Improved Fault Detection Research Articles

Obstacle-Aware Intelligent Fault Detection Scheme for Industrial Wireless Sensor Networks

Nowadays, the demand for the Industrial Internet of Things (IIoT) technology has increased immensely in various fields, such as the agriculture industry, smart mines, smart factories, healthcare industry, etc. Industrial wireless sensor networks (IWSNs) act as a backbone of any IIoT system by forming a network of heterogeneous sensors. In IWSNs, the fault occurrence probability is more due to continuous exposure to harsh environments. Furthermore, the presence of obstacles creates an extra burden in fault detection. In this article, the proposed scheme presents an optimal fault diagnostic point selection mechanism that significantly reduces fault detection latency and energy consumption. Multiple intelligent mobile fault detectors effectively avoid obstacles during the fault detection process that significantly improves fault detection accuracy (FDA). Extensive simulations and a testbed experiment demonstrate the effectiveness of the proposed scheme in terms of FDA, false alarm rate, false positive rate, F1-score, energy consumption, and network lifetime.

Automatic determination of optimal fault detection filter

Optimal detection filters can greatly enhance fault detection performance, but designing these filters requires fault data which is difficult to obtain in practice. This paper proposes a scheme that automatically determines the optimal detection filter from a filter bank online without using fault data. The method can improve fault detection rate and accelerate detection speed. In order to reduce the false alarm rate, a method of threshold setting is introduced based on kernel density estimation. Implementation issues concerning filter bank design and online decision rule are also discussed. The method is validated in a numerical example and Tennessee Eastman process, and its performance is compared to those of other state-of-the-art methods.

나주 통합 직류 마이크로그리드의 보호를 위한 개선된 고장검출 방안의 비교 분석

A renewable energy source that can reduce carbon emissions is a DC microgrid, a new type of bidirectional power grid, which is mostly connected through a power converter. Unlike AC, DC power source does not cause zero point crossing, so it is not easy to interrupt fault currents, and since fault detection methods and grounding systems are different, the development of appropriate protection technology is required. As a part of multi-circuit DC microgrid protection and cooperation research, this article is an improved fault detection schemes based on DWT targeting the field integrated DC microgrid. The purpose of this article is to compare novel fault detection schemes for pole to ground fault and pole to pole fault using the PSCAD platform and MATLAB tool. The field integration DC microgrid is modeled using the PSCAD platform. In addition, for integrated model protection, the proposed DWT-based fault detection schemes are implemented using the PSCAD platform and MATLAB tools. Finally, the applicability of the proposed improved scheme is described by comparing it through various faults analysis.

Fault Detection Using Backward Propagating Traveling Waves for Bipolar LCC-HVDC Lines

The line commutated converter (LCC)-high voltage direct current (HVDC) transmission lines may have various complementary protection algorithms based on derivatives of line parameters or differential line currents. The DC line fault detection based on distance relaying, traveling wave (TW), artificial neural network, fuzzy logic, and wavelet are a few of the popular schemes. However, the TW-based technique has been reported as one of the fastest techniques to detect and locate faults. The conventional TW techniques face limitations in detecting high resistance DC line faults. Therefore, this paper introduces an improved fault detection, classification, and location algorithm based on backward propagating TWs and fault classifier indices. The proposed algorithm is tested to detect, classify, and locate the faults under different system conditions such as pole-to-ground, pole-to-pole, and rectifier and inverter sides’ external faults. A bipolar LCC-HVDC transmission system of 900 km length is utilized to simulate the various fault conditions. The simulation results indicate fast, accurate, and reliable detection of faults. This scheme uses only single-end data measurement. The simulation study was performed for various fault locations (0–900 km) and transition resistances (0–150 Ω).

Application of Differential Magnetic Field Measurement (DMFM method) in winding fault detection of AC rotating machines as part of expert monitoring systems

