Search

Probabilistic Boolean Networks can capture the dynamics of complex biological systems as well as other non-biological systems, such as manufacturing systems and smart grids. In this proof-of-concept manuscript, we propose a Probabilistic Boolean Network architecture with a learning process that significantly improves the prediction of the occurrence of faults and failures in smart-grid systems. This idea was tested in a Probabilistic Boolean Network model of the WSCC nine-bus system that incorporates Intelligent Power Routers on every bus. The model learned the equality and negation functions in the different experiments performed. We take advantage of the complex properties of Probabilistic Boolean Networks to use them as a positive feedback adaptive learning tool and to illustrate that these networks could have a more general use than previously thought. This multi-layered PBN architecture provides a significant improvement in terms of performance for fault detection, within a positive-feedback network structure that is more tolerant of noise than other techniques. [ABSTRACT FROM AUTHOR]

Fast detection of motor failures is crucial for multi-rotor unmanned aerial vehicle (UAV) safety. It is well established in the literature that UAVs can adopt fault-tolerant control strategies to fly even when losing one or more rotors. We present a motor fault detection and isolation (FDI) method for multi-rotor UAVs based on an external wrench estimator and a recurrent neural network composed of long short-term memory nodes. The proposed approach considers the partial or total motor fault as an external disturbance acting on the UAV. Hence, the devised external wrench estimator trains the network to promptly understand whether the estimated wrench comes from a motor fault (also identifying the motor) or from unmodelled dynamics or external effects (i.e., wind, contacts, etc.). Training and testing have been performed in a simulation environment endowed with a physic engine, considering different UAV models operating under unknown external disturbances and unexpected motor faults. To further assess this approach’s effectiveness, we compare our method’s performance with a classical model-based technique. The collected results demonstrate the effectiveness of the proposed FDI approach. [ABSTRACT FROM AUTHOR]

This paper presents an online model-free sensor fault-tolerant control scheme capable of tolerating the most common faults affecting an induction motor. This approach involves using neural networks for fault detection to provide the controller with sufficient information to counteract adverse consequences due to sensor faults, such as degradation in performance, reliability, and even failures in the control system. The proposed approach does not consider the knowledge of the nominal model of the system or when the fault may occur. Therefore, a high-order recurrent neural network trained online by the Extended Kalman Filter is used to obtain a mathematical model of the system. The obtained model is used to synthesize a discrete-time sliding mode control. Then, the fault-detection and -isolation stage is performed by independent neural networks, which have as input the signal from the current sensor and the position sensor, respectively. In this way, the neural classifiers continuously monitor the sensors, showing the ability to know the sensor status. The combination of controller and fault detection maintains the operation of the motor during the time of the fault occurrence, whether due to sensor disconnection, degradation, or connection failure. In fact, the MLP neural network achieves an accuracy between 95% and 99% and shows an AUC of 97% to 99%, and this neural network correctly classifies true positives with acceptable performance. The Recall value is high, between 97% and 99%, and the F1 score confirms a good performance. In contrast, the CNN shows a higher accuracy, between 96% and 99% in accuracy and 98% to 99% in AUC. In addition, its Recall and F1 reflect a better balance and capacity to handle complex data, demonstrating its superiority to MLP in fault classification. Therefore, neural networks are a promising approach in areas such as fault-tolerant control. [ABSTRACT FROM AUTHOR]

This article presents an experimental application of fault detection, isolation, and estimation in a chemical reactor system, introducing a functional observer‐based approach without the need for linear approximation. The residual signal generators, functioning as disturbance‐decoupled functional observers, provide fault size estimates and enable fault isolation through multiple generators operating independently. The experimental study focuses on the 3‐Picoline oxidation process, deriving a discrete‐time model, and constructing specific residual generators for coolant inlet temperature and feed concentration faults. Fault diagnosis employs Fast Fourier Transform (FFT) filtering and Generalized Likelihood Ratio (GLR), facilitating on‐the‐fly detection during the experiment. The effectiveness of fault detection, disturbance decoupling, and estimation is experimentally validated. [ABSTRACT FROM AUTHOR]

The optimal functionality and dependability of mechanical systems are important for the sustained productivity and operational reliability of industrial machinery, and have a direct impact on its longevity and profitability. Therefore, the failure of a mechanical system or any of its components would be detrimental to production continuity and availability. Consequently, this study proposes a robust diagnostic framework for analyzing the blade conditions of shot blast industrial machinery. The framework explores the spectral characteristics of the vibration signals generated by the industrial shot blast for discriminative feature excitement. Furthermore, a peak detection algorithm is introduced to identify and extract the unique features present in the peak magnitudes of each signal spectrum. A feature importance algorithm is then deployed as the feature selection tool, and these selected features are fed into ten machine learning classifiers (MLCs), with extreme gradient boosting (XGBoost (version 2.1.1)) as the core classifier. The results show that the XGBoost classifier achieved the best accuracy of 98.05%, with a cost-efficient computational cost of 0.83 s. Other global assessment metrics were also implemented in the study to further validate the model. [ABSTRACT FROM AUTHOR]

