Different Types Of Faults Research Articles

Neural Network-Based Active Fault-Tolerant Control Design for Unmanned Helicopter with Additive Faults

A novel adaptive neural network-based fault-tolerant control scheme is proposed for six degree-of-freedom nonlinear helicopter dynamic. The proposed approach can detect and mitigate actuators and sensors’ faults in real time. An adaptive observer-based on neural network (NN) and extended Kalman filter (EKF) is designed, which incorporates the helicopter’s dynamic model to detect faults in the actuators and navigation sensors. Based on the detected faults, an active fault-tolerant controller, including three loops of dynamic inversion, is designed to compensate for the occurred faults in real time. The simulation results showed that the proposed approach is able to detect and mitigate different types of faults on the helicopter actuators, and the helicopter tracks the desired trajectory without any interruption.

A Deep Learninag based Non-invasive and Real-Time Fault Detection System for 3-Phase Induction Motors

Induction motor plays a major role in industry. Despite of its strong structure, induction motors are often prone to faults. There are different types of faults that occurs in the induction motor such as bearing faults, winding faults, etc. Thus motors in major applications require continuous and effective monitoring. In this paper, a stand-alone and non-invasive condition monitoring system that can monitor the condition of 3-phase induction motor using motor current signatures with aid of deep learning (DL) approaches. The proposed system extracts the features using non-invasive current sensors it further samples the features using an analog to digital converter (ADC) and organizes the data acquired from ADC using Raspberry-pi microcomputer. The current data acquired from induction motor is used to train and test the DL models including Multilayer Perceptron (MLP), Long Short-term Memory (LSTM), and One-Dimensional Convolutional Neural Networks (1DCNN). The comparative analysis is demonstrated and the LSTM model as best fault classifier among all with accuracy up to 100%. Finally, the real-time testing of the device showed that the developed system can effectively monitor the conditions of motor using non-invasive current sensors.

Advances in Fault Diagnostics and Post‐Fault Operation of Electrical Drives

Advances in Fault Diagnostics and Post‐Fault Operation of Electrical Drives

Rolling Element Bearing Fault Diagnosis for Complex Equipment based on MFMD and BP Neural Network

A new fault feature extraction method for rolling element bearing is put forward in this paper based on modified Fourier mode decomposition (MFMD) and multi-scale permutation entropy, and the fault pattern recognition is studied by combining BP neural network. First, introduce frequency band entropy (FBE) to optimize the boundary frequency search and effective modal component selection of Fourier decomposition. Then, use MFMD to adaptively decompose the original vibration signal to several Fourier intrinsic mode functions (FIMFs) and select effective FIMFs. Next, use multi-scale permutation entropy to quantify the fault features. Finally, input the fault feature vector into the BP neural network for fault diagnosis model training and testing. The method proposed in this paper is applied to the rolling element bearing simulation data and the public bearing fault test data set of Case Western Reserve University to verify the feasibility of the method. The results show that the method proposed in this paper has a high identification accuracy for different types of faults, reaching over 98%. The feasibility and superiority of the rolling element bearing fault diagnosis method based on MFMD and BP neural network are verified, and technical support is provided for the health state assessment of rolling element bearings.

An Efficient Neural Network-Based Method for Diagnosing Faults of PV Array

This paper presents an efficient neural network-based method for fault diagnosis in photovoltaic arrays. The proposed method was elaborated on three main steps: the data-feeding step, the fault-modeling step, and the decision step. The first step consists of feeding the real meteorological and electrical data to the neural networks, namely solar irradiance, panel temperature, photovoltaic-current, and photovoltaic-voltage. The second step consists of modeling a healthy mode of operation and five additional faulty operational modes; the modeling process is carried out using two networks of artificial neural networks. From this step, six classes are obtained, where each class corresponds to a predefined model, namely, the faultless scenario and five faulty scenarios. The third step involves the diagnosis decision about the system’s state. Based on the results from the above step, two probabilistic neural networks will classify each generated data according to the six classes. The obtained results show that the developed method can effectively detect different types of faults and classify them. Besides, this method still achieves high performances even in the presence of noises. It provides a diagnosis even in the presence of data injected at reduced real-time, which proves its robustness.

