system. The simulation results show that the control can compensate and process the nonlinear effects of control input saturation, delay, and actuator faults synchronously under the condition of uncertain parameters, external disturbances of the system model and can achieve a small error tracking the desired curve.

Adaptive PID actuator fault tolerant control of single-link flexible manipulator

2018 ◽  
Vol 41 (4) ◽  
pp. 1019-1031 ◽  
Author(s):  
Siti Fadilah Abd Latip ◽  
Abdul Rashid Husain ◽  
Zaharuddin Mohamed ◽  
Mohd Ariffanan Mohd Basri
Keyword(s):  
Pid Controller ◽  
Fault Tolerant ◽  
Angular Position ◽  
Fault Tolerant Control ◽  
Flexible Manipulator ◽  
Actuator Fault ◽  
Fault Reconstruction ◽  
Offline Learning ◽  
Single Link ◽  
The Stability

Actuator faults may cause performance degradation of a system and may sometimes even lead to instability. This paper deals with the fault tolerant control problem of a single-link flexible manipulator under a loss of actuator effectiveness. The proposed control scheme uses an adaptive proportional–integral–derivative (APID) controller, which may automatically online tune the three control gains, kp, ki, and kd. The adaptation laws of the APID controller are derived in the sense of the Lyapunov function, so that the stability of the closed-loop system may be guaranteed. The main advantage of the proposed methodology is that no prior offline learning or manual retuning of the PID controller is required to accommodate the actuator fault. In addition, the proposed APID controller does not require any knowledge of the fault magnitude in advance. The effectiveness and feasibility of the proposed approach is tested for the hub angular position and tracking control of a single-link flexible manipulator under both faulty and fault-free conditions. The results demonstrate that the approach is valid, leading to an accurate fault reconstruction, a better transient and good tracking performance, and significantly improved upon previous approaches in terms of errors with respect to the corresponding traditional fixed-gain PID controller.

Adaptive fault-tolerant control for a joint flexible manipulator based on dynamic surface

2019 ◽  
Vol 41 (15) ◽  
pp. 4240-4253 ◽  
Author(s):  
Lijun Wang ◽  
Dan Zhang ◽  
Jinkun Liu ◽  
Haifeng Huang ◽  
Qiuyue Shi ◽  
...  
Keyword(s):  
Lyapunov Method ◽  
Fault Tolerant ◽  
Fault Tolerant Control ◽  
Flexible Manipulator ◽  
Actuator Failure ◽  
Dynamic Surface ◽  
The Stability ◽  
Bounded Disturbance ◽  
Flexible Joint Manipulator ◽  
Surface Technique

In order to solve the problem of actuator failure of flexible joint manipulator, adaptive fault-tolerant control for a flexible manipulator with bounded disturbance is proposed, both actuator partial failure and actuator stuck are considered. The control lows are devised by means of the dynamic surface technique, and the bounded disturbance is compensated via the design of robust items. The stability of the control system is guaranteed via the Lyapunov method. The effectiveness of the theoretical schemes is finally verified by two simulation examples.

A Review on Fault-Tolerant Control for Single-Link Flexible Manipulator System

2012 ◽  
Vol 229-231 ◽  
pp. 2389-2393
Author(s):  
Siti Fadilah Abd Latip ◽  
Abdul Rashid Husain ◽  
Amira Sarayati ◽  
Shahrul Hamzah Abdul Razak
Keyword(s):  
Literature Review ◽  
Historical Development ◽  
Fault Tolerant ◽  
Research Effort ◽  
Fault Tolerant Control ◽  
Flexible Manipulator ◽  
Single Link ◽  
The Subject ◽  
New Research ◽  
Tolerance Control

In this paper, a review of the historical development of fault- tolerant control, some proposals for the terminology in the field of supervision, fault detection and tolerance control are presented. The directions in which the subject is going are summarised and some pointers are given as to the likely issues and where new research effort is required. The paper provides a basic literature review covering most areas of fault-tolerant control of single-link flexible manipulator system.

FAULT TOLERANT CONTROL FOR SENSOR FAULT OF A SINGLE-LINK FLEXIBLE MANIPULATOR SYSTEM

2016 ◽  
Vol 78 (6-13) ◽  
Author(s):  
Siti Fadilah Abd Latip ◽  
Abdul Rashid Husain ◽  
Mohamad Noh Ahmad ◽  
Zaharuddin Mohamed
Keyword(s):  
Fault Tolerant ◽  
Fault Tolerant Control ◽  
Absolute Magnitude ◽  
Fault Detection And Isolation ◽  
Flexible Manipulator ◽  
Sensor Fault ◽  
Luenberger Observer ◽  
Single Link ◽  
Fault Compensation ◽  
Value Decomposition

This paper presents a new approach for sensor fault tolerant control (FTC) of a single-link flexible manipulator system (FMS) by using Finite Element Method (FEM). In this FTC scheme, a new control law is proposed where it is added to the nominal control.  This research focuses on one element without any payload assumption in the modelling.  The FTC method is designed in such way that aims to reduce fault while maintaining nominal FMS controller without any changes in both faulty and fault free cases. This proposed FTC approach is achieved by augmenting Luenberger observer that is capable of estimating faults in fault detection and isolation (FDI) analysis. From the information provided by the FDI, fault magnitude is assessed by using Singular Value Decomposition (SVD) where this information is used in the fault compensation strategy. For the nominal FMS controller, Proportional- integral- derivative (PID) controller is used to control the FMS where it follows the desired hub angle. This work proved that the FTC approach is capable of reducing fault with both incipient and abrupt signals and in two types of faulty conditions where the sensor is having loss of effectiveness and totally malfunction. All the performances are compared with FTC with Unknown Input Observer (FTC-UIO) method via the integral of the absolute magnitude of error (IAE) method.

Iterative Fault Tolerant Control for General Discrete-Time Stochastic Systems Using Output Probability Density Estimation

2013 ◽  
pp. 1-24
Author(s):  
Zakwan Skaf
Keyword(s):  
Neural Network ◽  
Probability Density ◽  
Discrete Time ◽  
Basis Function ◽  
Fault Tolerant ◽  
Rbf Neural Network ◽  
Tracking Error ◽  
Sufficient Conditions ◽  
Fault Tolerant Control ◽  
Fixed Number

A new design of a fault tolerant control (FTC)-based an adaptive, fixed-structure proportional-integral (PI) controller with constraints on the state vector for nonlinear discrete-time system subject to stochastic non-Gaussian disturbance is studied. The objective of the reliable control algorithm scheme is to design a control signal such that the actual probability density function (PDF) of the system is made as close as possible to a desired PDF, and make the tracking performance converge to zero, not only when all components are functional but also in case of admissible faults. A Linear Matrix Inequality (LMI)-based FTC method is presented to ensure that the fault can be estimated and compensated for. A radial basis function (RBF) neural network is used to approximate the output PDF of the system. Thus, the aim of the output PDF control will be a RBF weight control with an adaptive tuning of the basis function parameters. The key issue here is to divide the control horizon into a number of equal time intervals called batches. Within each interval, there are a fixed number of sample points. The design procedure is divided into two main algorithms, within each batch, and between any two adjacent batches. A P-type Iterative Learning Control (ILC) law is employed to tune the parameters of the RBF neural network so that the PDF tracking error decreases along with the batches. Sufficient conditions for the proposed fault tolerance are expressed as LMIs. An analysis of the ILC convergence is carried out. Finally, the effectiveness of the proposed method is demonstrated with an illustrated example.

Sign in / Sign up

Export Citation Format

Share Document