Showing papers on "Fault detection and isolation published in 2015"

A Survey of Fault Diagnosis and Fault-Tolerant Techniques—Part II: Fault Diagnosis With Knowledge-Based and Hybrid/Active Approaches

Abstract: This is the second-part paper of the survey on fault diagnosis and fault-tolerant techniques, where fault diagnosis methods and applications are overviewed, respectively, from the knowledge-based and hybrid/active viewpoints. With the aid of the first-part survey paper, the second-part review paper completes a whole overview on fault diagnosis techniques and their applications. Comments on the advantages and constraints of various diagnosis techniques, including model-based, signal-based, knowledge-based, and hybrid/active diagnosis techniques, are also given. An overlook on the future development of fault diagnosis is presented.

Improved PLS Focused on Key-Performance-Indicator-Related Fault Diagnosis

Abstract: Standard partial least squares (PLS) serves as a powerful tool for key performance indicator (KPI) monitoring in large-scale process industry for last two decades. However, the standard approach and its recent modifications still encounter some problems for fault diagnosis related to KPI of the underlying process. To cope with these difficulties, an improved PLS (IPLS) approach is presented in this paper. IPLS is able to decompose the measurable process variables into the KPI-related and unrelated parts, respectively. Based on it, the corresponding test statistics are designed to offer meaningful fault diagnosis information and thus, the corresponding maintenance actions can be further taken to ensure the desired performance of the systems. In order to demonstrate the effectiveness of the proposed approach, a numerical example and Tennessee Eastman (TE) benchmark process are respectively utilized. It can be seen that the proposed approach shows satisfactory results not only for diagnosing KPI-related faults but also for its high fault detection rate.

Advances in Electrical Machine, Power Electronic, and Drive Condition Monitoring and Fault Detection: State of the Art

Abstract: Recently, research concerning electrical machines and drives condition monitoring and fault diagnosis has experienced extraordinarily dynamic activity. The increasing importance of these energy conversion devices and their widespread use in uncountable applications have motivated significant research efforts. This paper presents an analysis of the state of the art in this field. The analyzed contributions were published in most relevant journals and magazines or presented in either specific conferences in the area or more broadly scoped events.

A Comprehensive Review of Catastrophic Faults in PV Arrays: Types, Detection, and Mitigation Techniques

Abstract: Three major catastrophic failures in photovoltaic (PV) arrays are ground faults, line-to-line faults, and arc faults. Although there have not been many such failures, recent fire events on April 5, 2009, in Bakersfield, CA, USA, and on April 16, 2011, in Mount Holly, NC, USA, suggest the need for improvements in present fault detection and mitigation techniques, as well as amendments to existing codes and standards to avoid such accidents. This review investigates the effect of faults on the operation of PV arrays and identifies limitations to existing detection and mitigation methods. A survey of state-of-the-art fault detection and mitigation technologies and commercially available products is also presented.

Performance Monitoring for Vehicle Suspension System via Fuzzy Positivistic C-Means Clustering Based on Accelerometer Measurements

Abstract: This paper focuses on fault detection and isolation for vehicle suspension systems. The proposed method is divided into three steps: 1) confirming the number of clusters based on principal component analysis; 2) detecting faults by fuzzy positivistic C-means clustering and fault lines; and 3) isolating the root causes for faults by utilizing the Fisher discriminant analysis technique. Different from other schemes, this method only needs measurements of accelerometers that are fixed on the four corners of a vehicle suspension. Besides, different spring attenuation coefficients are regarded as a special failure instead of several ones. A full vehicle benchmark is applied to demonstrate the effectiveness of the method.

