Fault Isolation Methodology Research Articles

Cyberattack and Machine-Induced Fault Detection and Isolation Methodologies for Cyber-Physical Systems

Cyberattack and Machine-Induced Fault Detection and Isolation Methodologies for Cyber-Physical Systems

Artificial neural network-based fault detection and isolation in a parabolic-trough solar plant with defocusing strategy

Fault detection is crucial for ensuring optimal operation and maintenance of solar plants. This paper proposes a methodology for fault detection and isolation using artificial neural networks (ANNs) in a model of a 50 MW parabolic-trough solar plant that employs a defocusing strategy. The proposed methodology focuses on detecting three different types of faults in the collector area, namely, faults in the optical efficiency, flow rate, and thermal losses. The methodology is divided into three steps. Firstly, a feedforward dynamic neural network that internally models the concentrated parameter model of the system is used to detect faults and output the fault type. Secondly, information on the defocusing mechanism is added to the inputs of the neural network. Finally, the range of faults considered is adjusted based on the neural networks’ ability to detect each fault size and its impact on the plant’s outlet temperature. The accuracy of fault detection is evaluated through several simulations, and the proposed methodology shows promising results. The accuracy of fault detection is found to be 71.72%, 83.96%, and 90.62% for the first, second, and third approaches, respectively. The proposed methodology based on ANNs has the potential to improve the operational efficiency and reduce maintenance costs of solar plants.

Fault detection and isolation of multi-variate time series data using spectral weighted graph auto-encoders

Fault or anomaly detection is one of the key problems faced by the chemical process industry for achieving safe and reliable operation. In this study, a novel methodology, spectral weighted graph autoencoder (SWGAE) is proposed, wherein, the problem of anomaly detection is addressed with the help of graphs. The proposed approach entails the following key steps. Firstly, constructing a spectral weighted graph, where each time step of a process variable in the multivariate time series dataset is modelled as a node in an appropriately tuned moving window. Subsequently, we propose to monitor the weights of the edges between two nodes that make a connection. The faulty instances are identified based on the discrepancy in the weight pattern compared to normal operating data. To this end, once the weights are determined, they are fed to the auto-encoder network, where reconstruction loss is calculated, and faults are identified if the reconstruction loss exceeds a threshold. Further, to make the proposed approach comprehensive, a fault isolation methodology is also proposed to identify the faulty nodes once the faulty variables are identified. The proposed approach is validated using Tennessee-Eastman benchmark data and pressurized heavy water nuclear reactor real-time plant data. The results indicate that the SWGAE method, when compared to the other state-of-the-art methods, yielded more accurate results in correctly detecting faulty nodes and isolating them.

A Dynamic Principal Component Analysis and Fréchet-Distance-Based Algorithm for Fault Detection and Isolation in Industrial Processes

Fault Detection and Isolation (FDI) methodology focuses on maintaining safe and reliable operating conditions within industrial practices which is of crucial importance for the profitability of technologies. In this work, the development of an FDI algorithm based on the use of dynamic principal component analysis (DPCA) and the Fréchet distance δdF metric is explored. The three-tank benchmark problem is studied and utilized to demonstrate the performance of the FDI method for six fault types. A DPCA transformation for the system was established, and fault detection was conducted based on the Q statistic. Fault isolation is also of critical importance for proper intervention to mitigate fault effects. To identify the type of detected faults, the fault responses within the PC subspace were analyzed using the δdF metric. The use of the Fréchet distance metric for the isolation of faults combined with DPCA for feature extraction is a novel technique to the best of the authors’ knowledge that provides a robust computational tool with low computational cost for FDI purposes that fits well into the Industry 4.0 framework.The robustness and sensitivity of the method was validated for a wide variety of signal-to-noise ratio (SNR) conditions, with findings indicating a possible average false and missed alarm rate of 0.1 and a macro-averaged F-score above 0.8 in all cases.