Multivariate nuisance alarm management in chemical processes

Alarm systems are of vital importance in the safe and effective functioning of industrial plants, yet they frequently suffer from too many nuisance alarms (alarm overloading). It is necessary to intelligently enhance existing alarm systems and supply accurate information for the operators. Nowadays, process variables are more correlated and complicated. This correlation structure can be used as a basis to manage alarms efficiently. Hence, multivariate approaches are more appropriate. Designing a system aimed at reducing nuisance alarms is an essential phase to guarantee the reliable operation of a plant. Due to the definition of alarm limits, the problem of false alarms is inevitable in multivariate methods. In this paper, the conventional Principal Component Analysis (PCA) is applied to extract the sum of squared prediction error (SPE) known as the Q statistic and the Hotelling T2 statistic. These statistics are used separately as alarm indicators where their control limits are duly modified. Consequently, for each statistic, a nonlinear combination of alarm duration and alarm deviation, is additionally exploited as a new requirement to activate an alarm or not. The resulting new index is fed to a delay timer with a defined parameter n. The implementation of this technique resulted in a significant reduction in the severity of alarm overloading. Historical data collected from the cement rotary kiln operating under healthy conditions are employed to adequately build the PCA model and extract the proposed alarming indexes. Then, various testing data sets, covering different types of faults occurring in the cement process, are used to assess the performance of the developed method. In comparison with the conventional PCA technique, alarms are better managed nd almost nuisance alarms are suppressed. The proposed method is more robust to false alarms and more sensitive to fault detection.

Adaptive Neuro Fuzzy Interface System Based Short Circuit Fault Diagnoses in a Three Phase Induction Motor Drive System

Induction motors are commonly used in different industrial, housing and medical applications, such as air conditioners, transportation, elevators and others. These motors are rugged, reliable and economical. Generally, the reliable operation of the motor and its drive system is very important in industry so that any expected fault must be detected immediately by a monitoring system. This paper reviews and simulates a three-phase induction motor model and different types of faults that may happen in the drive system. Due to short circuit severity on the overall drive system, this study focuses only on short circuit faults, e.g., when any Insulated Gate Bipolar Transistor (IGBT) is shorted out and DC link capacitor is shorted out. Also, an Adaptive Neuro Fuzzy Interface System (ANFIS) algorithm is programmed to detect different types of faults and classify them. The ANFIS system takes two parameters as input from the motor: the first one is the load torque whereas the second one is the stator current. Whereas, the previously published works analyze only the motor's stator current. MATLAB is used to train the ANFIS system and also to analyze samples. Additionally, LTSpice is used simulate the drive system. The ANFIS system shows very high accuracy in short circuit fault detection and classification.

Statistical Analysis of Electric Power Distribution Grid Outages

Power systems in general supply consumers with electrical energy as economically and reliably as possible. Reliable electric power systems serve customer loads without interruptions in supply voltage. Electric power generation facilities must produce enough power to meet customer demand. Electrical energy produced and delivered to customers through generation, transmission and distribution systems, constitutes one of the largest consumers markets the world over. The benefits of electric power systems are integrated into the much faster modern life in such extent that it is impossible to imagine the society without the electrical energy. The rapid growth of electric power distribution grids over the past few decades has resulted in a large increment in the number of grid lines in operation and their total length. These grid lines are exposed to faults as a result of lightning, short circuits, faulty equipment, mis-operation, human errors, overload, and aging among others. A fault implies any abnormal condition which causes a reduction in the basic insulation strength between phase conductors or phase conductors and earth, or any earthed screens surrounding the conductors. In this paper, different types of faults that affected the electric power distribution grid of selected operational districts of Electricity Company of Ghana (ECG) in the Western region of Ghana was analyzed and the results presented. Outages due to bad weather and load shedding contributed significantly to the unplanned outages that occurred in the medium voltage (MV) distribution grid. Blown fuse and loose contact faults were the major contributor to unplanned outages in the low voltage (LV) electric power distribution grid.