Graph-Based Semi-supervised Learning for Fault Detection and Classification in Solar Photovoltaic Arrays

Abstract: Fault detection in solar photovoltaic (PV) arrays is an essential task for increasing reliability and safety in PV systems. Because of PV's nonlinear characteristics, a variety of faults may be difficult to detect by conventional protection devices, leading to safety issues and fire hazards in PV fields. To fill this protection gap, machine learning techniques have been proposed for fault detection based on measurements, such as PV array voltage, current, irradiance, and temperature. However, existing solutions usually use supervised learning models, which are trained by numerous labeled data (known as fault types) and therefore, have drawbacks: 1) the labeled PV data are difficult or expensive to obtain, 2) the trained model is not easy to update, and 3) the model is difficult to visualize. To solve these issues, this paper proposes a graph-based semi-supervised learning model only using a few labeled training data that are normalized for better visualization. The proposed model not only detects the fault, but also further identifies the possible fault type in order to expedite system recovery. Once the model is built, it can learn PV systems autonomously over time as weather changes. Both simulation and experimental results show the effective fault detection and classification of the proposed method.

Fault Detection for T-S Fuzzy Time-Delay Systems: Delta Operator and Input-Output Methods

Abstract: This paper focuses on the problem of fault detection for Takagi–Sugeno fuzzy systems with time-varying delays via delta operator approach. By designing a filter to generate a residual signal, the fault detection problem addressed in this paper can be converted into a filtering problem. The time-varying delay is approximated by the two-term approximation method. Fuzzy augmented fault detection system is constructed in $\delta $ -domain, and a threshold function is given. By applying the scaled small gain theorem and choosing a Lyapunov–Krasovskii functional in $\delta $ -domain, a sufficient condition of asymptotic stability with a prescribed $H_\infty $ disturbance attenuation level is derived for the proposed fault detection system. Then, a solvability condition for the designed fault detection filter is established, with which the desired filter can be obtained by solving a convex optimization problem. Finally, an example is given to demonstrate the feasibility and effectiveness of the proposed method.

Detection of Localized Bearing Faults in Induction Machines by Spectral Kurtosis and Envelope Analysis of Stator Current

Abstract: Early detection of faults in electrical machines, particularly in induction motors, has become necessary and critical in reducing costs by avoiding unexpected and unnecessary maintenance and outages in industrial applications. Additionally, most of these faults are due to problems in bearings. Thus, in this paper, experimental bearing fault detection of a three-phase induction motor is performed by analyzing the squared envelope spectrum of the stator current. Spectral kurtosis-based algorithms, namely, the fast kurtogram and the wavelet kurtogram, are also applied to improve the envelope analysis. Experimental tests are performed, considering outer bearing faults at different stages, and the results are promising.

Induction Machine Bearing Fault Detection by Means of Statistical Processing of the Stray Flux Measurement

Abstract: Rolling bearing faults are generally slowly progressive; therefore, the development of an effective diagnostic technique could be worth detecting such faults in their incipient phase and preventing complete failure of the motor. The methods proposed in the literature for this purpose are mainly based on measuring and analyzing vibration and current. Here, a novel technique based on the stray flux measurement in different positions around the electrical machine is proposed. The main advantages of this method are due to the simplicity and the flexibility of the custom flux probe with its amplification and filtering stage. The flux probe can be easily positioned on the machines and adapted to a wide range of power levels. This paper also reports an extensive survey on the stray-flux-based fault detection methods for induction motors, prior to introducing a novel sensor/diagnostic scheme.

Fault Detection and Localization Method for Modular Multilevel Converters

Abstract: The modular multilevel converter (MMC) is attractive for medium- or high-power applications because of the advantages of its high modularity, availability, and high power quality. However, reliability is one of the most important issues for MMCs which are made of large number of power electronic submodules (SMs). This paper proposed an effective fault detection and localization method for MMCs. An MMC fault can be detected by comparing the measured state variables and the estimated state variables with a Kalman filter. The fault localization is based on the failure characteristics of the SM in the MMC. The proposed method can be implemented with less computational intensity and complexity, even in case that multiple SM faults occur in a short time interval. The proposed method is not only implemented in simulations with professional tool PSCAD/EMTDC, but also verified with a down-scale MMC prototype controlled by a real-time digital signal controller in the laboratory. The results confirm the effectiveness of the proposed method.

