Piotr Witczak

Neural-network based robust predictive fault-tolerant control for multi-tank system

The main contribution of the paper was to propose a robust predictive fault-tolerant control scheme for a class of non-linear discrete-time systems that can be described with the LPV models using neural networks. Indeed, the contribution can be divided into a few important points: extension of the efficient predictive control to the robust case with exogenous external disturbances acting on the system, development of robust fault estimation and compensation scheme, and an integration of the developed schemes within a unified robust predictive fault-tolerant control framework. The proposed approach was applied to the benchmark example of the multi-tank system. The achieved results show the performance of the high performance of the proposed approach. In spite of the incontestable appeal of the proposed approach there are still some points, which may further improve its effectiveness. Indeed, in the proposed approach it is assumed the the state is available and, hence a natural approach is to relax this assumption by the introduction of a suitable state estimation strategy.

A robust fault-tolerant model predictive control for linear parameter-varying systems

The paper deals with the problem of robust fault-tolerant model predictive control for non-linear discrete-time systems described by the Linear Parameter-Varying model. The proposed approach is based on a multi-stage stage procedure. Robust controller is designed without taking into account the input constraints related with the actuator saturation and deals with previously estimated faults. Thus, to check the compensation feasibility, employed robust invariant set takes into account the input constraints. If the current state does not belong to the robust invariant set, then a predictive control is performed in order to enhance the invariant set. This appealing phenomenon makes it possible to enlarge the domain of attraction, which makes the proposed approach an efficient solution for the fault-tolerant control. The final part of the paper shows an illustrative example for the variable-speed variable-pitch wind turbines.

Efficient Predictive Fault-Tolerant Control for Non-linear Systems

The paper deals with the problem of robust predictive fault-tolerant control for non-linear discrete-time systems. The proposed approach is based on a triple stage procedure, i.e. its starts from fault estimation, the fault is compensated with a robust controller. Finally, if the fault compensation does not provide satisfactory, which means that the current state does not belong to the robust invariant set, then a suitable predictive control actions are performed in order to enhance the invariant set. This appealing phenomenon makes it possible to enlarge the domain of attraction, which makes the proposed approach an efficient solution. The final part of the paper shows how to extend the proposed approach to the non-linear systems that can be described with the Takagi-Sugeno models.

A practical test for assessing the reachability of discrete-time Takagi-Sugeno fuzzy systems

Abstract This paper provides a necessary and sufficient condition for the reachability of discrete-time Takagi–Sugeno fuzzy systems that is easy to apply, such that it constitutes a practical test. The proposed procedure is based on checking if all the principal minors associated to an appropriate matrix are positive. If this condition holds, then the rank of the reachability matrix associated to the Takagi–Sugeno fuzzy system is full for any possible sequence of premise variables, and thus the system is completely state reachable. On the other hand, if the principal minors are not positive, the property of the matrix being a block P one with respect to a particular partition of a set of integers is studied in order to conclude about the reachability of the Takagi–Sugeno system. Examples obtained using an inverted pendulum are used to show that it is easy to check this condition, such that the reachability analysis can be performed efficiently using the proposed approach.

Robust H ∞ actuator fault diagnosis with neural network

The paper deals with the problem of a robust actuator fault diagnosis for Linear Parameter-Varying (LPV) systems with Recurrent Neural-Network (RNN). The preliminary part of the paper describes the derivation of a discrete-time polytopic LPV model with RNN. Subsequently, a robust fault detection, isolation and identification scheme is developed, which is based on the observer and H∞ framework for a class of nonlinear systems. The proposed approach is designed in such a way that a prescribed disturbance attenuation level is achieved with respect to the actuator fault estimation error while guaranteeing the convergence of the observer.

Neural-Network Based Robust FTC: Application to Wind Turbines

The paper deals with the problem of a robust fault diagnosis of a wind turbine. The preliminary part of the paper describes the Linear Parameter-Varying model derivation with a Recurrent Neural Network. The subsequent part of the paper describes a robust fault detection, isolation and identification scheme, which is based on the observer and \(\mathcal{H}_{\infty}\) framework for a class of non-linear systems. The proposed approach is designed in such a way that a prescribed disturbance attenuation level is achieved with respect to the actuator fault estimation error while guaranteeing the convergence of the observer. Moreover, the controller parameters selection method of the considered system is presented. Final part of the paper shows the experimental results regarding wind turbines, which confirms the effectiveness of proposed approach.

A Neural-Network-Based Robust Observer for Simultaneous Unknown Input Decoupling and Fault Estimation

The paper deals with the problem of neural-network based on robust unknown input observer design for the fault diagnosis. Authors review the recent development in the area of robust observers for non-linear discrete-time systems and propose less restrictive procedure for design of the \({\mathcal {H}_\infty }\) observer. The approach guaranties simultaneously the unknown input decoupling and the fault estimation. The paper presents an unknown input observer design that reduces to a set of linear matrix inequalities. The final part of the paper presents an illustrative example devoted to fault diagnosis of the wind turbine.

Design of robust predictive fault-tolerant control for Takagi-Sugeno fuzzy systems: Application to the twin-rotor system

The paper deals with the problem of robust predictive fault-tolerant control for non-linear discrete-time systems described by the Takagi-Sugeno models as well as application to the so-called Twin-Rotor system. Approach proposed in this paper is in fact series of three, i.e. it starts from fault estimation, which is subsequently compensated with a robust controller. While robust controller is designed without taking into account the input constraints, compensation feasibility is proven by introducing invariant set of states, which takes into account the input constraints. If the current state do not belong to a robust invariant set, appropriate predictive control actions are performed. This appealing phenomenon makes it possible to enlarge the domain of attraction, making the proposed approach an efficient solution for the fault-tolerant control. The final part of the paper shows an illustrative example of proposed approach to the Twin-Rotor system.

A predictive actuator fault-tolerant control strategy under input and state constraints

The paper deals with the design of a robust predictive fault-tolerant control for linear discrete-time systems with an application of the quadratic boundedness theory and an associated robust invariant set. The main problem is to maintain the state of the system inside the robust invariant set obtained under asymmetric input and state constraints. The proposed strategy relies on a three-stage procedure, which is based on adaptive fault estimation as well as robust and predictive controller. The fault-recovery procedure is initiated with fault estimation and then the fault is compensated with a robust controller. In a case when robust fault compensation fails, i.e. the current state does not belong to the robust invariant set, a suitable predictive action is started. The main goal of this action is to generate control allocation enhancing the robust invariant set. This appealing phenomenon makes it possible to enlarge the domain of attraction of the possibly faulty system. The final part of the paper shows an illustrative example regarding a two-tank system.

Thrust balance estimation of an unmanned aerial vehicle: Application to fault detection

Due to uncertain flight conditions as well as faults, an outdoor performance of any unmanned aerial vehicle is a challenging task. Indeed, owing to weather conditions it is entirely different that any laboratory tests. While small and radio controlled drones are relatively common devices, they are still unruly while wind blows. Moreover, process and actuator faults may also significantly impair the overall system performance. All of these factors are reflected by the thrust balance. Thus, the main objective of this paper is to propose a scheme that can be used for simultaneous estimation the thrust balance as well as the state under uncertain environment. The estimated information allows performing decisions about the current faulty/fault-free situation of the system. The proposed approach is based on the paradigm, which can be relatively easily implemented on the chips dedicated to popular drones, such as Arduino or raspberry pi based solutions that are widely available.