Statistical Analysis of Electric Power Distribution Grid Outages

Power systems in general supply consumers with electrical energy as economically and reliably as possible. Reliable electric power systems serve customer loads without interruptions in supply voltage. Electric power generation facilities must produce enough power to meet customer demand. Electrical energy produced and delivered to customers through generation, transmission and distribution systems, constitutes one of the largest consumers markets the world over. The benefits of electric power systems are integrated into the much faster modern life in such extent that it is impossible to imagine the society without the electrical energy. The rapid growth of electric power distribution grids over the past few decades has resulted in a large increment in the number of grid lines in operation and their total length. These grid lines are exposed to faults as a result of lightning, short circuits, faulty equipment, mis-operation, human errors, overload, and aging among others. A fault implies any abnormal condition which causes a reduction in the basic insulation strength between phase conductors or phase conductors and earth, or any earthed screens surrounding the conductors. In this paper, different types of faults that affected the electric power distribution grid of selected operational districts of Electricity Company of Ghana (ECG) in the Western region of Ghana was analyzed and the results presented. Outages due to bad weather and load shedding contributed significantly to the unplanned outages that occurred in the medium voltage (MV) distribution grid. Blown fuse and loose contact faults were the major contributor to unplanned outages in the low voltage (LV) electric power distribution grid.

Classification Of Faults During Integration Of Hybrid System To Microgrid Using Neuro-Fuzzy Technique

To improve microgrid efficiency, detecting the fault as soon as possible is imperative. Taking into account the above problem a peculiar technique has been implemented in the analysis of this paper with a micro grid consisting of wind turbine (WT) and diesel generator for the classification of different types of faults. All Neuro-fuzzy (NF) fault disturbances are introduced by taking the input function data for accurate classification of different faults. One technically applicable 3-bus framework integrated with various forms of delivery generations that are considered for the purpose of security analysis and the simulation is done for the environment using MATLAB / SIMULINK. The fault classification is achieved by using Neuro Fuzzy. The results of the comparison are presented, showing the improved performance of Neuro Fuzzy (NF).

Magnetic Flux Analysis for the Condition Monitoring of Electric Machines: A Review

Magnetic flux analysis is a condition monitoring technique that is drawing the interest of many researchers and motor manufacturers. The great enhancements and reduction in the costs and dimensions of the required sensors, the development of advanced signal processing techniques that are suitable for flux data analysis, along with other inherent advantages provided by this technology, are relevant aspects that have allowed the proliferation of flux-based techniques. This article reviews the most recent scientific contributions related to the development and application of flux-based methods for the monitoring of rotating electric machines. Particularly, aspects related to the main sensors used to acquire magnetic flux signals as well as the leading signal processing and classification techniques are commented on. The discussion is focused on the diagnosis of different types of faults in the most common rotating electric machines used in industry, namely: squirrel cage induction machines, wound rotor induction machines, permanent magnet machines, and wound field synchronous machines. A critical insight of the techniques developed in the area is provided and several open challenges are also discussed.

Deep learning through LSTM classification and regression for transmission line fault detection, diagnosis and location in large-scale multi-machine power systems

Fault detection, diagnosis, identification and location are crucial to improve the sensitivity and reliability of system protection. This maintains power systems continuous proper operation; however, it is challenging in large-scale multi-machine power systems. This paper introduces three novel Deep Learning (DL) classification and regression models based on Deep Recurrent Neural Networks (DRNN) for Fault Region Identification (FRI), Fault Type Classification (FTC), and Fault Location Prediction (FLP). These novel models explore full transient data from pre- and post-fault cycles to make reliable decisions; whereas current and voltage signals are measured through Phasor Measurement Units (PMUs) at different terminals and used as input features to the DRNN models. Sequential Deep Learning (SDL) is employed herein through Long Short-Term Memory (LSTM) to model spatiotemporal sequences of high-dimensional multivariate features to achieve accurate classification and prediction results. The proposed algorithms were tested in a Two-Area Four-Machine Power System. Training and testing data are collected during transmission lines faults of different types introduced at various locations in different regions. The presented algorithms achieved superior detection, classification and location performance with high accuracy and robustness compared to contemporary techniques.