An Entropy-Based Network Anomaly Detection Method

Abstract: Data mining is an interdisciplinary subfield of computer science involving methods at the intersection of artificial intelligence, machine learning and statistics. One of the data mining tasks is anomaly detection which is the analysis of large quantities of data to identify items, events or observations which do not conform to an expected pattern. Anomaly detection is applicable in a variety of domains, e.g., fraud detection, fault detection, system health monitoring but this article focuses on application of anomaly detection in the field of network intrusion detection.The main goal of the article is to prove that an entropy-based approach is suitable to detect modern botnet-like malware based on anomalous patterns in network. This aim is achieved by realization of the following points: (i) preparation of a concept of original entropy-based network anomaly detection method, (ii) implementation of the method, (iii) preparation of original dataset, (iv) evaluation of the method.

Online Fault Detection in PV Systems

Abstract: This paper presents the development of a practical fault detection approach in photovoltaic (PV) systems, intended for online implementation. The approach was developed and validated using field measurements from a Canadian PV system. It has a fairly low degree of complexity, but achieves a high fault detection rate and is able to successfully cope with abnormalities present in real-life measurements. The fault detection is based on the comparison between the measured and model prediction results of the ac power production. The model estimates the ac power production using solar irradiance and PV panel temperature measurements. Prior to model development, a data analysis procedure was used to identify values not representative of a normal PV system operation. The original 10-min measurements were averaged over 1h, and both datasets were used for modeling. In order to better represent the PV system performance at different sunlight levels, models for different irradiance ranges were developed. The results reveal that the models based on hourly averages are more accurate than the models using 10-min measurements, and the models for different irradiance intervals lead to a fault detection rate greater than 90%. The PV system performance ratio (PR) was used to keep track of the system's long-term performance.

Vibration Spectrum Imaging: A Novel Bearing Fault Classification Approach

Abstract: Incipient fault detection in low signal-to-noise ratio (SNR) conditions requires robust features for accurate condition-based machine health monitoring Accurate fault classification is positively linked to the quality of features of the faults Therefore, there is a need to enhance the quality of the features before classification This paper presents a novel vibration spectrum imaging (VSI) feature enhancement procedure for low SNR conditions An artificial neural network (ANN) has been used as a fault classifier using these enhanced features of the faults The normalized amplitudes of spectral contents of the quasi-stationary time vibration signals are transformed into spectral images A 2-D averaging filter and binary image conversion, with appropriate threshold selection, are used to filter and enhance the images for the training and testing of the ANN classifier The proposed novel VSI augments and provides the visual representation of the characteristic vibration spectral features in an image form This provides enhanced spectral images for ANN training and thus leads to a highly robust fault classifier

An SVM-Based Solution for Fault Detection in Wind Turbines

Abstract: Research into fault diagnosis in machines with a wide range of variable loads and speeds, such as wind turbines, is of great industrial interest. Analysis of the power signals emitted by wind turbines for the diagnosis of mechanical faults in their mechanical transmission chain is insufficient. A successful diagnosis requires the inclusion of accelerometers to evaluate vibrations. This work presents a multi-sensory system for fault diagnosis in wind turbines, combined with a data-mining solution for the classification of the operational state of the turbine. The selected sensors are accelerometers, in which vibration signals are processed using angular resampling techniques and electrical, torque and speed measurements. Support vector machines (SVMs) are selected for the classification task, including two traditional and two promising new kernels. This multi-sensory system has been validated on a test-bed that simulates the real conditions of wind turbines with two fault typologies: misalignment and imbalance. Comparison of SVM performance with the results of artificial neural networks (ANNs) shows that linear kernel SVM outperforms other kernels and ANNs in terms of accuracy, training and tuning times. The suitability and superior performance of linear SVM is also experimentally analyzed, to conclude that this data acquisition technique generates linearly separable datasets.

Fault detection and classification in electrical power transmission system using artificial neural network

Abstract: This paper focuses on the detection and classification of the faults on electrical power transmission line using artificial neural networks. The three phase currents and voltages of one end are taken as inputs in the proposed scheme. The feed forward neural network along with back propagation algorithm has been employed for detection and classification of the fault for analysis of each of the three phases involved in the process. A detailed analysis with varying number of hidden layers has been performed to validate the choice of the neural network. The simulation results concluded that the present method based on the neural network is efficient in detecting and classifying the faults on transmission lines with satisfactory performances. The different faults are simulated with different parameters to check the versatility of the method. The proposed method can be extended to the Distribution network of the Power System. The various simulations and analysis of signals is done in the MATLAB® environment.

