Fault Detection And Isolation Scheme Research Articles

Wind turbine fault detection and isolation robust against data imbalance using KNN

AbstractDue 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.

FREEDOM: Validated Method for Rapid Assessment of Incipient Faults of Aerospace Systems

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.

Deep Learning-Based Robust Actuator Fault Detection and Isolation Scheme for Highly Redundant Multirotor UAVs

This article presents a novel approach for detecting and isolating faulty actuators in highly redundant Multirotor UAVs using cascaded Deep Neural Network (DNN) models. The proposed Fault Detection and Isolation (FDI) framework combines Long Short-Term Memory (LSTM)-based fault detection and faulty actuator locator models to achieve real-time monitoring. The study focuses on a Hexadecarotor multirotor UAV equipped with sixteen rotors. To tackle the complexity of FDI resulting from redundancy, a partitioning technique is introduced based on system dynamics. The proposed FDI scheme is composed of a region classifier model responsible for detecting faults and fault locator models that precisely determine the location of the failed actuator. Extensive training and testing of the models demonstrate high accuracy, with the regional classifier model achieving 98.97% accuracy and the fault locator model achieving 99.107% accuracy. Furthermore, the scheme was integrated into the flight control system of the UAV, before being tested via both real-time monitoring in the simulation environment and analysis of recorded real flight data. The models exhibit remarkable performance in detecting and localizing injected faults. Therefore, using DNN models and the partitioning technique, this research offers a promising method for accurately detecting and isolating faulty actuators, thereby improving the overall performance and dependability of highly redundant Multirotor UAVs in various operational scenarios.

Actuator FDI Scheme for a Wind Turbine Benchmark Using Sliding Mode Observers

This paper proposes a fault detection and isolation (FDI) scheme for a wind turbines subject to actuator faults in both the pitch system and the drive train system. The proposed scheme addresses fault detection and isolation problems using a fault estimation approach. The proposed approach considers the use of a particular class of sliding mode observers (SMOs) designed to maintain the sliding motion even in the presence of actuator faults. The fault detection problem is solved by reconstructing the actuator faults through an appropriate analysis of the nonlinear output error injection signal, which is required to keep the SMO in a sliding motion. To ensure accurate fault reconstruction, only two conditions are required, namely that the faults are bounded and they meet the matching condition. A scheme based on a bank of SMOs is proposed to solve the fault detection and isolation problem in the pitch system. For the drive train system, a scheme using only one SMO is proposed. The performance of the proposed FDI scheme is validated by using a wind turbine benchmark model subjected to several actuator faults. Normalized root mean square error (NRMSE) analysis is performed to evaluate the accuracy of the actuator fault estimations.

Fault diagnosis of floating offshore wind farms, a benchmark case study*

Operation and maintenance costs of floating offshore wind farms (FOWFs) can be reduced by considering appropriate fault detection and isolation (FDI) and fault-tolerant control methods. This paper introduces a FOWF benchmark with the capacity to recreate common fault scenarios on the subsystems composing the turbines. Additionally, the paper proposes a FDI strategy as an example case, based on nonlinear parity equations, obtained from structural analysis and non-faulty data, with an adaptive threshold generation mechanism. The proposed FDI approach is assessed using the benchmark case study, showing that most of the faults can be effectively detected, while showing to be insensitive to the electric generator faults.

An energy graph eigendecomposition approach to fault detection and isolation applied to a gas-to-liquids process