Multi‐upgradation software reliability growth model with dependency of faults under change point and imperfect debugging

AbstractWith the improvement of innovation, software developers consistently build up a new version of software by adding new features in the previously existing version of the software. In resent day's competitive market, the reliability and release time of multi‐upgradation software are very important issues to both: customers and developers. Many researchers have proposed various software reliability growth models (SRGMs) to improve the precision of assessing the reliability of programming. For reliability estimation, a detailed study is necessary to know the characteristics of different types of faults. It has been noticed that some faults present in software remove independently at the same time some faults remove some other faults. During upgradation, new faults generate due to many reasons. Though dependency of faults is an important issue, there is no such SRGM exist for multi‐release problem. Hence, an SRGM has been proposed for multi‐release problems here with the dependency of faults under the imperfect debugging phenomenon. The effect of change point has been incorporated in SRGM due to changes in testing strategy, changes in testing environments, and so forth, during up‐gradation. Based on datasets, it can be said the performance of the proposed model is better than some other existing models. Also, it is very important for software companies to know the optimal time of release a new version of software. As testing charges change with time, it cannot be constant throughout testing phase. Hence, a new random cost model has also been proposed for release time analysis in case of a multi‐release problem.

Uncorrelated discriminant graph embedding for fault classification

AbstractRecently, graph embedding methods have been successfully used in process monitoring. To improve the discriminant power, a novel supervised graph embedding method, called uncorrelated discriminant graph embedding (UDGE), is proposed. Different from the unsupervised design of locality preserving projection (LPP), UDGE utilizes both the local geometrical structure and label information to construct the similarity between different data points. The “local geometrical structure” means that each data point can be represented as a combination of its neighbours. Due to add the uncorrelated constraint, the extracted features of UDGE are statistically uncorrelated. Uncorrelated attributes are essential for dimension reduction since they contain minimum redundancy. The application of UDGE is evaluated on the Tennessee Eastman process (TEP) benchmark. Experimental results show UDGE can better separate different types of faults and provide more promising fault diagnosis performance. The code of UDGE is released in https://github.com/htz-ecust/Uncorrelated-Discriminant-Graph-Embedding-for-Fault-Classification.

An improved protection scheme of the ground electrode line based on two frequency components injection

The ground electrode line plays an important part in the high-voltage direct current (HVDC) systems. For the protection of the ground electrode line, the electrode line impedance supervision system is designed. However, the system has a dead zone problem. And the existing analysis on the protection scheme is not complete, because the model used in the analysis is not accurate. Therefore, an accurate analysis of the measured impedance under the normal operation and different types of faults was given in this paper, to find the property of the impedance. Based on the derivation, an improved protection scheme was proposed, which mainly consists of the injection of the signal of two frequency components to eliminate the dead zones of each other, and the frequency selection criterion. The dead zones can be eliminated greatly with the proposed scheme, and the proposed scheme has a high reliability and a strong ability to endure high transition resistance, which was verified by lots of simulation cases based on the PSCAD/EMTDC.

Performance of Low Voltage Ride-Through Protection Techniques for DFIG Wind Generator.(Dept.E)

Due to the increase of the number of wind turbines connected directly to the electric utility grid, new regulator codes have been issued that require Low-Voltage Ride-Through capability (LVRT) for wind turbines so that they can remain online and support the electric grid during low voltage fault events instead of direct tripping of the wind turbines. This LVRT capability will increase the stability of the network and reduce the need for load shedding after the fault clearance. Each utility has its own grid codes for this LVRT. There are many types of wind generators, and currently the Doubly Fed Induction Generator (DFIG) is the most popular type among the leading wind turbine (WT) manufacturers. In this paper five LVRT methods for protection of DFIG during LV events are implemented and compared. The five methods are Crowbar, DC Chopper, series dynamic resistances, and two hybrid methods that combine DC chopp er with Crowbar and DC chopper with series dynamic resistances respectively. These methods were tested under different types of fault including symmetrical and unsymmetrical faults and their performances were compared.