Speed and Current Sensor Fault Detection and Isolation Technique for Induction Motor Drive Using Axes Transformation

Abstract: This paper presents a new technique for fault detection and isolation to make the traditional vector-controlled induction motor (IM) drive fault tolerant against current and speed sensor failure. The proposed current estimation uses d- and q-axes currents and is independent of the switching states of the three-leg inverter. While the technique introduces a new concept of vector rotation to generate potential estimates of the currents, speed is estimated by one of the available model reference adaptive system (MRAS) based formulations. A logic-based decision mechanism selects the right estimate and reconfigures the system (by rejecting the signal from the faulty sensors). Such algorithm is suitable for different drives, including electric vehicles to avoid complete shutdown of the system, in case of sensor failure. The proposed method is extensively simulated in MATLAB/SIMULINK and experimentally validated through a dSPACE-1104-based laboratory prototype.

Application of higher order spectral features and support vector machines for bearing faults classification

Abstract: Condition monitoring and fault diagnosis of rolling element bearings timely and accurately are very important to ensure the reliability of rotating machinery This paper presents a novel pattern classification approach for bearings diagnostics, which combines the higher order spectra analysis features and support vector machine classifier The use of non-linear features motivated by the higher order spectra has been reported to be a promising approach to analyze the non-linear and non-Gaussian characteristics of the mechanical vibration signals The vibration bi-spectrum (third order spectrum) patterns are extracted as the feature vectors presenting different bearing faults The extracted bi-spectrum features are subjected to principal component analysis for dimensionality reduction These principal components were fed to support vector machine to distinguish four kinds of bearing faults covering different levels of severity for each fault type, which were measured in the experimental test bench running under different working conditions In order to find the optimal parameters for the multi-class support vector machine model, a grid-search method in combination with 10-fold cross-validation has been used Based on the correct classification of bearing patterns in the test set, in each fold the performance measures are computed The average of these performance measures is computed to report the overall performance of the support vector machine classifier In addition, in fault detection problems, the performance of a detection algorithm usually depends on the trade-off between robustness and sensitivity The sensitivity and robustness of the proposed method are explored by running a series of experiments A receiver operating characteristic (ROC) curve made the results more convincing The results indicated that the proposed method can reliably identify different fault patterns of rolling element bearings based on vibration signals

High-Impedance Fault Detection in the Distribution Network Using the Time-Frequency-Based Algorithm

Abstract: A new high-impedance fault (HIF) detection method using time-frequency analysis for feature extraction is proposed. A pattern classifier is trained whose feature set consists of current waveform energy and normalized joint time–frequency moments. The proposed method shows high efficacy in all of the detection criteria defined in this paper. The method is verified using real-world data, acquired from HIF tests on three different materials (concrete, grass, and tree branch) and under two different conditions (wet and dry). Several nonfault events, which often confuse HIF detection systems, were simulated, such as capacitor switching, transformer inrush current, nonlinear loads, and power-electronics sources. A new set of criteria for fault detection is proposed. Using these criteria, the proposed method is evaluated and its performance is compared with the existing methods. These criteria are accuracy, dependability, security, safety, sensibility, cost, objectivity, completeness, and speed. The proposed method is compared with the existing methods, and it is shown to be more reliable and efficient than its existing counterparts. The effect of choice of the pattern classifier on method efficacy is also investigated.

Quality-Related Fault Detection Approach Based on Orthogonal Signal Correction and Modified PLS

Abstract: Partial least squares (PLS) is an efficient tool widely used in multivariate statistical process monitoring. Since standard PLS performs oblique projection to input space $\mathbf{X}$ , it has limitations in distinguishing quality-related and quality-unrelated faults. Several postprocessing modifications of PLS, such as total projection to latent structures (T-PLS), have been proposed to solve this issue. Further studies have found that these modifications fail to reduce false alarm rates (FARs) of quality-unrelated faults when fault amplitude increases. To cope with this problem, this paper proposes an enhanced quality-related fault detection approach based on orthogonal signal correction (OSC) and modified-PLS (M-PLS). The proposed approach removes variation orthogonal to output space $\mathbf{Y}$ from input space $\mathbf{X}$ before PLS modeling, and further decomposes $\mathbf{X}$ into two orthogonal subspaces in which quality-related and quality-unrelated statistical indicators are designed separately. Compared with T-PLS, the proposed approach has a more robust performance and a lower computational load. Two case studies, including a numerical example and the Tennessee Eastman (TE) process, show the effeteness of the proposed approach.