Physics-based modeling and information-theoretic sensor and settings selection for tool wear detection in precision machining

Precision machining of metals is an energy intensive process with applications and impacts across the manufacturing industry. The energy efficiency, product yield, and maintenance of the precision machine require a digital twin that can assist with prognostics and health management. Here, a physics-based model is developed and validated against face milling data, and then used for the timely and precise inference of machining faults that cannot be measured directly. Computer numerical control (CNC) measurements of power and force are used through this physics-based machining model to predict deviations of the outputs of power consumption and cutting forces during normal operation. A model-based fault detection and isolation methodology is applied to determine the optimal (traditional and available) sensor suite and the test settings (admissible input values) that improve the inference of tool wear in face milling. The optimal sensor suite and input test settings are obtained by solving a mixed integer non-linear program that optimizes information-theoretic metrics relevant to the detection and isolation of tool wear from steady-state or transient machining measurements. Dynamic time warping and k—NN classification are then used to validate the robustness of the optimal design for fault detection test design, including the optimal sensor suite.

An integrated methodology for system-level early fault detection and isolation

Fault diagnosis is an indispensable technique to ensure the high-performance operation of a mechanical system during its life-cycle. Existing research works mainly limits in the diagnosis of single component or some certain components of interest. The systematic investigation of fault diagnosis for a full system is rare, making it inefficient to implement the method developed in the practice of a complete engineering system. In this paper, a system-level fault diagnosis methodology is proposed based on fault behaviour analysis, optimal sensor placement and intelligent data analytics for multiple fault detection and isolation in a complex machine system. A dynamical model of a mechanical system is firstly constructed using Bond graph, and the response characteristics of observable parameters under different faults are derived by analysing the functional relationships of system variables. A set partitioning theory-based sensor placement approach is then presented for designing a condition monitoring system with a quantity-optimal set of sensors for a desired performance of fault isolatability. Two multivariate statistic measures, i.e. Hotelling’s T2 and Q are calculated from the system operation parameters as the indices to detect the potential faults. The abnormal parameters are separated by constructing a contribution plot once a fault is reported. The separated abnormal parameters are then input to a Bayesian network model, and the real root cause of the abnormity is isolated by blending the observations with expert knowledge of diagnosis. The diesel engine lubrication system, which involves three common domains: mechanical, hydraulic and thermodynamic processes, is taken as an example to show the implementation and performance of proposed approach. This approach can be used to design a system-level fault diagnosis scheme that including various tasks such as fault behaviour analysis, sensor placement, data collection, data processing, information fusion in order to achieve an accurate fault isolation ultimately.

A fault model extension for a geometric fault isolation methodology to detect leakages and sensor faults on engine test beds

Analytical model-based methods for fault diagnosis on engine test bench systems remain the subject of intensive research. In some cases, such methods are also being used productively even though their application is mainly limited to the isolation of sensor faults. This paper presents a method for isolating process faults—and leakages in particular—that does not require any direct changes to the analytical models used for residual generation. Based on a geometric isolator, this method generates relations between fault causes and fault symptoms through the definition of fault models using latent variables. The application of the methodology is first explained in detail using a simple example. Taking data from a simulated engine test bench, we then show how different causes of faults, including sensor faults and leakages at different positions, can be correctly isolated.

Observer-based robust actuator fault isolation and identification for microsatellite attitude control systems

Purpose The purpose of this paper is to accomplish robust actuator fault isolation and identification for microsatellite attitude control systems (ACSs) subject to a series of space disturbance torques and gyro drifts. Design/methodology/approach For the satellite attitude dynamics with Lipschitz constraint, a multi-objective nonlinear unknown input observer (NUIO) is explored to accomplish robust actuator fault isolation based on a synthesis of Hinf techniques and regional pole assignment technique. Subsequently, a novel disturbance-decoupling learning observer (D2LO) is proposed to identify the isolated actuator fault accurately. Additionally, the design of the NUIO and the D2LO are reformulated into convex optimization problems involving linear matrix inequalities (LMIs), which can be readily solved using standard LMI tools. Findings The simulation studies on a microsatellite example are performed to prove the effectiveness and applicability of the proposed robust actuator fault isolation and identification methodologies. Practical implications This research includes implications for the enhancement of reliability and safety of on-orbit microsatellites. Originality/value This study proposes novel NUIO-based robust fault isolation and D2LO-based robust fault identification methodologies for spacecraft ACSs subject to a series of space disturbance torques and gyro drifts.