Fault Diagnosis for Power Cables Based on Convolutional Neural Network With Chaotic System and Discrete Wavelet Transform

In this paper, the discrete wavelet transform (DWT) and a chaotic system were combined with a convolutional neural network (CNN) and applied to the diagnosis of insulation faults in XLPE (cross-linked polyacetylene) power cables. First, four different types of insulation faults in power cables were constructed, including the normal state of the cable, the short outer semi-conducting layer, impurities in the insulation layer, and insulation layer damage, and a high-speed capture card (NI PXI-5105) was adopted to measure the partial discharge (PD) signal, which was then filtered through discrete wavelet transform. Then, based on the Lorenz chaotic system, a dynamic error scatter diagram was established as the feature of each fault state. Finally, the dynamic error scatter diagram was processed by CNN to recognize four different types of faults in the power cable. The test results show that the method proposed in this paper can quickly recognize the fault state of power cables and has excellent performance in terms of recognition accuracy, which reaches 97.5%. Therefore, the proposed method can effectively detect the fault signal changes of power cables and identify the fault state of power cables in real time.

Sequential Fault Detection and Classification in Chemical Process Using a Deep Convolutional Encoder-Decoder Architecture Based on System Dynamics

In this paper, we propose a high-level spatiotemporal feature extraction based on deep convolutional bidirectional encoder-decoder representation network with gated recurrent unit (GRU) cell for dynamic fault diagnosis. Although traditional recurrent neural networks (RNNs) have a major issue with extracting the spatial dependencies, temporal convolutional operation is designed to extract the local features which provide insight into different types of faults. The system dynamics are further extracted with the context by the bidirectional encoder-decoder network, which distils the representations from future time steps. Moreover, GRU cell in both encoder and decoder deploys a more compact structure than a usual RNNs network due to the reduction of gates. The resulting deep network is not only generalizing the importance of temporal feature, but it also allows the interpretable feature representation and classification simultaneously. Detailed comparative case study on the benchmark Tennessee Eastman process demonstrates that the proposed method is competitive with the classical long-short term memory (LSTM) network for the fault detection and diagnosis.

Fault location in the distribution network based on power system status estimation with smart meters data

Abstract Due to the existence of different branches in the electricity distribution network and only available voltage and current information at the beginning of the line and lack of access to the information at the end of the network line, the detection of the faulted section in the distribution network has become more important. Today, smart meters are used to measure the voltage and current of network lines, but due to the limitations of the installation sites, these devices are not possible in all network lines. In this paper, two techniques have been used to identify the faulted section and fault location in the network so that the fault distance at the beginning of the line can be estimated by estimating the current at the end of each network line. Therefore, in this project, by installing smart meters in the main branch of the network and also the information obtained from power flow in the network normal mode, it has been tried to practically estimate the voltage and current at the beginning and end of each distribution network line. In this method, more power flow is used to calculate the voltage drop of the lines and estimate the voltage and current at the end of the network lines so that the faulted part can be identified. Finally, the proposed method is implemented on the IEEE_15, 37 bus networks, the results of which show the proper performance of the proposed method in estimating location and Fault resistance for different types of faults in the distribution network.

Automotive Brake Part Inspection and Fault Localization using Deep Learning

Inspection of brake components is very essential to detect the damaged manufactured parts before it is assembled in any vehicle. Manual inspection of brakes is extremely difficult since most of defects are very minute and cannot be identified by human eyes. Therefore, automatic inspection of manufactured brakes is indispensible to prevent failure of brakes and accidents. Previously, various research articles perform inspection of brake through conventional image processing and traditional image processing algorithms. However, these techniques are capable of identifying a single fault only and are less robust to detecting numerous faults. Further, the existing techniques hardly localize the exact location of faults in the surface of brake. In order to over these drawbacks, in this research we utilize deep learning object detection algorithms namely Single Shot Detector and Faster RCNN to identify and localize the exact location of fault on the brake surface. Furthermore, the proposed system is capable to detect different types of faults in a single algorithm and is robust to brake’s material surface, environmental and lightening factors. The deep learning algorithms are trained using transfer learning on custom collected dataset. The proposed algorithms deliver an accuracy of 95.64% and mAP of 73.2% on cylindrical grey shade brakes.