Fault detection analysis using data mining techniques for a cluster of smart office buildings

Abstract: An energy fault detection analysis was performed for a cluster of buildings.Pattern recognition techniques coupled with outliers detection methods were used.Anomalies are detected during early morning, lunch break, and end of working hours.The methodology can be easily implemented in BEMS. There is an increasing need for automated fault detection tools in buildings. The total energy request in buildings can be significantly reduced by detecting abnormal consumption effectively. Numerous models are used to tackle this problem but either they are very complex and mostly applicable to components level, or they cannot be adopted for different buildings and equipment. In this study a simplified approach to automatically detect anomalies in building energy consumption based on actual recorded data of active electrical power for lighting and total active electrical power of a cluster of eight buildings is presented. The proposed methodology uses statistical pattern recognition techniques and artificial neural ensembling networks coupled with outliers detection methods for fault detection. The results show the usefulness of this data analysis approach in automatic fault detection by reducing the number of false anomalies. The method allows to identify patterns of faults occurring in a cluster of bindings; in this way the energy consumption can be further optimized also through the building management staff by informing occupants of their energy usage and educating them to be proactive in their energy consumption. Finally, in the context of smart buildings, the common detected outliers in the cluster of buildings demonstrate that the management of a smart district can be operated with the whole buildings cluster approach.

Open-Switch Fault Detection Method of a Back-to-Back Converter Using NPC Topology for Wind Turbine Systems

Abstract: In wind turbine generation (WTG) systems, a back-to-back converter with a neutral-point-clamped (NPC) topology is widely used because this topology has more advantages than a conventional two-level topology, particularly when operating at high power. There are 12 switches in the NPC topology. An open-switch fault in the NPC rectifier of the back-to-back converter leads to the distortion of the input current and torque vibration in the system. Additionally, an open-switch fault in the NPC inverter of the back-to-back converter causes the distortion of the output current. Furthermore, the WTG system can break down in the worst case scenario. To improve the reliability of WTG systems, an open-switch fault detection method for back-to-back converters using the NPC topology is required. This study analyzes effects of inner and outer open-switch faults of the NPC rectifier and inverter and describes a novel open-switch fault detection method for all possible open-switch faults in the back-to-back converter.

Photovoltaic Systems Reliability Improvement by Real-Time FPGA-Based Switch Failure Diagnosis and Fault-Tolerant DC–DC Converter

Abstract: The increased penetration of photovoltaic (PV) systems in different applications with critical loads such as in medical applications, industrial control systems, and telecommunications has highlighted pressing needs to address reliability and service continuity. Recently, distributed maximum power point tracking architectures, based on dc–dc converters, are being used increasingly in PV systems. Nevertheless, dc–dc converters are one of the important failure sources in a PV system. Since the semiconductor switches are one of the most critical elements in these converters, a fast switch fault detection method (FDM) is a mandatory step to guarantee the service continuity of these systems. This paper proposes a very fast FDM based on the shape of the inductor current associated to fault-tolerant (FT) operation for boost converter used in PV systems. By implementing fault diagnosis and reconfiguration strategies on a single field-programmable gate array target, both types of switch failure (open- and short-circuit faults) can be detected, identified and handled in real time. The FDM uses the signal provided by the current sensor dedicated to the control of the system. Consequently, no additional sensor is required. The proposed FT topology is based on a redundant switch. The results of hardware-in-the-loop and experimental tests, which all confirm the excellent performances of the proposed approach, are presented and discussed. The obtained results show that a switch fault can be detected in less than one switching period, typically around 100 ms in medium power applications, by the proposed FDM.