Integration of Hidden Markov Modelling and Bayesian Network for fault detection and prediction of complex engineered systems

This paper presents a methodology for fault detection, fault prediction and fault isolation based on the integration of hidden Markov modelling (HMM) and Bayesian networks (BN). This addresses the nonlinear and non-Gaussian data characteristics to support fault detection and prediction, within an explainable hybrid framework that captures causality in a complex engineered system. The proposed methodology is based on the analysis of the pattern of similarity in the log-likelihood (LL) sequences against the training data for the mixture of Gaussians HMM (MoG-HMM). The BN model identifies the root cause of detected/predicted faults, using the information propagated from the HMM model as empirical evidence. The feasibility and effectiveness of the presented approach are discussed in conjunction with the application to a real-world case study of an automotive exhaust gas Aftertreatment system. The paper details the implementation of the methodology to this case study, with data available from real-world usage of the system. The results show that the proposed methodology identifies the fault faster and attributes the fault to the correct root cause. While the proposed methodology is illustrated with an automotive case study, its applicability is much wider to the fault detection and prediction problem of any similar complex engineered system.

Optical Beam-Based Defect Localization Methodologies for Open and Short Failures in Micrometer-Scale 3-D TSV Interconnects

We report laser-based fault isolation methodologies for the localization of open and short failures in $1 \times 5\,\,\mu \text{m}$ via-last through-silicon via (TSV) structures for 3-D system-on-chip (SoC) integration. Due to the photosensitive TSV interconnect capacitance, observation of the photocapacitance response enables nondestructive localization of metallization ruptures. A light-induced capacitance alteration (LICA) measurement is demonstrated on an open failed $1 \times 5\,\,\mu \text{m}$ TSV chain structure with a manufacturing defect. We validate our measurements with active voltage contrast imaging in the scanning electron microscope (SEM) and focused-ion beam (FIB) cross sectioning. Second, TSV dielectric defects generating leakage current between TSV and substrate (i.e., short defects) are detected and localized by sensing the laser-induced TSV photocurrent. An optical beam-induced current (OBIC) measurement is demonstrated on electrically overstressed TSV array structures whereby multiple TSVs are configured in a parallel arrangement. By applying a selective substrate removal process, we can expose the full TSV array and perform optical and tilted SEM inspection and reveal pinhole defects in the TSV liner. We further investigate the effect of breakdown energy on the pinhole formation, relate electrical measurements to SEM inspection, and confirm our results by FIB cross sectioning.

A Multi-Domain Diagnostics Approach for Solenoid Pumps Based on Discriminative Features

Accurate condition monitoring of industrial cyber-physical systems/components demands the use of reliable fault detection and isolation (FD&I) methodologies. Meta-heuristic algorithms for feature selection have good exploration capability for optimal discriminative feature selection for fault isolation/classification of which the Binary Particle swarm optimization (BPSO) is superior to its counterparts. This study presents a robust approach for vibration-based failure diagnostics of electromagnetic/solenoid pumps which employ a multi-domain feature extraction procedure (statistical time-domain and frequency-domain features, Mel frequency cepstral coefficients, and continuous wavelet coefficients) for capturing linear and nonlinear properties from the signals. Compared with other filter and wrapper methods for supervised feature selection, a hybrid filter-wrapper (Pearson’s correlation-BPSO ( $\rho $ -BPSO)) feature selection procedure is proposed for global search of optimal discriminative (uncorrelated) features for fault diagnosis with an RBF-kernel support vector machine (SVM*). Subsequently, a practical case study involving five VSC63A5 solenoid pumps at various operating/fault conditions is presented for validating the performance of the proposed approach. Results show the superior performance of the proposed hybrid filter-wrapper approach against filter-based and wrapper-based techniques for discriminative feature selection. Also, the proposed $\rho $ -BPSO-SVM* diagnostics model performance was compared with other standard fault isolation/classification methods.

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.

