Nizar Chatti

Bridging data-driven and model-based approaches for process fault diagnosis and health monitoring: A review of researches and future challenges

Fault Diagnosis and Health Monitoring (FD-HM) for modern control systems have been an active area of research over the last few years. Model-based FD-HM computational approaches have been extensively developed to detect and locate faults by considering logical or mathematical description of the monitored process. However, because of parametric, measurement and model uncertainties, applicable approaches that endeavor to locate faults with great accuracy are likely to give false alarms. Recently, many research works have been conducted in order to tackle this issue by making a tradeoff between accuracy and robustness during the fault detection phase. Due to the recent advances in sensor technology, computational capabilities and dedicated software/hardware interfaces, data-driven FD-HM approaches have demonstrated that highly accurate fault detection is possible when the system monitoring data for nominal and degraded conditions are available. Therefore, it seems that more than one approach is usually required for developing a complete robust fault detection and diagnosis tool. In this paper, the features of different model-based and data-driven approaches are investigated separately as well as the existing works that attempted to integrate both of them. In this latter context, there have been only few works published in the literature and hence reviewing and discussing them is strongly motivated by providing a good reference for those interested in developing hybrid approaches for FD-HM.

Signed Bond Graph for multiple faults diagnosis

Different approaches have been developed to perform diagnosis and supervision on continuous systems. On the one hand, Consistency-Based Diagnosis (CBD) as a qualitative approach has proved its convenience to diagnose multiple faults. However, it faces some problems regarding robustness in decision step and difficulties to obtain an accurate qualitative model. On the other hand, the quantitative approaches based Fault Detection and Isolation (FDI) enable to generate a set of fault indicators called residuals in order to carry out on-line diagnosis. The performances of such methods depend mainly on the behavioural model accuracy and their implementation is sometimes difficult to realise, especially when the possibility of multiple faults is taken into account. To overcome the drawbacks of such methods and to fully exploit their strengths, we give a formal description of a graphical model called Signed Bond Graph (SBG). This formalism exploits its qualitative and quantitative structural properties enabling the generation of multiple behaviour predictions (i.e. possible conflicts). Furthermore, since the SBG is constructed from the Bond Graph (BG) model, the use of this latter as a quantitative method for residuals generation allows to compare the results emanating from the qualitative reasoning based SBG in order to eliminate the possible conflicts which are inconsistent or not physically possible even though they sound logical from a qualitative point of view. The proposed approach is illustrated by a real application to a traction system of an intelligent and autonomous vehicle performed within the European project InTraDE. The result shows its good applicability and efficiency.

Functional and Behavior Models for the Supervision of an Intelligent and Autonomous System

The graphical approaches often have different backgrounds and view a system or an algebraic model from different perspectives in order to facilitate the communication and the understanding. These graphical approaches satisfy the modeling needs and give a clear and easily understandable overview of the behavioral and functional models and make easier to see what the process is, which vulnerabilities and asset that are involved and how the system works. The main goal of this paper is to develop and implement a methodology which combines the functional analysis and the bond graph (BG) tool for intelligent and autonomous systems. As a result, a supervisory interface is obtained, given under a finite automaton, displaying to the operators the possibilities the system has to achieve or not, its objectives. Each operating mode, corresponding to a vertex of the automaton, is associated with a set of services from a functional point-of-view and is defined accurately by a behavioral BG model. Furthermore, the service availability (associated to the BG elements) and the conditions for switching from one mode to another one are analyzed by fault detection and isolation algorithms generated on the basis of the structural and causal properties of the BG tool. Moreover, when a fault is not completely isolable some results can nevertheless be expressed in terms of available or unavailable services.

Model-based approach for fault diagnosis using set-membership formulation

This paper describes a robust model-based fault diagnosis approach that enables to enhance the sensitivity analysis of the residuals. A residual is a fault indicator generated from an analytical redundancy relation which is derived from the structural and causal properties of the signed bond graph model. The proposed approach is implemented in two stages. The first stage consists in computing the residuals using available input and measurements while the second level leads to moving horizon residuals enclosures according to an interval consistency technique. These enclosures are determined by solving a constraint satisfaction problem which requires to know the derivatives of measured outputs as well as their boundaries. A numerical differentiator is then proposed to estimate these derivatives while providing their intervals. Finally, an inclusion test is performed in order to detect a fault upon occurrence. The proposed approach is well suited to deal with different kinds of faults and its performances are demonstrated through experimental data of an omni-directional robot.