This paper proposes a new geometric fault detection and isolation (FDI) strategy for uncertain neutral time-delay systems (UNTDS). Firstly, the concept of unobservability subspace is extended to the considered system. Subsequently, utilizing the geometric properties of factor space and canonical projection, the fault is divided into different unobservability subspaces. Therefore, an algorithm for constructing the subspace is developed for fault isolation. Finally, a set of observers is designed for the subsystems, and generates a set of structured residuals which is sensitive only to a specific fault. Additionally, the H ∞ technique is utilized to suppress the disturbances and error signals due to time-varying delays on the residual. The simulation examples verify the effectiveness of the proposed approach. • A new geometric FDI strategy can decouple all the residuals from the faults. • The H ∞ technique is used to suppress error signals due to time-varying delays. • Geometric approach is used to uncertain neutral time-delay system for the first time. • The occurrence and disappearance of multiple faults can be detected simultaneously. [ABSTRACT FROM AUTHOR]

This paper presents a mathematical model of the cardiovascular system (CVS) designed to simulate both normal and pathological conditions within the systemic circulation. The model introduces a novel representation of the CVS through a change of coordinates, transforming it into the "quadratic normal form". This model facilitates the implementation of a sliding mode observer (SMO), allowing for the estimation of system states and the detection of anomalies, even though the system is linearly unobservable. The primary focus is on identifying valvular heart diseases, which are significant risk factors for cardiovascular diseases. The model's validity is confirmed through simulations that replicate hemodynamic parameters, aligning with existing literature and experimental data. [ABSTRACT FROM AUTHOR]

This research introduces a new data-driven methodology for fault detection and isolation in dynamic systems, integrating fuzzy/Bayesian change point detection and decision trees induced by genetic programming for pattern classification. Tracking changes in sensor signals enables the detection of faults, and using decision trees generated by genetic programming allows for accurate categorization into specific fault classes. Change point detection utilizes a combination of fuzzy set theory and the Metropolis–Hastings algorithm. The primary contribution of the study lies in the development of a distinctive classification system, which results in a comprehensive and highly effective approach to fault detection and isolation. Validation is carried out using the Tennessee Eastman benchmark process as an experimental framework, ensuring a rigorous evaluation of the efficacy of the proposed methodology. [ABSTRACT FROM AUTHOR]

This paper proposes a new fault-tolerant control approach for gas turbines, based on fuzzy techniques that allow real-time observation of their behavior. The approach consists of detecting and locating faults, and then determining the appropriate control action to keep the turbine in stable operation. This improves the efficiency and lifespan of the turbine, and reduces maintenance costs with optimal planning. The state space model of the turbine is subjected to a diagnostic procedure based on Type-1 and Type-2 fuzzy models, using the operational data of the different operating points studied. The Luenberger observer is used in the fault detection mechanism, to characterize turbine component malfunctions by comparing the observed real behaviors and the fuzzy models. The results show that the fault-tolerant fuzzy control has ensured the stability and availability of the turbine during fault occurrence, with good performance in detection, isolation and reconfiguration. [ABSTRACT FROM AUTHOR]

The identification of railway vehicle components’ characteristics from measured data is a challenging task with compelling applications in health monitoring, fault detection, and system prognosis. Usually, though, such systems are highly nonlinear, and naive identification techniques may lead to unstable methods and inaccurate results. In this paper, we show that these issues can be easily tackled with the recently introduced proximal Gauss–Newton method, which we employ to identify the parameters of a railway nonlinear suspension system. In the proposed model, the parameters are subject to safety bounds in form of box constraints, which allows preventing nonphysical solutions. The suspension system we consider is highly nonlinear due to the presence of an airspring in the secondary suspension, which we introduce in a simplified Berg model. Numerical examples, featuring data corrupted by various noise levels, demonstrate the accuracy and efficiency of our proposed method. Comparisons with state-of-the-art approaches are also provided.

Abstract Due to the difficulties of system modeling, nonlinearity effects, uncertainties, and the availability of Wind Turbines (WTs) SCADA system data, data‐driven Fault Detection and Isolation (FDI) methods for WTs have received increasing attention. In this paper, using the wind turbine SCADA data, an effective FDI scheme is proposed using the K‐Nearest Neighbors (KNN) classifier. The operational data set is labeled by the status and warning data sets, and the labeled operational data set, after eliminating invalid data, feature selection, and standardization, is used for training and validation of the FDI model. Data imbalance, which is common in real data sets, does not affect the performance of the proposed method, hence there is no need for data balancing methods in this algorithm and the performance is not deteriorated by occurring false alarms. Therefore, the proposed method has provided impressive performance in FDI compared with previous research on this data set. Also, many of the fault classes addressed in this paper were not considered in previous works on this data set.