Stator and rotor winding damages in rotating machines are result of electrical, mechanical, and thermal stress. Online magnetic field monitoring via permanently installed measuring coils inside air gap is a well-established methodology which enables winding fault detection. The paper deals with a new method for detection of stator and rotor winding inter-turn short circuits of synchronous machines and slip rings induction machines, as well as rupture of rotor bars and cage ring of induction machines. The method novelty is based on differential measurement of magnetic field by using two serial connected measuring coils. They are installed on the places (stator or rotor teeth) in the machine which have, by absolute value, equal magnetic vector potential. The distance between the measuring coils is n·tp, where tp is a pole pitch, and n = 1, 2, 3, 4,... is a multiple of the pole pitch. Measuring the coil-induced voltage enables us to detect stator and rotor winding faults, which means that measured voltage is approximately zero without fault and increases in the presence of fault. Analysis of the measuring signal allows us to detect and locate fault. With this new method it is possible with high sensitivity to determine winding fault, which enables more reliable fault detection. For example, in comparison with the motor current signature analysis method (the most widely used method for motor faults detection), this new method gives 200 times higher sensitivity to fault occurrence. Also, by using the DMFM method, faults can be detected in the time domain and there is no need for spectral or other complex signal analysis. This is very important because the measuring equipment used for machine fault detection can be simple and more economically acceptable. The DMFM method enables fault detection for even small machines with small expense in a very effective way. The only downside of the DMFM method is the fact that machine should be disassembled in order to install measuring coils. This problem is solved during the machine overhaul or during the manufacturing of the machine, when sensors can be easily implemented in the machine. For machines with large air gap, measuring coils can be installed without a machine disassembly. For the purpose of the method testing, numerous finite-element (FE) simulations on the 2- and 3-D machine models have been carried out to verify the method. Powerful numerical tools generate realistic results with properly selected starting and boundary conditions. By FEM models, actual machines with embedded measuring coils where created and simulated. The voltage induced inside the measuring coils is calculated for different machine states, load point and with and without a fault (broken rotor bar or inter-turn short circuit). Also, this method was experimentally validated via series of laboratory tests performed on the real electric machines specially designed for fault study (broken rotor bars, broken ring and inter-turn short circuits in a stator and rotor winding). Additionally, this method is applied on more than 20 real machines in industry. Due to the large amount of measured data, in this paper, it will be presented only one measurement performed on an induction motor on which we have detected one broken rotor bar. The thickness of the measuring coil designed in the printed circuit board technique is 0.3 mm. The number of turns is from 3 to 10. This new method and performed FEM calculations together with the experimental measurements improve fault detection portfolio knowledge that can be used in monitoring and diagnostics of rotating machines. Furthermore, this patent-pending method is already implemented in three innovative products placed on market (expert monitoring systems), so this method is fully confirmed in practice.

Automatic geologic fault identification from seismic data using 2.5D channel attention U-net

Fault identification plays a vital role in geologic structure interpretation, reservoir characterization, and reservoir evaluation. The traditional process for fault identification is label intensive. Deep learning-based automatic fault detection from seismic data has attracted extensive attention in recent years. However, using a 2D neural network (i.e., a single seismic data slice) leads to the loss of correlation among seismic slices, and using a 3D neural network (i.e., a 3D seismic data cube) increases the workload of fault labeling and the difficulty of training. To overcome the drawbacks of 2D and 3D neural networks, we have introduced a channel attention mechanism in the original U-net architecture. The new model, which is referred to as the 2.5D channel attention U-net (2.5D CAU-net), takes four adjacent seismic slices as inputs instead of the entire 3D seismic data cube. The efficacy of 2.5D CAU-net for fault detection is demonstrated using publicly available synthetic seismic data sets and real seismic field data sets. We explored the influence of cropping the original seismic data into various sizes on fault identification. Experimental results find that the 2.5D CAU-net can effectively use the correlation information among adjacent seismic slices to improve fault detection performance. For different seismic data cropping strategies, results indicate that the more extensive size cropping method allows the network to obtain more contextual information and more complete fault features, improving the efficacy of fault picking. However, the cropping approach with a larger size leads to a smaller number of labeled examples. When the amount of training data is not large enough, the larger size cropping approach tends to lead to model overfitting, which will decrease the performance of the fault recognition, especially in a 3D neural network. Overall, 2.5D CAU-net can improve the efficiency of fault recognition with less annotation effort and computational resources.

Detecting Wind Turbine Blade Icing with a Multiscale Long Short-Term Memory Network

Blade icing is one of the main problems of wind turbines installed in cold climate regions, resulting in increasing power generation loss and maintenance costs. Traditional blade icing detection methods greatly rely on dedicated sensors, such as vibration and acoustic emission sensors, which require additional installation costs and even reduce reliability due to the degradation and failures of these sensors. To deal with this challenge, this paper aims to develop a cost-effective detection system based on the existing operation data collected from the supervisory control and data acquisition (SCADA) systems which are already equipped in large-scale wind turbines. Considering that SCADA data is essentially a multivariate time series with inherent non-stationary and multiscale temporal characteristics, a new wavelet-based multiscale long short-term memory network (WaveletLSTM) approach is proposed for wind turbine blade icing detection. The proposed method incorporates wavelet-based multiscale learning into the traditional LSTM architecture and can simultaneously learn global and local temporal features of multivariate SCADA signals, which improves fault detection ability. A real case study has shown that our proposed WaveletLSTM method achieved better detection performance than the existing methods.