Modeling and fault diagnosis design for HVAC systems using recurrent neural networks

In this work, we develop models and a fault detection and isolation (FDI) methodology for heating, ventilation and air conditioning (HVAC) systems that utilizes recurrent neural networks (RNN). The FDI design does not require the existence of plant fault history, mechanistic models or a set of expert rules to isolate faults. The key is to first use plant data to build predictive models and input/output estimators, and then embed them within FDI filters. A distributed FDI framework is designed consisting of local FDI (LFDI) schemes that communicate with each other for improved FDI. The distributed FDI framework enables diagnosis of multiple faults in different components of the HVAC system when a fault in one of the control components directly affects the other subsystems. The effectiveness of the proposed FDI scheme is shown via simulation examples on a simulation test bed, as well as using real data. The simulations revealed superior performance of the proposed FDI methodology over FDI approaches using subspace based models for both simulation and real data cases.

Fault diagnosis and prognosis of a hydro-motor drive system using priority valve

In this article, an improved fault isolation in the model-based fault detection and isolation (FDI) method is presented using parallely computed bond graph models. All component faults in a system may not be uniquely isolable. However, some faulty parameters’ subspaces may be identified. One of the possible solutions as proposed in this article is to estimate parameters from the actual performance of the plant assuming a single fault hypothesis. Then incorporating the estimated values, all the parallel models are run on a single-core processor and their responses are compared with the healthy plant to identify the actual fault. In this respect, a typical hydro-motor drive system is considered for the FDI analysis, where a stable source of flow is supplied through a priority flow divider valve to two hydro-motors. A methodology for parametric fault isolation under single fault assumption with minimum measurements is discussed. Such method is capable to estimate the remaining useful life (RUL) of the faulty components of a system. The proposed methodology used for identifying the fault and estimating the RUL is simple enough to adopt it in industrial practices.

Exploiting Bayesian networks for fault isolation: A diagnostic case study of diesel fuel injection system

Fault isolation is known to be a challenging problem in machinery troubleshooting. It is not only because the isolation of multiple faults contains considerable number of uncertainties due to the strong correlation and coupling between different faults, but often massive prior knowledge is needed as well. This paper presents a Bayesian network-based approach for fault isolation in the presence of the uncertainties. Various faults and symptoms are parameterized using state variables, or the so-called nodes in Bayesian networks (BNs). Probabilistically causality between a fault and a symptom and its quantization are described respectively by a directed edge and conditional probability. To reduce the qualitative and quantitative knowledge needed, particular considerations are given to the simplification of Bayesian networks structures and conditional probability expressions using rough sets and noisy-OR/MAX model, respectively. By adopting the simplified approach, symptoms under multiple-fault are decoupled into the ones under every single fault, while the quantity of the conditional probabilities is simplified into the linear form of the faults quantity. Prior knowledge needed in Bayesian network-based diagnostic model is reduced significantly, which decreases the complexity in establishing and applying this diagnosis model. The computational efficiency is improved accordingly in the simplified BN model, after eliminating the redundant symptoms. The fault isolation methodology is illustrated through an example of diesel engine fuel injection system to verify the developed model.

A Dendritic Cell Immune System Inspired Scheme for Sensor Fault Detection and Isolation of Wind Turbines

In this paper, a fault detection and isolation (FDI) methodology based on an immune system (IS) inspired mechanism known as the dendritic cell algorithm (DCA) is developed and implemented. Our proposed DCA-based FDI methodology is then applied to a well-known wind turbine test model. The proposed DCA-based scheme performs both detection as well as isolation of sensor faults given dual sensor redundancy, unlike other works in the literature that only address the fault detection problem and rely on analytical redundancy approach for accomplishing the fault isolation task. A nonparametric statistical comparison test is also performed to compare the performance of the DCA-based FDI scheme with another IS-based scheme known as the negative selection algorithm. Through extensive simulation case study scenarios the capabilities and performance of our proposed methodologies have been fully demonstrated and justified.