This paper presents an online model-free sensor fault-tolerant control scheme capable of tolerating the most common faults affecting an induction motor. This approach involves using neural networks for fault detection to provide the controller with sufficient information to counteract adverse consequences due to sensor faults, such as degradation in performance, reliability, and even failures in the control system. The proposed approach does not consider the knowledge of the nominal model of the system or when the fault may occur. Therefore, a high-order recurrent neural network trained online by the Extended Kalman Filter is used to obtain a mathematical model of the system. The obtained model is used to synthesize a discrete-time sliding mode control. Then, the fault-detection and -isolation stage is performed by independent neural networks, which have as input the signal from the current sensor and the position sensor, respectively. In this way, the neural classifiers continuously monitor the sensors, showing the ability to know the sensor status. The combination of controller and fault detection maintains the operation of the motor during the time of the fault occurrence, whether due to sensor disconnection, degradation, or connection failure. In fact, the MLP neural network achieves an accuracy between 95% and 99% and shows an AUC of 97% to 99%, and this neural network correctly classifies true positives with acceptable performance. The Recall value is high, between 97% and 99%, and the F1 score confirms a good performance. In contrast, the CNN shows a higher accuracy, between 96% and 99% in accuracy and 98% to 99% in AUC. In addition, its Recall and F1 reflect a better balance and capacity to handle complex data, demonstrating its superiority to MLP in fault classification. Therefore, neural networks are a promising approach in areas such as fault-tolerant control.

The optimal functionality and dependability of mechanical systems are important for the sustained productivity and operational reliability of industrial machinery, and have a direct impact on its longevity and profitability. Therefore, the failure of a mechanical system or any of its components would be detrimental to production continuity and availability. Consequently, this study proposes a robust diagnostic framework for analyzing the blade conditions of shot blast industrial machinery. The framework explores the spectral characteristics of the vibration signals generated by the industrial shot blast for discriminative feature excitement. Furthermore, a peak detection algorithm is introduced to identify and extract the unique features present in the peak magnitudes of each signal spectrum. A feature importance algorithm is then deployed as the feature selection tool, and these selected features are fed into ten machine learning classifiers (MLCs), with extreme gradient boosting (XGBoost (version 2.1.1)) as the core classifier. The results show that the XGBoost classifier achieved the best accuracy of 98.05%, with a cost-efficient computational cost of 0.83 s. Other global assessment metrics were also implemented in the study to further validate the model.

In many transport applications, one of the safety critical function is the localization. This is all the more true for land transport applications such as autonomous vehicles. While the democratization of satellite positioning systems, such as GPS, Galileo, Beidou or Glonass, has made it possible to consider a global solution applicable anywhere in the world, the principle of positioning by receiving signals from satellites more than twenty thousand kilometers away shows limits when they are confronted with disturbances related to the environment close to the receiver. However, for these safety-critical applications, the requirements are strong and sometimes even conflicting. The developed function must meet a defined level of precision, availability, continuity of service, integrity, operational safety and finally robustness to environment changes. Taken separately, these requirements can be achieved by actions recommended by the literature. For more precision and availability, coupling between absolute GNSS data and relative INS and odometer data, is recommended. To increase safety and integrity, a fault detection layer is essential, but this will negatively impact availability. One therefore needs a fault management layer. A harmonious policy, thought at the function design, makes it possible to achieve all the objectives. In this study, we propose a framework based on a tripartite approach: the tight fusion of GNSS and IMU data, the development of a diagnostic layer based on information theory and using the very promising alpha Rényi divergence, as well as a fault isolation layer. The diagnostic layer is designed to be robust and adaptive to changing environment through a deep neural network. The proposed framework is tested on data acquired in the field. Encouraging results allow to consider the generalization of the concept. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Due to the difficulties of system modeling, nonlinearity effects, uncertainties, and the availability of Wind Turbines (WTs) SCADA system data, data‐driven Fault Detection and Isolation (FDI) methods for WTs have received increasing attention. In this paper, using the wind turbine SCADA data, an effective FDI scheme is proposed using the K‐Nearest Neighbors (KNN) classifier. The operational data set is labeled by the status and warning data sets, and the labeled operational data set, after eliminating invalid data, feature selection, and standardization, is used for training and validation of the FDI model. Data imbalance, which is common in real data sets, does not affect the performance of the proposed method, hence there is no need for data balancing methods in this algorithm and the performance is not deteriorated by occurring false alarms. Therefore, the proposed method has provided impressive performance in FDI compared with previous research on this data set. Also, many of the fault classes addressed in this paper were not considered in previous works on this data set. [ABSTRACT FROM AUTHOR]