An Energy Aware Intelligent Fault Detection Scheme for IoT-Enabled WSNs

Recent years have seen an explosion in the demand for the Internet of Things (IoT). IoT makes any physical object smart by providing sensing capability. The physical objects are embedded with sensors that form a network of sensors. However, sensors are vulnerable to faults due to energy depletion, software failures, and hardware failures. The existing fault detection schemes put huge computational overhead on the battery-limited and low computational capacity sensor nodes that are subject to the premature death of the sensor nodes. Also, they suffer from poor fault detection accuracy and huge false alarm rate that significantly reduce the overall performance of the networks. In this paper, an energy-aware intelligent fault detection scheme is proposed for IoT-enabled wireless sensor networks that significantly improve fault detection accuracy and reduce false alarm rate. A novel 3-Tier hard fault detection mechanism is used for detecting hardware unit faults of the sensor nodes. Furthermore, an optimized deep learning mechanism is used for various soft fault detection that prevents premature death of sensor nodes. The paper mathematically analyses the proposed scheme in terms of energy consumption, time complexity, and message complexity. Extensive simulations show the enhanced performance of the proposed scheme compared with the state-of-the-art algorithms in terms of fault detection accuracy, false alarm rate, false-positive rate, energy consumption, and network lifetime.

Unified Impedance-Based Relaying Scheme for the Protection of Hybrid AC/DC Microgrid

Even though the implementation of hybrid AC/DC microgrid is increasing, their protection schemes face multiple challenges such as inconsistent fault current supply from DGs, difficulty in discriminating internal/ external faults and missing of universal protection scheme for both AC and DC distribution networks. In this regard, a unified fault detection and localization scheme is proposed for hybrid AC/DC microgrid. By measuring the impedance at system frequency for AC circuit and at a specific pre-inserted frequency for DC network, the suggested technique achieves proper discrimination between internal faults and external events. Several fault scenarios such as internal/external faults, single/double line faults with varying fault location and fault resistance have been investigated on both AC and DC circuits by modeling hybrid AC/DC microgrid in PSCAD/EMTDC environment. The results reveal the effectiveness of the proposed algorithm in discriminating internal faults with external events and also in estimating accurate fault location even under noisy environment. Finally, a comparative evaluation of the proposed unified AC/DC protection scheme with other individual AC/DC protection schemes shows its superiority in combining both the AC and DC schemes together into a single relay, having an improved fault detection time and an increased fault localization accuracy.

Challenges of DC Microgrid Protection: a Comprehensive Study

DC Microgrids have become a widespread phrase among scholars all around the world in recent decades. DC Microgrid is penetrating deeper into our conventional grid system, thanks to technology advancements and widely available DC renewable power sources and local DC demand. However, the DC microgrid's protection remains a major issue that must be addressed for it to be feasible and reliable. Another issue is the lack of established norms and regulations in DC Microgrid protection, which adds to the complexity of DC Microgrid applications. The current review study focuses on identifying numerous defects that can occur in the DC Microgrid, difficulties that are commonly experienced during its implementation, protective appliances used in the DC Microgrid system, and the number of protections schemes available in the literature. A literature review was also carried out to discover suitable grounding methods and protective devices needed to ensure that the grid-connected DC Microgrid maintains a constant power flow. Finally, recommendations are offered in support of additional research and testing to develop improved fault detection algorithms with faster fault clearance times.