Set-Membership-Based Fault Detection and Isolation for Robotic Assembly of Electrical Connectors

This paper addresses the fault detection and isolation (FDI) problem for robotic assembly of electrical connectors in the framework of set-membership. Both the fault-free and faulty cases of assembly are modeled by different switched linear models with known switching sequences, bounded parameters, and external disturbances. The locations of switching points of each model are assumed to be inside some areas but the accurate positions are not clear. Given current input/output data, the feasible parameter set of fault-free switched linear model is obtained by sequentially calculating an optimal ellipsoid. If the pair of data is not consistent with any possible submodel, a fault is then detected. The isolation of fault is realized by checking the consistency between the data sequence and each possible fault model one by one. The robustness of the proposed FDI algorithms is proved. The effectiveness of these algorithms is verified by the robotic assembly experiments of mating electrical connectors. Note to Practitioners —In modern robotic assembly tasks, the industrial robots often need to manipulate tiny objects with complex structure. Electrical connectors are a typical kind of these objects and widely used in many industrial fields. To avoid damaging the fragile connectors and accelerate the assembly process, it is required to promptly detect and isolate the certain assembly fault in real time so that the robot can immediately implement an error recovery procedure according to the identified fault. The proposed set-membership-based fault detection and isolation (FDI) methodology satisfies both the timing and fault-isolation requirements for this kind of robotic assembly task. In terms of the set-membership theory, no false alarm will occur if there are sufficient training data for the proposed method. In addition, it turns out that the proposed method can signal an alarm faster than conventional residual-based FDI method from plentiful experiments. Although only the robotic assembly of electrical connectors is investigated, our FDI method can also be applied in the assembly task of other small and complex parts. This is especially useful for increasing the productivity and promoting the automation level of electronic industries.

Data-driven fault detection, isolation and estimation of aircraft gas turbine engine actuator and sensors

Abstract In this work, a data-driven fault detection, isolation, and estimation (FDI&E) methodology is proposed and developed specifically for monitoring the aircraft gas turbine engine actuator and sensors. The proposed FDI&E filters are directly constructed by using only the available system I/O data at each operating point of the engine. The healthy gas turbine engine is stimulated by a sinusoidal input containing a limited number of frequencies. First, the associated system Markov parameters are estimated by using the FFT of the input and output signals to obtain the frequency response of the gas turbine engine. These data are then used for direct design and realization of the fault detection, isolation and estimation filters. Our proposed scheme therefore does not require any a priori knowledge of the system linear model or its number of poles and zeros at each operating point. We have investigated the effects of the size of the frequency response data on the performance of our proposed schemes. We have shown through comprehensive case studies simulations that desirable fault detection, isolation and estimation performance metrics defined in terms of the confusion matrix criterion can be achieved by having access to only the frequency response of the system at only a limited number of frequencies.

Fault Diagnosis of Pneumatic Systems: Application of a Systematic Model-Based Methodology

Inclusion of real system data and a systematic model-based approach provides new opportunities in the field of fault diagnosis. The included work was conducted during the first phase of a larger multi-phase project that has the goal of developing methods for detection and diagnosis of faults in large, complex industrial fluid systems. This paper focuses on the application of a systematic model-based fault detection and isolation (FDI) methodology to a small-scale pneumatic test bench for proof of concept. FDI schemes were physically implemented on the test bench, leading to successful detection and isolation of injected faults using developed residuals.

Fault detection and isolation of high temperature proton exchange membrane fuel cell stack under the influence of degradation

Abstract This study proposes a data-drive impedance-based methodology for fault detection and isolation of low and high cathode stoichiometry, high CO concentration in the anode gas, high methanol vapour concentrations in the anode gas and low anode stoichiometry, for high temperature PEM fuel cells. The fault detection and isolation algorithm is based on an artificial neural network classifier, which uses three extracted features as input. Two of the proposed features are based on angles in the impedance spectrum, and are therefore relative to specific points, and shown to be independent of degradation, contrary to other available feature extraction methods in the literature. The experimental data is based on a 35 day experiment, where 2010 unique electrochemical impedance spectroscopy measurements were recorded. The test of the algorithm resulted in a good detectability of the faults, except for high methanol vapour concentration in the anode gas fault, which was found to be difficult to distinguish from a normal operational data. The achieved accuracy for faults related to CO pollution, anode- and cathode stoichiometry is 100% success rate. Overall global accuracy on the test data is 94.6%.