Model-based fault detection and isolation (FDI) methods allow to infer the health status of complex aerospace systems through a large quantity of data acquired in flight and evaluations of numerical models of the equipment. This results in an intensive computational procedure that can be addressed only grounding the aircraft. We introduce an original methodology to sensitively accelerate FDI by reducing the computational demand to identify the health status of the aircraft. Our scheme FREEDOM (Fast Reliability Estimate and Incipient Fault Detection of Multiphysics Aerospace Systems) proposes an original combination of a novel two-step compression strategy to compute offline a synthesized representation of the dynamical response of the system and uses an inverse Bayesian optimization approach to infer online the level of damage determined by multiple fault modes affecting the equipment. We demonstrate and validate FREEDOM against numerical and physical experiments for the case of an electromechanical actuator employed for secondary flight controls. Particular attention is dedicated to simultaneous incipient mechanical and electrical faults considering different experimental settings. The outcomes validate our FDI strategy, which permits to achieve the accurate identification of complex damages outperforming the computational time of state-of-the-art algorithms by two orders of magnitude. [ABSTRACT FROM AUTHOR]

Abstract For the integrity monitoring of a multi-source PNT (Positioning, Navigation, and Timing) resilient fusion navigation system, a theoretical framework of multi-level autonomous integrity monitoring is proposed. According to the mode of multi-source fusion navigation, the framework adopts the top-down logic structure and establishes the navigation source fault detection model based on the multi-combination separation residual method to detect and isolate the fault source at the system level and subsystem level. For isolated non-redundant navigation sources, the system level recovery verification model is used. For the isolated multi-redundant navigation sources, the sensor fault detection model optimized with the dimension-expanding matrix is used to detect and isolate the fault sensors, and the isolated fault sensors are verified in real-time. Finally, according to the fault detection and verification results at each level, the observed information in the fusion navigation solution is dynamically adjusted. On this basis, the integrity risk dynamic monitoring tree is established to calculate the Protection Level (PL) and evaluate the integrity of the multi-source integrated navigation system. The autonomous integrity monitoring method proposed in this paper is tested using a multi-source navigation system integrated with Inertial Navigation System (INS), Global Navigation Satellite System (GNSS), Long Baseline Location (LBL), and Ultra Short Baseline Location (USBL). The test results show that the proposed method can effectively isolate the fault source within 5 s, and can quickly detect multiple faulty sensors, ensuring that the positioning accuracy of the fusion navigation system is within 5 m, effectively improving the resilience and reliability of the multi-source fusion navigation system.

This paper presents a mathematical model of the cardiovascular system (CVS) designed to simulate both normal and pathological conditions within the systemic circulation. The model introduces a novel representation of the CVS through a change of coordinates, transforming it into the “quadratic normal form”. This model facilitates the implementation of a sliding mode observer (SMO), allowing for the estimation of system states and the detection of anomalies, even though the system is linearly unobservable. The primary focus is on identifying valvular heart diseases, which are significant risk factors for cardiovascular diseases. The model’s validity is confirmed through simulations that replicate hemodynamic parameters, aligning with existing literature and experimental data.

This paper considers model-based fault detection of large-scale (possibly rank-deficient) dynamic systems. Assuming only global (and not local) observability over a sensor network, we introduce a single time-scale networked estimator/observer. Sensors take local outputs/measurements of system states with partial observability and share their information (including estimation and/or output) over a communication network, and gain distributed observability. We define the conditions on the network structure ensuring distributed observability and stabilising the error dynamics. However, system outputs are prone to faults and uncertainties, which affect the state estimation of all sensors as a consequence of communicating (possibly) faulty data. From the cyber-physical-systems (CPS) perspective, such faults add bias to the data transferred from the physical layer (dynamic system) to the cyber layer (sensor network). In this work, we propose a localised fault detection and isolation (FDI) mechanism at sensors to secure distributed estimation. This protocol enables every sensor to locally identify the possible fault at the sensor measurement, and, via local detection and isolation, to prevent the spread of biased/faulty information over the network. This distributed isolation and localisation of fault follows from our partial observability assumption instead of full observability at every sensor. Then, other sensors can estimate/track the system by using observationally-equivalent output information to recover for possible loss of observability. In particular, we study rank-deficient systems as they are known to demand more information-sharing, and thus, are more vulnerable to the spread of possible faults over the network. One challenge is the detection of faults in the presence of system/output noise without making (simplifying and unrealistic) upper-bound assumptions on the noise support. We resolve this by adopting probabilistic threshold designs on the residuals. Further, we show that additive faults at rank-deficiency-related outputs affect the residuals at all sensors, a consequence that mandates more constraints on the (distributed) FDI strategy. We address this problem by constrained LMI design of the feedback gain matrix. Finally, we design q-redundant distributed estimators, resilient to isolation/removal of up to q number of faulty sensors, and further, we consider thresholding residual history over a sliding time-window, known as the stateful FDI. [ABSTRACT FROM AUTHOR]

