Marcin Pazera

Neural network-based robust actuator fault diagnosis for a non-linear multi-tank system

The paper is devoted to the problem of the robust actuator fault diagnosis of the dynamic non-linear systems. In the proposed method, it is assumed that the diagnosed system can be modelled by the recurrent neural network, which can be transformed into the linear parameter varying form. Such a system description allows developing the designing scheme of the robust unknown input observer within H∞ 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. The application of the robust unknown input observer enables actuator fault estimation, which allows applying the developed approach to the fault tolerant control tasks.

Robust unknown input observer for state and fault estimation in discrete-time Takagi–Sugeno systems

ABSTRACT In this paper, a robust unknown input observer (UIO) for the joint state and fault estimation in discrete-time Takagi–Sugeno (TS) systems is presented. The proposed robust UIO, by applying the framework, leads to a less restrictive design procedure with respect to recent results found in the literature. The resulting design procedure aims at achieving a prescribed attenuation level with respect to the exogenous disturbances, while obtaining at the same time the convergence of the observer with a desired bound on the decay rate. An extension to the case of unmeasurable premise variables is also provided. Since the design conditions reduce to a set of linear matrix inequalities that can be solved efficiently using the available software, an evident advantage of the proposed approach is its simplicity. The final part of the paper presents an academic example and a real application to a multi-tank system, which exhibit clearly the performance and effectiveness of the proposed strategy.

Neural Network-Based Simultaneous Estimation of Actuator and Sensor Faults.

The paper is devoted to the problem of a neural network-based robust simultaneous actuator and sensor faults estimator design for the purpose of the Fault Diagnosis (FD) of non-linear systems. In particular, the methodology of designing a neural network-based \(\mathcal {H_\infty }\) fault estimator is developed. The main novelty of the approach is associated with possibly simultaneous sensor and actuator faults. For this purpose, a Linear Parameter Varying (LPV) description of a Recurrent Neural Network (RNN) is exploited. The proposed approach guaranties a predefined disturbance attenuation level and convergence of the estimator. The final part of the paper presents an illustrative example concerning the application of the proposed approach to the multi-tank system fault diagnosis.

A process fault estimation strategy for non-linear dynamic systems

The paper deals with the problem of simultaneous state and process fault estimation for non-linear dynamic systems. Instead of estimating the fault directly, its product with state and the state itself are estimated. To derive the fault from the product, a simple algebraic approach is proposed. The estimation strategy is based on the quadratic boundedness approach. The final part of the paper presents an illustrative example concerning a laboratory multi-tank system. The real data experiments clearly exhibit the performance of the proposed approach.

Towards robust process fault estimation for uncertain dynamic systems

The paper deals with the problem of simultaneous state and process fault estimation for uncertain dynamic systems. Contrarily to the approaches presented in the literature, the nonlinear estimation problem is reduced to the linear one by introducing a suitable system reparameterization and new estimator structure. Instead of estimating the fault directly, its product with state and the state itself are estimated. To tackle this problem, a robust design procedure is proposed that takes into account uncertainties acting onto the system being diagnosed. The approach is based on the quadratic boundedness approach allowing convergence analysis of uncertain systems with bounded uncertainties. Subsequently, a simple algebraic approach is proposed to derive the fault estimate. The final part of the paper shows a numerical example concerning state and pitch actuator component fault estimation of a wind turbine.

Fault Tolerant-Control: Solutions and Challenges

Fault-Tolerant Control (FTC) systems are intensively investigated both from the theoretical and practical viewpoints. It is reflected in a large number of publications and research teams dealing with this emerging area. FTC is perceived as a technique integrating advanced fault diagnosis techniques and modern control methods that makes it possible a system to continue its mission under a faulty situation. It can be also observed that the fault diagnosis theory is well developed for linear systems. There are also approaches that can be efficiently used to minimize the uncertainty effect of the model of the system being controlled and diagnosed as well as noise and disturbances. This means that the development of analogous strategies for non-linear systems is fully justified. One of the main difficulties in the current development of FTC is the fact that most works presented in the literature treat fault diagnosis and FTC problems separately. Unfortunately, perfect fault diagnosis, and in particular fault identification, is impossible to attain. This justifies the necessity of developing integrated fault diagnosis and FTC, which takes into account such an unappealing phenomenon, both for linear and non-linear systems. As indicates the state-of-the-art regarding FTC, the integration issue is treated cursorily while the lack of suitable solution is replaced with a chain of (possibly conservative) assumptions related to fault diagnosis. Taking into account the above difficulties, the paper focuses on the presentation of modern FTC with analytical and soft computing approaches. An effective FTC methods are discussed along with the integration process of fault diagnosis and FTC.

Robust multiple sensor fault-tolerant control for dynamic non-linear systems: Application to the aerodynamical twin-rotor system

Abstract The paper deals with the problem of designing sensor-fault tolerant control for a class of non-linear systems. The scheme is composed of a robust state and fault estimator as well as a controller. The estimator aims at recovering the real system state irrespective of sensor faults. Subsequently, the fault-free state is used for control purposes. Also, the robust sensor fault estimator is developed in a such a way that a level of disturbances attenuation can be reached pertaining to the fault estimation error. Fault-tolerant control is designed using similar criteria. Moreover, a separation principle is proposed, which makes it possible to design the fault estimator and control separately. The final part of the paper is devoted to the comprehensive experimental study related to the application of the proposed approach to a non-linear twin-rotor system, which clearly exhibits the performance of the new strategy.

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.

A quadratic boundedness approach to a neural network-based simultaneous estimation of actuator and sensor faults

The paper is devoted to the problem of a neural network-based robust simultaneous actuator and sensor faults estimator design for the purpose of the fault diagnosis of nonlinear systems. In particular, the methodology of designing a neural network-based fault estimator is developed. The main novelty of the approach is associated with possibly simultaneous sensor and actuator faults under imprecise measurements. For this purpose, a linear parameter-varying description of a recurrent neural network is exploited. The proposed approach guaranties a predefined disturbance attenuation level and convergence of the estimator. In particular, it uses the quadratic boundedness approach to provide uncertainty intervals of the achieved estimates. The final part of the paper presents an illustrative example concerning the application of the proposed approach to the multitank system fault diagnosis.

Simultaneous estimation of multiple actuator anc sensor faults for Takagi-Sugeno fuzzy systems

The paper is devoted to the problem of a Takagi-Sugeno(TS)-based robust simultaneous actuator and sensor faults estimator design for the purpose of the Fault Diagnosis (FD) of non-linear systems. The proposed methodology of designing a TS-based H∞ fault estimator is developed in this paper. The main novelty of the approach is associated with possibly of simultaneous sensor and actuator faults estimation. The developed approach guaranties a predefined disturbance attenuation level and convergence of the designed estimator. The illustrative part of the paper shows an example of the application of the developed approach in the task of the fault diagnosis of the multi-tank system.