Fault detection and isolation (FDI), which make up a large part of a process monitoring protocol, is a refined scheme which aims to detect and isolate anomalies that occur within an industrial plant. For the past 50+ years, much work has been done on developing FDI schemes for a vast array of different applications. In recent years, novel energy-based FDI techniques were proposed, as energy is seen as a unifying parameter of different domains. Additionally, the proposed energy-based approaches attempt to capture causal (or structural) information of the considered physical system. Keeping with this theme, this study will determine, after some alterations, the applicability and performance of some of the previously proposed energy-based approaches, especially compared to one another, when applied to a single, larger-scale gas-to-liquid (GTL) process. The approaches covered in this study include one qualitative eigendecomposition approach, one quantitative eigendecomposition approach, and a graph matching approach utilising a distance parameter (DC-value). Even though the quantitative eigendecomposition approach revealed improved detection sensitivity over the DC-value approach for faulty conditions, both techniques revealed a detection accuracy of 89%. The DC-value approach could correctly isolate 71% of the fault cases while the quantitative and qualitative eigendecomposition approaches could respectively only match 37.69% and 11% correctly. Even though the eigendecomposition approaches could not outperform the DC-value approach, the resolution benefit of 6 parameters that it offers warrants further research.

Sensor fault detection and isolation via networked estimation: rank-deficient dynamical systems

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.

Design of a computationally efficient observer-based distributed fault detection and isolation scheme in second-order networked control systems

This paper presents a novel directional observer-based fault detection and isolation scheme for second-order networked control systems (NCS). The directional unknown input observer (UIO) tool is exploited to study the problem of distributed fault detection and isolation (FDI). Two design schemes with global and partial/local network models are proposed to solve the distributed FDI problem. Thresholds are computed for the application of the proposed schemes in a noisy environment. In addition, the salient features of the proposed schemes are that both fault detection and fault isolation are achieved in a single step using a single observer. The schemes are applied to power system models to validate their results. A detailed comparison with existing FDI schemes is also provided, which clearly shows the effectiveness of the proposed scheme in terms of computational requirements.

Model-Based FDI Applied to a Piezoelectric Active Vibration Suppression System for Smart Flexible Spacecraft

Fault Detection and Isolation (FDI) techniques have captured extensive interest and attention in modern autonomous systems; in particular, they are of foremost importance in space applications, due to their scientific relevance, cost and current inability of doing on-orbit maintenance of space systems. In this scenario, FDI strategies are required to counteract possible failure events that, if not properly handled, can reduce system performance or compromise the realization of the mission objectives. In this paper, a model-based FDI strategy is implemented onboard a satellite equipped with a very large mesh reflector on which a distributed network of smart actuators/sensors is mounted to actively counteract undesired elastic vibrations. In particular, the detection and isolation of a possible piezo-actuator failure occurring in the Active Vibration Control (AVC) system of the antenna is addressed by a bank of Unknown Input Observers (UIOs). The design of the proposed UIOs is derived by solving a Linear Matrix Inequality (LMI) problem, which provides the conditions for their existence, and it is based on the linearized 3D state-space model of the controlled spacecraft, under the assumption that all the uncertainties, exogenous disturbances and measurement noises are neglected. Furthermore, pole assignment in the sense of D-stability is integrated in the standard formulation of the UIO to guarantee an adequate transient behaviour of the observers. Finally, an extensive Monte Carlo simulation campaign is conducted to assess the effectiveness of the proposed FDI architecture and its robustness against modelling uncertainties and measurement noise.

Fault Detection and Isolation for a Cooling System of Fuel Cell via Model-based Analysis

The development of fuel cell electric vehicles in recent years has led to increased interest in the use of fuel cells as sources of renewable energy. To achieve successful commercialization of fuel cell vehicles, it will be necessary to guarantee the safety, reliability, and lifetime of fuel cell systems by predictive fault detection and isolation (FDI). In this study, the parity equation, an observer, and a Kalman filter are employed together to compare the characteristics of FDI, focusing on the sensors of the thermal management system. Residuals corresponding to the difference between temperature outputs of linear models under driving cycles and nonlinear temperature outputs are used to isolate faults. Then, assessment of three model-based sensor FDI schemes is used to isolate sensor faults using the Cumulative Sum Control Chart (CUSUM) method. Generated residuals are evaluated by CUSUM to detect the presence of a sensor fault. As a result, isolated sensor faults are assessed.