Data-driven models have emerged as popular choices for fault detection and isolation (FDI) in process industries. However, real-time updating of these models due to streaming data requires significant computational resources, is tedious and therefore pauses difficulty in fault detection. To address this problem, in this study, we have developed a novel forward-learning neural network framework that can efficiently update data-driven models in real time for high-frequency data without compromising the accuracy. The neural network parameters are updated using a suitably constructed forward-forward learning algorithm instead of the traditional backpropagation algorithm. Firstly, we develop a variance-capturing forward-forward autoencoder (VFFAE) for FDI. Further, we showcase that the previously trained VFFAE model can be quickly adapted to incoming data which demonstrate the efficacy of the proposed framework. We have three process case studies to validate the proposed approach, namely, the Tennesse-Eastman dataset, nuclear power flux dataset, and wastewater plant dataset, to validate the proposed approach. Our findings demonstrate that within the initial 90 s, the model underwent 90 updates using a forward-forward approach and only 10 updates using backpropagation-based methods without compromising accuracy. This highlights the model's capacity to effectively handle streaming data during the modeling process. [Display omitted] [ABSTRACT FROM AUTHOR]

This paper aims to improve the fault detection adaptive threshold of Single-Phase Cascade Five-Level Inverter (SPFLCI) systems to make the system fault diagnosis more accurate. According to the complex electromechanical structure and various fault modes of the SPFLCI system, we proposed a fault diagnosis technique of cascade inverter system based on bonding diagram. Firstly, established a cascade inverter bond graph model through the bond graph theory and the ideas of controlled knots. Then, the upper and lower bounds of the range of uncertainty values of each parameter were calculated by minimizing the gap between residuals and interval thresholds in a normal state. And generated the optimized interval thresholds using the new ranges of these uncertainties. Finally, the optimized interval type (OIT) threshold is used to detect whether any fault has occurred. The simulation results showed that the OIT threshold can detect more minor faults relative to the absolute type. (AT) thresholds and the optimized absolute type (OAT) threshold. [ABSTRACT FROM AUTHOR]

A major concern in many electrical drives is the reliability of sensors and actuators. In the paper, the usage of the Drools expert system (ES) for Fault detection and isolation (FDI) of the additive actuator and sensor DC Motor faults using the Structured residuals design technique (SRDT) is presented. The SRDT is used to obtain essential knowledge about the system. Afterward, an expert system that can isolate faults based on the developed structure matrix and generated residuals is designed. Accordingly, following the structure matrix each residual becomes able to answer to a desired subset of faults and stands insensitive to the others. The proposed method is successfully applied in an analyzed laboratory system and can be used for online FDI.

This article addresses the problem of data-driven model discrimination for unknown switched systems with unknown linear temporal logic (LTL) specifications, representing tasks, that govern their mode sequences, where only sampled data of the unknown dynamics and tasks are available. To tackle this problem, we propose data-driven methods to over-approximate the unknown dynamics and to infer the unknown specifications such that both set-membership models of the unknown dynamics and LTL formulas are guaranteed to include the ground truth model and specification/task. Moreover, we present an optimization-based algorithm for analyzing the distinguishability of a set of learned/inferred model-task pairs as well as a model discrimination algorithm for ruling out model-task pairs from this set that are inconsistent with new observations at run time. Further, we present an approach for reducing the size of inferred specifications to increase the computational efficiency of the model discrimination algorithms.

Energy and exergy interactions in industrial systems hold meaning across physical domains. This paper builds on the notion that capturing the energy and exergy interactions of a system, while retaining physical structural context, enables fault detection and isolation. To this end, three energy graph-based visualisation methods were developed for the purpose of fault detection and isolation. This paper presents a comparative study of the three analysis methods designated the 1) distance parameter method, 2) eigenvalue decomposition method, and 3) residual method. The study utilises data from a physical lignite plant in Janschwalde, Germany, in combination with simulation data of specific faults in order to compare the sensitivity and robustness of the three methods. The comparison is done firstly in terms of detection and secondly in terms of isolation. The distance parameter and eigenvalue decomposition methods showed high sensitivity and robustness for fault detection, while the residual method showed moderate comparative performance. In terms of fault isolation, the distance parameter method showed high sensitivity and robustness, while the eigenvalue decomposition method had irregular isolation performance. The residual method isolation results proved inconclusive.

