A neural network approach to simultaneous state and actuator fault estimation under unknown input decoupling

Witczak, Piotr; Patan, Krzysztof; Witczak, Marcin; Mrugalski, Marcin

doi:10.1016/j.neucom.2016.10.076

Cited by 30 publications

(8 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The objective of further discussion is to design the observer (11) and (12) in such a way that the state estimation dynamic error () k e is asymptotically convergent and the following upper bound is guaranteed: (25) where 0   is a prescribed disturbance attenuation level. On the contrary to the method proposed in the existing literatures,  should be achieved with respect to the fault estimation error rather than the state estimation error.…”

Section: Uio Design For Faults Estimationmentioning

confidence: 99%

Recurrent Neural Network Based Robust Actuator and Sensor Fault Estimation for Satellite Attitude Control System

et al. 2020

View full text Add to dashboard Cite

For the satellite attitude control system with actuator and sensor fault, the paper proposes a neural network based robust state and fault estimation method. Compared with the traditional model-based approach that relies on the accurate model of the system, we train the recurrent neural network with the inputs and outputs of the current attitude control system to achieve the purpose of modeling and improving the accuracy of the model. Then, through the expansion of the system state vectors, the neural state space model is transformed into a generalized nonlinear system without sensor fault terms. Furthermore, a combination of the generalized unknown input observer scheme with the robust H linear parametervarying (LPV) approach is developed to estimate the system state and actuator faults simultaneously. According to Lyapunov theory, the stability analysis of observer is considered by transforming the dynamic error into the discrete time polytopic LPV form. Finally, some tests are performed on the satellite attitude control system to validate the effectiveness of the proposed method. INDEX TERMS Fault estimation, recurrent neural network, satellite attitude control system, unknown input observer, Lyapunov theory.

show abstract

Section: Uio Design For Faults Estimationmentioning

confidence: 99%

Recurrent Neural Network Based Robust Actuator and Sensor Fault Estimation for Satellite Attitude Control System

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Substituting (0) = 0 into (20), combining with the Lipchitz conditions of nonlinear term and taking Euclidean norm of both sides of (20), it can be obtained that…”

Section: Proof With Definition 6 and System Function (1) Let δ ( ) mentioning

confidence: 99%

“…However, on the assumptions that the systems are complex in practical issues [13,20], they display insufficiency when fault estimation needs a model of higher precision. Therefore, it is an irresistible trend to develop tools for fault estimation analysis and design of real industrial systems.…”

Section: Introductionmentioning

confidence: 99%

Iterative Learning Fault Estimation Design for Nonlinear System with Random Trial Length

et al. 2017

View full text Add to dashboard Cite

An iterative learning scheme-based fault estimation observer is designed for a class of nonlinear systems with randomly changed trial length. This is achieved by presenting a state observer for monitoring the system state and an iterative learning law for fault estimation in the presence of imprecise system model. An average factor is defined to deal with the lack and redundancy in tracking information caused by random trial length. Via the convergence analysis, sufficient design conditions are developed for estimation of fault signal. The observer gains and iterative learning law indexes are computed by solving the proposed conditions underconstraints. Numerical examples are presented to demonstrate the validity, the effectiveness, and the superiority of this method.

show abstract

“…A robust adaptive observer is developed to estimate state and both sensor and actuator faults for nonlinear systems despite the presence of disturbances. However, the authors in Aboutalebi et al (2018), Li et al (2016) and Valibeygi et al (2016) have proposed observers to estimate only the sensor faults and for the actuator fault estimation, methods have been given in Buciakowski et al (2017) and Witczak et al (2017). Furthermore, a FTC is applied not only to stabilize the closed-loop system but also to compensate the fault effects.…”

Section: Introductionmentioning

confidence: 99%

Robust fault tolerant control based on adaptive observer for Takagi-Sugeno fuzzy systems with sensor and actuator faults: Application to single-link manipulator

Makni

Bouattour

Chaabane

2020

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

In this work, we investigate the problem of control for nonlinear systems represented by Takagi-Sugeno (T-S) fuzzy models affected by both sensor and actuator faults subject to an unknown bounded disturbances (UBD). For this, we design an adaptive observer to estimate state, sensor and actuator fault vectors simultaneously despite the presence of external disturbances. Based on this observer, we develop a fault tolerant control (FTC) law not only to stabilize closed loop system, but also to compensate the fault effects. For the observer-based controller design, we propose less conservative conditions formulated in terms of linear matrix inequalities (LMIs). Moreover, both observer and controller gains are calculated via solving a set of LMIs only in single step. Finally, comparative results and an application to single-link flexible joint robot are afforded to prove the efficiency of the proposed design.

show abstract

A neural network approach to simultaneous state and actuator fault estimation under unknown input decoupling

Cited by 30 publications

References 37 publications

Recurrent Neural Network Based Robust Actuator and Sensor Fault Estimation for Satellite Attitude Control System

Recurrent Neural Network Based Robust Actuator and Sensor Fault Estimation for Satellite Attitude Control System

Iterative Learning Fault Estimation Design for Nonlinear System with Random Trial Length

Robust fault tolerant control based on adaptive observer for Takagi-Sugeno fuzzy systems with sensor and actuator faults: Application to single-link manipulator

Contact Info

Product

Resources

About