Event-Triggered Switching-Type Fault Detection and Isolation for Fuzzy Control Systems Under DoS Attacks

This article investigates the memory adaptive event-triggered fault detection and isolation (FDI) problem for nonlinear networked control systems under periodic denial-of-service (DoS) attacks, where the nonlinear systems are described by Takagi–Sugeno (T–S) fuzzy models with unknown membership functions. First, a novel event-triggered mechanism is proposed to save communication resources. The triggering threshold is adaptively adjusted by multiple previous sampled data, not only depending on the latest triggering data. Second, taking DoS attacks, and event-triggered mechanism into consideration, a switching state-feedback controller is established, and the exponential stability is derived. Meanwhile, the controller, and the event-triggered mechanism are simultaneously developed based on a piecewise Lyapunov function. Then, a set of switching T–S fuzzy observers are constructed to realize FDI under DoS attacks. Besides, a switching variable method is introduced to address the asynchronous premise variables problem caused by the event-triggered mechanism. Finally, simulation cases are given to demonstrate the validity, and merit of the proposed FDI scheme.

LMI‐based robust fault detection and isolation in linear stochastic systems

Here, a new fault detection and isolation (FDI) method based on linear optimisation is proposed for stochastic linear systems with unknown inputs. The stochastic system is discrete and its state and output equations are dependent on unknown inputs. Both stochastic/deterministic unknown inputs (external disturbances) and measurement noise are considered in the dynamic model; therefore, a simple and complete formulation of the robust FDI scheme is presented for stochastic systems. According to the proposed method, first an observable and controllable subsystem is found such that it is independent of the effect of unknown inputs. Then an innovation filter is used for the FDI task. Sufficient conditions to guarantee the stability and observability of the new subsystem are presented based on linear matrix inequalities. Simulation results demonstrate the effectiveness and capability of the proposed method for FDI in stochastic systems with unknown inputs.

Fault detection and isolation of gas turbine engine using inversion-based and optimal state observers

This paper aims to design, develop and compare fault detection and isolation (FDI) schemes including inversion-based fault reconstruction and optimal state observers for a class of nonlinear system subject to concurrent faults and unknown disturbances that represents the nonlinear dynamic model of a gas turbine engine. Towards this end, for each fault, utilizing an existing coordinate transformation, the original system is transformed into a new form in which both observers are applied for fault diagnosis. The coordinate transformation comes from observability concept in differential geometry. The inversion-based observer is highly beneficial for straightforward detection and directly isolating the faults, and the state observer is optimal with respect to the magnitude of observer gain and convergence time. The mentioned approaches are implemented for FDI of a gas turbine model subject to compressor efficiency, compressor mass flow capacity, and actuator faults in addition to an unknown disturbance. The simulation results illustrate that the proposed FDI schemes are a promising tool for the gas turbine diagnostics.

Sensor Fault Detection and Isolation for Degrading Lithium-Ion Batteries in Electric Vehicles Using Parameter Estimation with Recursive Least Squares

With the increase in usage of electric vehicles (EVs), the demand for Lithium-ion (Li-ion) batteries is also on the rise. The battery management system (BMS) plays an important role in ensuring the safe and reliable operation of the battery in EVs. Sensor faults in the BMS can have significant negative effects on the system, hence it is important to diagnose these faults in real-time. Existing sensor fault detection and isolation (FDI) methods have not considered battery degradation. Degradation can affect the long-term performance of the battery and cause false fault detection. This paper presents a model-based sensor FDI scheme for a Li-ion cell undergoing degradation. The proposed scheme uses the recursive least squares (RLS) method to estimate the equivalent circuit model (ECM) parameters in real time. The estimated ECM parameters are put through weighted moving average (WMA) filters, and then cumulative sum control charts (CUSUM) are implemented to detect any significant deviation between unfiltered and filtered data, which would indicate a fault. The current and voltage faults are isolated based on the responsiveness of the parameters when each fault occurs. The proposed FDI scheme is then validated through conducting a series of experiments and simulations.