For switched cyber-physical systems with disturbances and actuator faults, we address fault detection and isolation problems. First, the preconditions relative to subsystems are discussed in detail, and the original subsystems are turned into an overall system. Second, the frequency ranges of faults are considered to belong to the finite-frequency domain, and the observer, which makes the residual robust against disturbances and sensitive to faults, is designed by combining the finite-frequency H− technique with the mixed L2 − L∞/H∞ technique. Third, design conditions, which guarantee that the error system is stable and satisfies the mixed performance, are derived using the average dwell time method and Lyapunov functionals. Finally, a traffic density dynamic model is proposed to demonstrate the validity and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

When applying graph-based fault detection and isolation (FDI) methods to the attributed graph data of large and complex industrial processes, the computational abilities and speed of these methods are adversely affected by the increased complexity. This paper proposes and evaluates five reduction techniques for the exergy-graph-based FDI method. Unlike the graph reduction techniques available in literature, the reduction techniques proposed in this paper can easily be applied to the type of attributed graph used by graph-based FDI methods. The attributed graph data of the Tennessee Eastman process are used in this paper since it is a popular process to use for the evaluation of fault diagnostic methods and is both large and complex. To evaluate the proposed reduction techniques, three FDI methods are applied to the original attributed graph data of the process and the performance of these FDI methods used as control data. Each proposed reduction technique is applied to the attributed graph data of the process, after which all three FDI methods are applied to the reduced graph data to evaluate their performance. The FDI performance obtained with reduced graph data is compared to the FDI performance using the control data. This paper shows that, using the proposed graph reduction techniques, it is possible to significantly reduce the size and complexity of the attributed graph of a system while maintaining a level of FDI performance similar to that achieved prior to any graph reduction. [ABSTRACT FROM AUTHOR]

For the integrity monitoring of a multi-source PNT (Positioning, Navigation, and Timing) resilient fusion navigation system, a theoretical framework of multi-level autonomous integrity monitoring is proposed. According to the mode of multi-source fusion navigation, the framework adopts the top-down logic structure and establishes the navigation source fault detection model based on the multi-combination separation residual method to detect and isolate the fault source at the system level and subsystem level. For isolated non-redundant navigation sources, the system level recovery verification model is used. For the isolated multi-redundant navigation sources, the sensor fault detection model optimized with the dimension-expanding matrix is used to detect and isolate the fault sensors, and the isolated fault sensors are verified in real-time. Finally, according to the fault detection and verification results at each level, the observed information in the fusion navigation solution is dynamically adjusted. On this basis, the integrity risk dynamic monitoring tree is established to calculate the Protection Level (PL) and evaluate the integrity of the multi-source integrated navigation system. The autonomous integrity monitoring method proposed in this paper is tested using a multi-source navigation system integrated with Inertial Navigation System (INS), Global Navigation Satellite System (GNSS), Long Baseline Location (LBL), and Ultra Short Baseline Location (USBL). The test results show that the proposed method can effectively isolate the fault source within 5 s, and can quickly detect multiple faulty sensors, ensuring that the positioning accuracy of the fusion navigation system is within 5 m, effectively improving the resilience and reliability of the multi-source fusion navigation system. [ABSTRACT FROM AUTHOR]

In this paper, the problem of active fault tolerant control (AFTC) is studied for polynomial nonlinear systems subject to asymmetric state constraints and measurement noise. The AFTC scheme is composed of the fault detection and isolation unit and the fault tolerant control unit. By using polynomial filters, the fault detection (FD) module and the fault isolation (FI) module are designed to obtain the accurate estimations of states and faults in the presence of measurement noise. The FD is realized by the residual evaluation approach, while the FI is achieved through the residual matching method. When a fault is detected and isolated, the controller switches from a nominal controller (NC) to a reconfigured controller (RC). To ensure that the asymmetric state constraint is not violated, a universal barrier Lyapunov function is introduced in the design of the NC and the RC. Moreover, the boundedness of tracking errors and estimation errors is analysed. Finally, the effectiveness of the proposed AFTC method is verified by a simulation for a dynamic point-the-bit rotary steerable drilling tool system. [ABSTRACT FROM AUTHOR]