Improving Fault Detection in Industrial Processes by Event-Driven Data Acquisition

Data acquisition in process industries usually takes place at each sampling. The disadvantage is that a considerable amount of data without new information about the state of the process is continuously transmitted and processed. This negatively affects the communication system and computational power, which is more critical nowadays given the number of variables measured, even in seconds. One solution concerns the event-driven paradigm, in which only relevant data according to a pre-defined criterion is forwarded for further processing. This work investigated the event-based threshold and delta methods in the context of fault detection. The data transmission rate was also analyzed. The well-know Tennessee Eastman problem (TEP) was used as a case study. The fault detection system was based on PCA (principal component analysis), which is widely used for this purpose in this benchmark. The results were compared with the commonly used time-based approach, for a fixed false alarm rate. The threshold rule provided similar results, but with much less data. For the delta rule, significant MDR (missed detection rate) gains of up to 74% were obtained for five of the six hard-to-detect faults, and of up to 69%, for two of the three very hard-to-detect faults. MDR values very close to zero were reached for two of the three intermediate detection faults and two of the hard-to-detect faults. The detection time was also evaluated. In this regard, considerably lower values were obtained for all intermediate detection faults, three of the hard-to-detect faults and all very hard-to-detect faults. In short, the delta method was able to improve fault detection performance, especially for hard-to-detect faults, with a considerably lower data transmission rate, around 20% on average. Event-driven data acquisition can be very attractive for process industries.

Graph Attention Network-Based Fault Detection for UAVs With Multivariant Time Series Flight Data

Timely detection and isolation of faults is crucial to the survival of unmanned aerial vehicle (UAV) systems and to avoid threats to humans and the environment. This paper focused on automatically and accurately identifying the faults with data-driven methods as traditional algorithms may rely on the knowledge of underlying system dynamics. The analytical redundancies are provided with the proposed masked spatial GAT with GRU (masked-SGAT-GRU) model. The model extracts pair-wise dependencies between variables from different components of UAVs explicitly, which is of vital importance in improving fault detection (FD) performance. With the finely-optimized model, residuals are generated from measurements and predictions, which are smoothed with the exponential weighted moving average (EWMA) method to generate the proper fault thresholds. Real flight data under two flight modes are collected for model training and fault injection. The robustness and effectiveness of the model are demonstrated in FD with four types of faults compared with the commonly used data-driven methods.

An Improved Fault Detection Method for Overhead Transmission Lines Based on Differential Tunnel Magnetoresistive Sensor Array Approach

Overhead transmission lines play a key role in ensuring power system security and reliability in this current smart society. The overhead transmission line operates in a very complex terrain thereby making it vulnerable to various kinds of faults. Most transmission line faults lead to interruption in power supplies and therefore the need for a fast repair to restore the system to its normal state. A fast, timely, and accurate fault detection technique will ensure speedy restoration of the system thereby reducing outage time. In this article, an enhanced transmission lines’ fault detection approach is presented. This scheme deployed a highly sensitive, low cost, and energy-efficient differential sensor to detect flux density variation measured along transmission lines. The fault detection algorithm is developed for the detection of faults in transmission lines. The development is implemented on a model transmission line and tested for various fault scenarios. Scaled-up laboratory experiments were also conducted to measure magnetic flux density and fault identification to verify the validity of the proposed technique as well as estimate the amount of current produced when a fault occurred. From the simulated and measured current produced during a fault, the proposed technique yielded an estimated error of 1.38%, while the CT and a commercial current probe gave errors of 10.99% and 17.68%, respectively.

An Improved Fault Detection Method Based on HSMM and PCA for Multi-Mode Process Monitoring: Application to the Tennessee Eastman Process Model

An Improved Fault Detection Method Based on HSMM and PCA for Multi-Mode Process Monitoring: Application to the Tennessee Eastman Process Model

Attitude estimation and control based on modified unscented Kalman filter for gyro-less satellite with faulty sensors

A modified unscented Kalman filter is presented to estimate the quaternion parameters as well as the angular velocities of a rigid gyro-less satellite under faulty sensor conditions. The task is carried out using the Sun sensor and magnetometers as attitude sensors with bounded noise and unknown fault(s). Following the presentation of the satellite attitude dynamics and filtering formulations, a new fault detection and isolation algorithm is proposed. The latter is based on a modified unscented Kalman filter structure for improved fault detection, sensor isolation, and attitude control (AC). A Backtracking Search Algorithm (BSA) is also used to design and optimize the PID controller gains, as well as to optimize sensor installation orientation for residual signal decoupling. In this regard, the paper presents and proves a theory that describes how the proposed optimization process for sensor installation can analytically decouple the faulty orientation signal from the healthy ones. A comparison of attitude and angular velocity estimation approaches using the standard Kalman, extended Kalman, and a proposed modified unscented Kalman filter is also provided. The results show that the proposed filter performs significantly better in closed-loop AC systems and copes adequately with sensor faults.