Neuro-Fuzzy Logic Based Robust Detection and Isolation of Economizer and Air Pre-Heater Faults in Steam Boiler

The technique of Fault Detection and Isolation (FDI) of Economizer and Air-preheater of Boiler using Neuro-fuzzy system is presented in this paper. FDI using model based approach and intelligent methods are the current trend applied in space industries, process industries and power plants. Intelligent methods like Fuzzy, Neural network and Neuro-fuzzy methods are simpler for modeling and faster for detection and isolation of faults. Here the water wall type steam boiler which is used for producing steam in fertilizer industry is studied. The proposed scheme is detecting and isolating the faults and failures happens in the economizer and air preheater of boiler. The common faults are corrosion, erosion, cracking of boiler tubes at welding points, tube rupturing, scale formation in the tubes, external ash deposits etc. The inherent non-linearity of boiler makes Neuro-fuzzy logic method suitable for FDI for all possible faults. The detection of faults is carried out by computing residuals, which are the differences between real process output and estimated output by neuro-fuzzy logic model. These estimated outputs were obtained from the neuro-fuzzy logic model which is trained using real time data by Adaptive Neuro-fuzzy Inference Systems (ANFIS). The real time data of economizer and air-preheater of boiler is collected and used for residual generation. The residuals will be formed for two outputs which are playing important role. If the residual exceeds threshold value indicates various faults in the boiler components and makes the proposed FDI scheme robust against process and measurement noises, process modeling error, disturbances and all uncertainties etc. The threshold band is calculated using model error model method. To isolate the faults, the residuals are normalized and its magnitudes are compared with present fault severity limits. More the range of severity more will be the magnitude of faults in the boiler. FDI by neuro-fuzzy method is more advantages as it combines the advantage of artificial neural network and fuzzy logic methods. The neural networks are more adaptable and have more learning ability. Fuzzy systems are dealing with human reasoning and decision making. As a result the designed FDI scheme is more sensitive to faults and less sensitive to uncertainties and disturbances etc. makes the scheme robust. The required data and fault knowledge for the research work is collected from BHEL make 55 tons per hour capacity, water tube type boiler available in Madras fertilizer Limited (MFL), Chennai.

Fault diagnosis of nonlinear systems using recurrent neural networks

In this work, we propose a fault detection and isolation (FDI) methodology that enables diagnose of single, multiple and simultaneous actuator and sensor faults regardless of the utilized model structure. The basis of the proposed methodology is modelling and inversion of nonlinear systems using recurrent neural network (RNN)s. To this end, a bank of RNNs is used to estimate system inputs and/or outputs and build predictive models using the obtained estimates and an RNN as the plant model. Then a bank of residuals is generated in a way each residual is sensitive to a subset of faults and insensitive to the rest and as a result of this, a unique fault signature is obtained for each fault scenario. RNNs can be replaced by other machine learning techniques such as partial least square (PLS)s, random forest, etc. One of the advantages of the proposed methodology is that it does not require the existence of plant fault history or first principles models unlike other existing results in the literature. Also, it enables isolation of actuator and simultaneous actuator and sensor faults in highly interconnected systems. The effectiveness of the proposed FDI scheme is shown via simulation examples.

Fault diagnosis in grid‐connected PV NPC inverters by a model‐based and data processing combined approach

This study presents a fault detection and isolation (FDI) method for open-circuit faults (OCFs) in the switching devices of a grid-connected neutral-point-clamped (NPC) inverter for photovoltaic (PV) applications. The proposed methodology addresses the fault diagnosis problem by a combined model-based and data processing perspective to study single and simultaneous faults in the NPC inverter. For the model-based scheme, a bank of sliding-mode proportional-integral observers is suggested to estimate the fault profiles under an additive model. Thus, from the estimated fault profiles, and by performing a directional residual evaluation in a fixed reference frame, single and simultaneous fault scenarios can be isolated in the NPC inverter. However, for some fault classes, there is some ambiguity by just the model-based approach that is overcome by employing the average line currents to construct extra fault signatures. The proposed FDI scheme only requires the measurements of line currents and grid voltages in the diagnosis media and can isolate 6 x 2 single OCFs and 12 x 4 simultaneous OCFs in the order or lower than a fundamental period of the grid frequency. Our new FDI methodology is validated through experimental data from a practical PV system in a closed-loop grid-connected NPC inverter under single and simultaneous OCF conditions.