Sensors and transducers play a vital role in the productivity of any industry. A sensor that is frequently used in industries to monitor flow is an orifice flowmeter. In certain instances, faults can occur in the flowmeter, hindering the operation of other dependent systems. Hence, the present study determines the occurrence of faults in the flowmeter with a model-based approach. To do this, the model of the system is developed from the transient data obtained from computational fluid dynamics. This second-order transfer function is further used for the development of linear-parameter-varying observers, which generates the residue for fault detection. With or without disturbance, the suggested method is capable of effectively isolating drift, open-circuit, and short-circuit defects in the orifice flowmeter. The outcomes of the LPV observer are compared with those of a neural network. The open- and short-circuit faults are traced within 1 s, whereas the minimum time duration for the detection of a drift fault is 5.2 s and the maximum time is 20 s for different combinations of threshold and slope. [ABSTRACT FROM AUTHOR]

Fault detection and isolation (FDI) problems for linear parameter-varying (LPV) systems with state time-delays are studied in this paper. By defining the concept of unobservability subspace and designing its calculation algorithm, the geometric approach is introduced to the time-delay LPV systems. Utilizing Wirtinger-based integral inequality, we obtain a sufficient condition to solve the so-called H∞-based residual generation problem for the LPV systems. In this paper, we consider two cases: the time delay is known and the time delay is unknown but its estimated value can be obtained. Corresponding observers are proposed for both cases based on the geometric approach and H∞ techniques. Lyapunov-Krasovskii functional is utilized to handle the time-delays and Wirtinger’s inequality is employed to reduce conservatism. Numerical examples are presented to demonstrate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Interplanetary space missions require spacecraft autonomy in order to fulfill the mission objective. The fault detection and isolation (FDI) system increases the level of autonomy and can ensure the safety of the spacecraft by detecting and isolating potential faults before they become critical. The proposed FDI system is based on an innovative bank of SMOs (sliding mode observers), designed for different fault scenarios cases. The FDI system design aims to detect and isolate actuators and measurement units’ faults used by the satellite control system and considers the nonlinear model of the satellite dynamics. This approach gives the possibility of fault reconstruction based on the information provided by an equivalent injection signal, allowing to reconstruct external perturbances and faults. The SMO chattering phenomenon is avoided by using the pseudo-sliding function, being a linear approximation of the signum function, which gives the possibility of using the equivalent injection signal for fault reconstruction purposes. The proposed fault reconstruction methodology is illustrated by a case study for a 6U Cubesat.

Introduction. The photovoltaic market has been increased over the last decade at a remarkable pace even during difficult economic times. Photovoltaic energy production becomes widely used because of its advantages as a renewable and clean energy source. It is eco-friendly, inexhaustible, easy to install, and the manufacturing time is relatively short. Photovoltaic modules have a theoretical lifespan of approximately 20 years. In real-life and for several reasons, some photovoltaic modules start to fail after being used for a period of 8 to 10 years. Therefore, to ensure safe and reliable operation of photovoltaic power plants in a timely manner, a monitoring system must be established in order to detect, isolate and resolve faults. The novelty of the proposed work consists in the development of a new model of sensors placement for faults detection in a photovoltaic system. The fault can be detected accurately after the analysis of changes in measured quantities. Purpose. Analysis of the possibility of the number and the position of the sensors into the strings in function of different faults. Methods. This new method is adapted to the bridge linked configuration. It can detect and locate failure points quickly and accurately by comparing the measured values. Results. The feasibility of the chosen model is proven by the simulation results under MATLAB/Simulink environment for several types of faults such as short-circuit current, open circuit voltage in the photovoltaic modules, partially and completely shaded cell and module.

At present, global positioning system (GPS) was widely used in outdoor positioning.However, the continuous development of cities complicated the positioning environment, resulting in a sharp decline in positioning accuracy.Therefore, the integrated positioning scheme of GPS/5G base station angle of arrival positioning/strap-down inertial navigation system (GPS-AOA-SINS) was adopted, and a fault-tolerant integrated navigation algorithm based on federated Kalman filter was proposed.Based on the GPS-AOA-SINS integrated positioning scheme, the algorithm added fault detection between the federated Kalman sub filter and the main filter, and adaptively adjusted the filter gain matrix of the fault sub filter.Experiments show that the proposed algorithm can effectively detect system faults and deal with them in real time, so as to improve the reliability of the system.