Detection and Location of High Impedance Faults in Multiconductor Overhead Distribution Lines Using Power Line Communication Devices

Abstract: An effective power system protection scheme has to be able to detect and locate all occurring faults corresponding to low and high impedance values. The latter category poses the greatest challenge for the protection schemes due to the low values of the related fault current. This paper extends previous work by the authors on the subject, aiming to achieve detection and location of high impedance faults (HIFs) in multiconductor overhead distribution networks utilizing power line communication (PLC) devices. Fault detection is proposed to be performed by a PLC device installed at the starting point of the monitored line and by using differences to the values of metrics related to input impedance at frequencies utilized by narrowband systems. Moreover, fault location can be derived by a response to impulse injection procedure utilized by all installed PLC devices along the line. The method is evaluated and validated in various simulation test cases concerning its ability to effectively detect and locate HIFs.

Impact of HVDC Transmission System Topology on Multiterminal DC Network Faults

Abstract: This paper compares how a dc fault affects a multiterminal dc (MTdc) network depending on the HVDC transmission system topology. To this end, a six-step methodology is proposed for the selection of the necessary dc fault protection measures. The network consists of four voltage-source converters converters radially connected. The converters natural fault response to a dc fault for the different topologies is studied using dynamic simulation models. For clearing of the dc faults, four different dc breaker technologies are compared based on their fault interruption time, together with a current direction fault detection method. If necessary, the converters are reinforced with limiting reactors to decrease the peak value and rate of rise of the fault currents providing sufficient time for the breakers to isolate the fault without interrupting the MTdc network operation. The study shows that the symmetric monopolar topology is least affected by dc contingencies. Considering bipolar topologies, the bipolar with metallic return exhibits better fault response compared to the one with ground return. Topologies with ground or metallic return require full semiconductor or hybrid breakers with reactors to successfully isolate a dc fault.

Anomaly detection based on sensor data in petroleum industry applications.

Abstract: Anomaly detection is the problem of finding patterns in data that do not conform to an a priori expected behavior. This is related to the problem in which some samples are distant, in terms of a given metric, from the rest of the dataset, where these anomalous samples are indicated as outliers. Anomaly detection has recently attracted the attention of the research community, because of its relevance in real-world applications, like intrusion detection, fraud detection, fault detection and system health monitoring, among many others. Anomalies themselves can have a positive or negative nature, depending on their context and interpretation. However, in either case, it is important for decision makers to be able to detect them in order to take appropriate actions. The petroleum industry is one of the application contexts where these problems are present. The correct detection of such types of unusual information empowers the decision maker with the capacity to act on the system in order to correctly avoid, correct or react to the situations associated with them. In that application context, heavy extraction machines for pumping and generation operations, like turbomachines, are intensively monitored by hundreds of sensors each that send measurements with a high frequency for damage prevention. In this paper, we propose a combination of yet another segmentation algorithm (YASA), a novel fast and high quality segmentation algorithm, with a one-class support vector machine approach for efficient anomaly detection in turbomachines. The proposal is meant for dealing with the aforementioned task and to cope with the lack of labeled training data. As a result, we perform a series of empirical studies comparing our approach to other methods applied to benchmark problems and a real-life application related to oil platform turbomachinery anomaly detection.

Implementation of an Evolving Fuzzy Model (eFuMo) in a Monitoring System for a Waste-Water Treatment Process

Abstract: Increasing demands on effluent quality and loads call for an improved control, monitoring, and fault detection of waste-water treatment plants (WWTPs). Improved control and optimization of WWTP lead to increased pollutant removal, a reduced need for chemicals as well as energy savings. An important step toward the optimal functioning of a WWTP is to minimize the influence of sensor faults on the control quality. To achieve this, a fault-detection system should be implemented. In this paper, the idea of using an evolving method as a base for the fault-detection/monitoring system is tested. The system is based on the evolving fuzzy model method. This method allows us to model the nonlinear relations between the variables with the Takagi–Sugeno fuzzy model. The method uses basic evolving mechanisms to add and remove clusters and the adaptation mechanism to adapt the clusters’ and local models’ parameters. The proposed fault-detection system is tested on measured data from a real WWTP. The results indicate the potential improvement of the WWTP's control during a sensor malfunction.