Asynchronous Fault Detection and Isolation for Markov Jump Systems With Actuator Failures Under Networked Environment

This paper is concerned with the asynchronous fault detection and isolation (FDI) strategy in finite frequency domain for Markov jump systems (MJSs) with actuator failures under networked environment. A set of binary-valued Bernoulli distributed sequences is introduced to describe the transmission and the scheduling of the sensor nodes. Then, an MJS directing by two Markov process and with multiple stochastic parameters is derived to characterize the whole system dynamics. Subsequently, by means of the stochastic $\mathcal {H}_{-}$ index in finite frequency domain and the geometric mapping approach, an asynchronous FDI scheme is investigated, in which the filters complete the FDI mission with only partial information of the measurements. Meanwhile, each FDI filter is only sensitive to one possible actuator fault and decoupled from others. Then the existence of the desired filters is ensured by some novel sufficient conditions. Finally, an application example is presented to show the effectiveness of the proposed theoretical results.

Switch fault diagnosis for boost DC–DC converters in photovoltaic MPPT systems by using high‐gain observers

Open- and short-circuit faults (OSCFs) in boost dc–dc converters for photovoltaic (PV) maximum power point trackers (MPPTs) imply an inefficiency after fault is triggered, which affect the security and profitability of PV projects. Hence, fault detection and isolation (FDI) techniques have become an important issue for PV technology. In this study, a model-based FDI technique is proposed to boost dc–dc converters in PV MPPT systems. As is well-known, major issues of model-based FDI techniques have always been parametric uncertainty and no-modelled dynamics. This study focuses on how to mitigate these shortcomings by applying a high-gain observer (HGO) as a residual generator. A striking feature of HGO's is that exponential stability is still guaranteed for bounded disturbances (or faults). As demonstrated in this study, under an integral control action in the closed-loop control system, OSCFs are characterised for ever-growing signals, enabling the suggested FDI scheme. Also, the FDI proposal is decoupled from PV current (irradiance changes) and load variations, thereby avoiding false alarms. Moreover, the output-injection gain and thresholds are selected such that the fault diagnosis is achieved in eight switching cycles, enabling a fast and reliable diagnosis. Experimental results are illustrated to validate the FDI scheme proposed in this study.

Application of Exergy-Based Fault Detection in a Gas-To-Liquids Process Plant.

Fault detection and isolation (FDI) within the petrochemical industries (PCIs) is largely dominated by statistical techniques. Although a signal-based technique centered on exergy flows within a process plant was proposed, it has only been applied to single process units. The exergy-based scheme has not yet been applied to process plants that feature at least a single recycle stream. The Tennessee Eastman process (TEP) is commonly used as an FDI benchmark process, but due to obfuscation, the TEP cannot be directly implemented in a commercial process simulator. Thus, application of FDI techniques to proprietary processes will require significant investment into the implementation of the FDI scheme. This is a key impediment to the wide-spread comparison of various FDI techniques to non-benchmark processes. In this paper, a gas-to-liquids (GTL) process model is developed in Aspen HYSYS®, and the model’s performance is validated. The exergy-based FDI technique is applied to the GTL process while the process is subjected to carefully selected faults. The selected faults aim to affect several process units, and specifically, the resultant recycle stream of the GTL process is considered. The results indicate that even though the exergy-based technique makes use of fixed thresholds, complete detection and isolation can be achieved for a list of common process faults. This is significant since it shows, for the first time, that the exergy-based FDI scheme can successfully be deployed in processes with recycle streams.