This study investigated the detection and isolation of gas path faults in a power plant gas turbine using efficiency data and fundamental quantities. First, attention is given to balancing data and selecting instances. Two new neural-fuzzy networks were then designed and trained using the Hippopotamus optimization algorithm. Developing these two networks aims to create a network resilient to noise with high accuracy and a low parameter count. Third, a broad spectrum of Artificial Intelligence based methods, such as shallow neural networks, machine learning models, and deep learning models, were employed to compare the proposed networks for fault detection and isolation of one power plant 163 MW gas turbine from Siemens Company. The investigation results indicate that the proposed hierarchical structure achieved an average of 99.81 % for fault detection and 99.50 % for fault isolation, consisting of only 203 learning parameters for fault detection and 335 for fault isolation, and operates better than the methods mentioned above in terms of accuracy, precision, sensitivity, and F1-Score metrics criteria. [ABSTRACT FROM AUTHOR]

In this article, the problem of fixed-time active fault-tolerant control is investigated for dynamical linear systems with intermittent faults and unknown disturbances. Unlike traditional active fault-tolerant control, fixed-time control is taken into account in this article since intermittent faults appear and disappear within a certain period of time. The entire active fault-tolerant control framework is composed of fault detection, fault isolation, fault and state estimation as well as the reconfigurable controller. Using the homogeneity-based observers, states and faults are well estimated and a fault diagnosis scheme is proposed for the sake of detecting and isolating intermittent faults in a fixed time. The fault-tolerant controller, which provides global practical fixed-time stability of the closed-loop system, has two switching states corresponding to the appearance and disappearance of intermittent faults. As a consequence, intermittent faults are compensated via the designed active fault-tolerant control method and the system reaches practical stability with the entire convergence time bounded in a fixed time. Finally, two examples are exploited to demonstrate the effectiveness of theoretical results. • Active fault-tolerant controller is designed for systems with intermittent faults (IFs). • Fault diagnosis unit for IF is realized with diagnosis time bounded in a fixed time. • The global practical fixed-time stability of the closed-loop system is guaranteed. [ABSTRACT FROM AUTHOR]

The rise of Industry 4.0 technologies has revolutionized industries, enabled seamless data access, and fostered data-driven methodologies for improving key production processes such as maintenance. Predictive maintenance has notably advanced by aligning decisions with real-time system degradation. However, data-driven approaches confront challenges such as data availability and complexity, particularly at the system level. Most approaches address component-level issues, but system complexity exacerbates problems. In the realm of predictive maintenance, this paper proposes a framework for addressing drift detection and diagnosis in heterogeneous manufacturing processes. The originality of the paper is twofold. First, this paper proposes algorithms for handling drift detection and diagnosing heterogeneous processes. Second, the proposed framework leverages several machine learning techniques (e.g., novelty detection, ensemble learning, and continuous learning) and algorithms (e.g., K-Nearest Neighbors, Support Vector Machine, Random Forest and Long-Short Term Memory) for enabling the concrete implementation and scalability of drift detection and diagnostics on industrial processes. The effectiveness of the proposed framework is validated through metrics such as accuracy, precision, recall, F1-score, and variance. Furthermore, this paper demonstrates the relevance of combining machine learning and deep learning algorithms in a production process of SEW USOCOME, a French manufacturer of electric gearmotors and a market leader. The results indicate a satisfactory level of accuracy in detecting and diagnosing drifts, and the adaptive learning loop effectively identifies new drift and nominal profiles, thereby validating the robustness of the framework in real industrial settings. [ABSTRACT FROM AUTHOR]

The paper proposes an original, comprehensive, and methodically consistent graph theory-based approach to the description of the diagnosed process and the diagnosing system. The main baseline of the presented approach is in the dichotomous approach to diagnosing. It involves a separate description of both the process and the diagnostic system. This approach reflects the practice of designing implementable diagnostic systems. Thus, it can be seen as a proposal of a new, alternative, and, at the same time, flexible design procedure with great potential for applications. The primary motivation behind it was an attempt to circumvent the numerous limitations of well-known and well-established diagnosis approaches proposed by the communities working on fault detection and isolation (FDI) and artificial intelligence theories for diagnosis (DX). Accordingly, the paper identifies and provides an extensive discussion and a critical analysis of the existing limitations. Numerous examples and references to practical applications of the approach are indicated.

This paper proposes a data-driven actuator fault detection and isolation approach for the general class of nonlinear systems. The proposed method uses a deep neural network architecture to obtain an invariant set of basis functions for the Koopman operator to form a linear Koopman predictor for a nonlinear system. Then, the obtained linear model is used for fault detection and isolation purposes without relying on prior knowledge about the underlying dynamics. Moreover, a recursive method is proposed for fault detection and isolation that is entirely data-driven with the key feature of global validity for the system's whole operating region due to the Koopman operator's global characteristic. Finally, the approach's efficacy is demonstrated using two simulations on a coupled nonlinear system and a two-link manipulator benchmark. • A novel data-driven DMD-based Koopman FDI (K-FDI) method is presented for detecting and isolating actuator faults. • A new Koopman-based state-preserving DNN architecture is proposed for actuated systems. • The nonlinear FDI problem is formulated as linear FDI using Koopman operator. • The presented Koopman FDI method is extended to be computed incrementally for real-time situation. [ABSTRACT FROM AUTHOR]