A bond graph modeling for health monitoring and diagnosis of the Tennessee Eastman process

Data-driven fault detection and diagnosis approaches are widely applicable in many real-time practical applications. Among these applications, the industrial benchmark of Tennessee Eastman Process (TEP) is widely used to illustrate and compare control and monitoring studies. However, due to the complexity of physical phenomena occurring in such process, no model-based approach for fault diagnosis has been developed and most of the diagnosis approaches applied to the TEP are based on experiences and qualitative reasoning that exploit the massive amount of available measurement data. In this paper, we propose to use the Bond Graph formalism as a multidisciplinary energetic approach that enables to obtain a graphical nonlinear model of the TEP not only for simulation purposes but also for monitoring tasks by generating formal fault indicators. In this study, the proposed BG model is validated from the experiment data and the problem of the TEP model design is hence overcome.

Model-based fault detection and diagnosis of complex chemical processes: A case study of the Tennessee Eastman process

Fault detection and diagnosis for industrial systems has been an important field of research during the past years. Among these systems, the Tennessee Eastman process is extensively used as a realistic benchmark to test and compare different fault detection and diagnosis strategies. In this context, data-driven approach has been widely applied for fault detection and diagnosis of the Tennessee Eastman process, by exploiting the massive amount of available measurement data. However, only few published works had attempted to deal with the dynamic behavior of the whole system including the mixing zone, circulating pumps, the reactor, the separator, the stripper, and so on, because of the difficulty of modeling physical phenomena that may occur in such complex system. In this article, an accurate model of the Tennessee Eastman process, properly tailored for fault detection and diagnosis purposes, is provided. This model shows better fault detection and diagnosis performances than all the others proposed in the literature and gives better or comparable results with the data-driven approaches. This work uses the bond graph methodology to systematically develop computational and graphical model. This methodology provides a physical understanding of the system and a description of its dynamic behavior. The bond graph model is then used for monitoring purposes by generating formal fault indicators, called residuals, and algorithms for fault detection and diagnosis. Hence, abnormal situations are detected by supervising the residuals’ evolution and faults are isolated using the nature of the violated residuals. Therefore, the dynamic model of the Tennessee Eastman process can now be used as a basis to achieve accurately different analysis through the causal and structural features of the bond graph tool.

A generic framework for decision fusion in Fault Detection and Diagnosis

Abstract In this paper, we propose a unified framework that enables decisions fusion for applications dealing with multiple heterogeneous Fault Detection and Diagnosis (FDD) methods. This framework, which is a discrete Bayesian Network (BN), is generic and can encompass all FDD method, whether it requires an accurate model or historical data. The main issue concerns the integration of different decisions emanating from individual FDD methods in order to obtain more reliable results. The methodology is based on a theoretical learning of the BN parameters, according to the FDD objectives to be reached. The development leads to a multi-objective problem under constraints, which is solved with a lexicographic approach. The effectiveness of the proposed decision fusion approach is validated through the Tennessee Eastman Process (TEP), which represents a challenging industrial benchmark. The application demonstrates the viability of the approach and highlights its ability to ensure a significant improvement in FDD performances, by providing a high fault detection rate, a small false alarm rate and an effective strategy for the resolution of conflicts among different FDD methods.

SBG for Health Monitoring of Fuel Cell System

To guarantee the safe operation of the Fuel Cell (FC) systems, it is necessary to use systematic techniques to detect and isolate faults for diagnosis purposes. The problematic for Fault Detection and Isolation (FDI) model-based of fuel cell consists in that such system is bad instrumented, its model is complex (because of coupling of multi-physical phenomena such as electrochemical, electrical, thermo fluidic…) and the numerical values related to it are not always known. This is why qualitative model (based on existence or not of the links between variables and the relations) is well suited for fuel cell diagnosis. In this paper, we propose a new graphical model (named Signed Bond Graph) allowing to combine both qualitative and quantitative features for health monitoring (in terms of diagnosis and prognosis) of the fuel cell. The innovative interest of the presented paper is the use of only one representation for not only structural model but also diagnosis of faults which may affect the fuel cell. The developed theory is illustrated by an application to a Proton Exchange Membrane Fuel Cell (PEMFC).

Bond Graph Model Based and Fuzzy Logic For Robust FDI of Mechatronic Systems

Abstract Fault diagnosis is crucial for ensuring the safe operation of complex engineering systems and avoiding to execute an unsafe behaviour. This paper deals with robust decision making (RDM) for fault detection of an electromechanical system by combining the advantages of Bond Graph (BG) modelling and Fuzzy logic reasoning. The proposed fault diagnosis method is implemented in two stages. In the first stage, the residuals are deduced from the BG model allowing to build a Fault Signature Matrix (FSM) according to the sensitivity of residuals to different parameters. In the second stage, the result of FSM and the robust residual thresholds are used by the fuzzy reasoning mechanism in order to evaluate a degree of detectability for each set of components. Finally, in order to make robust decision according to the detected fault component, an analysis is done between the output variables of the fuzzy system and components having the same signature in the FSM. The performance of the proposed fault diagnosis methodology is demonstrated through experimental data of an omnidirectional robot.