Improved fault detection and control allocation for hypersonic re‐entry vehicle subject to intermittent fault and disturbance

AbstractThis study investigates the nonlinear fault detection and control allocation of a hypersonic re‐entry vehicle with intermittent faults and disturbances. The uncertain external disturbances in the inner loop system are processed on the basis of the studied intermittent fault mode. A set of residuals is generated by sliding time windows, and two hypothesis tests based on the residual mean are proposed to detect the appearance and disappearance of faults. An augmented observer is used to estimate the faults subject to the ‐gain disturbance rejection constraint. A nonlinear backstepping fault‐tolerant control is designed to generate the desired control torque and make the output attitude track the given signal. An optimization control allocation algorithm distributes the desired torque to aerodynamic surfaces and reaction control system jets. The stability of the schemes is analyzed by Lyapunov and linear matrix inequality theories. Numerical simulation and rapid prototyping results are presented to demonstrate the validity of the proposed methods.

An Integrated Cost-Aware Dual Monitoring Framework for SMPS Switching Device Diagnosis

The ability of a switch-mode AC/DC power supply to shrink supplies is a benefit and a requirement for most electronic devices with limited space. Major failures in switch-mode power supply (SMPS) during adverse working conditions are subject to mostly the switching devices and capacitors. For effective condition monitoring of the SMPS, dual (or multiple) sensing provides a more reliable standpoint against the traditional single sensing techniques as it provides a more comprehensive paradigm for accurate condition monitoring. This study proposes an integrated approach to SMPS condition monitoring by exploiting statistically extracted features from current and voltage signals for system fault diagnosis based on electrical stress. Following a correlation-based feature selection approach, salient features were utilized for improved fault detection and isolation (FDI) using ML-based classifiers. Diagnostic results by the classifiers reveal that the random forest and gradient boosting classifiers are highly reliable but computationally expensive when compared with the others while the decision tree was quite cost-efficient with reliable diagnostic results. The proposed framework is effectively applicable for use in diagnosing the switching devices and classification at different states.

Analysis and assessment of weighted combinatorial criterion for test suite reduction

AbstractSoftware plays an important role in modern society. New software features have to be completed and tested rapidly due to business and user needs and goals. To ensure the quality of modified software components, new test cases must be generated and included in the current test pool. Furthermore, test pool size often grows too large to test all cases. A considerably large test pool typically consumes an exorbitant quantity of time, leading to inefficient regression testing. Test suite reduction is often used to solve this problem by removing redundant test cases. Thus, time and resource constraints make it necessary to minimize the test suite. That is, test pool size should be efficiently reduced, while the remaining test cases should be adequate to provide the same coverage as the pool. The main purpose of this paper is to propose four weighted combinatorial algorithms and a three‐objective binary integer linear programming (ILP) model to improve fault detection effectiveness. We first consider both the control flow and data flow as our testing criteria and combine them by using a weighted means with four existing test suite reduction algorithms. A genetic algorithm is used to find the best combination of weighting factors to assign to the two testing criteria. Experiments based on real subject programs are presented. Experimental results demonstrate that 77.5% of our proposed weighted combinatorial algorithms have an even or better performance in suite size reduction, 83.75% of our approaches perform even or better in fault detection effectiveness, and 82.5% of our approaches have even or better effectiveness in fault‐to‐test ratio. For the three‐objective binary ILP model, test suite size is significantly reduced without any accompanying loss in fault detection ability.

Data driven case study of a wind turbine main-bearing failure

This paper presents a data driven case study of two outer-race spalling faults in double-row spherical roller main-bearings, with the purpose of identifying key features and relevant measurements associated with this failure mode in wind turbine main-bearings. Supervisory data is analysed for one fault case and vibration data for the other. The aim of this work is to inform practitioners and assist in improving fault detection systems for this component.

Identification based fault detection: Residual selection and optimal filter

In this work, an identification based fault detection method is proposed. The idea is to identify a dynamic process model from test data and to generate residuals using the identified model for fault detection. The method intends to improve fault detection performance while taking disturbance and model error into account. To this end, a fault detection performance index is introduced in a statistical framework. Then it is shown that the output error residual is more suitable for fault detection than the prediction error residual. Further an optimal detection filter maximizing the performance index is developed. Practical issues for implementing the detection filter are also addressed. Finally, the proposed method is illustrated through a numerical example and Tennessee Eastman process.