Fault Identification Algorithm Research Articles

Fault diagnosis of virtually‐coupled trains by adaptive observer with pattern‐matched detection and reinforced identification

SummaryVirtual coupling is gaining in popularity as a promising development direction to maximize the rail‐line efficiency by minimizing the headway distance among trains in the presence of potentially encountered traction engines' faults with unknown amplitude, happening time and probability, which would be huge threat to the safety of trains without proper sensing and handling. This paper considers the fault diagnosis problem for virtually‐coupled multiple trains using adaptive observer design. In order to generate false‐free and timely fault alarming and relieving signals, an adaptive threshold function design is firstly given using a novel pattern‐matched gain technique with explicit consideration of model uncertainty. Then, reinforced regressor‐based fault identification algorithm is proposed to generate precise estimation of unknown fault values, activated and powered‐off by the fault alarming and relieving signals output by fault detection observer, with globally Lipschitz property and fast convergence performance. Finally, comparative and simulation results are given to demonstrate the effectiveness and advantages of proposed fault diagnosis algorithms.

Data-driven fault diagnosis method for abnormal RF oscillation of gyrotrons

Gyrotrons are vacuum electronic devices capable of generating high-power, high-frequency THz radiation. With the increasing utilization of gyrotrons in thermonuclear fusion experimental devices, achieving higher output performance and ensuring stable and reliable operation have become key development goals. However, occasional radio frequency (RF) oscillation faults inside the gyrotron during long-pulse operation hinder its stable and reliable operation. Due to the difficulty in directly observing abnormal changes within the gyrotron resonator during operation, this paper explores a data-driven approach to diagnose RF oscillation faults in the gyrotron for the first time and proposes a classification model that combines K-Nearest Neighbors and Random Forest (KNN-RForest) algorithms for fault identification. Compared with seven baseline models, the results show that our proposed KNN-RForest model has a better classification performance. It is verified that data-driven methods can effectively identify RF oscillation faults in gyrotrons. Finally, the state probabilities of the gyrotron under different power levels were predicted using the KNN-RForest model, demonstrating the application of the KNN-RForest model in identifying gyrotron RF oscillation faults, which may be helpful for setting stable operating parameters for the gyrotron to reduce the likelihood of RF oscillation faults.

An Integrated Monitoring, Diagnostics, and Prognostics System for Aero-Engines under Long-Term Performance Deterioration

In the field of aircraft engine diagnostics, many advanced algorithms have been proposed over the last few years. However, there is still wide room for improvement, especially in the development of more integrated and complete engine health management systems to detect, identify, and forecast complex faults in a short time. Furthermore, it is necessary to ensure that these systems preserve their capabilities over time despite engine deterioration. This paper addresses these necessities by proposing an integrated system that considers the joint operation of feature extraction, anomaly detection, fault identification, and prognostic algorithms for engines with long operation times. To effectively reveal the actual engine condition, light adaptive degraded engine models are computed along with different health indicators that are used as inputs to train and test recognition and prediction models. The system is developed and evaluated using a specialized NASA platform which provides data from a turbofan engine fleet simultaneously experiencing long-term performance deterioration and faults. Contrary to other compared solutions, our results show that the proposed system is robust against the effects of engine deterioration, maintaining its level of detection, recognition, and prediction accuracy over a total engine service life. The low computational cost algorithms has generally fast performance in all stages, making the system suitable for online applications.

Fast Arc Detection Technology Based on Fractal Dimension for SADA Slip Ring in Satellite Power System

The solar array drive assembly (SADA) slip ring is a critical link that provides electrical power and electric signal transmission between solar arrays and satellite power systems, which is prone to arc faults in the space environment. If these arc faults cannot be detected and eliminated quickly enough, they will seriously threaten the safety of the satellite power system and the satellite. In this paper, a fast arc detection method based on fractal dimension is proposed that adapts to different operating modes of power systems. The detection method collects the current differential signal data flowing through the SADA slip ring, and, according to the trend of the fractal dimension change in this signal, the fault identification algorithm is designed for different operating modes of the power system to achieve real-time and rapid identification of arc faults. Finally, the effectiveness of the proposed method is demonstrated using test data under several different fault conditions.

A novel scheme based on modified hierarchical time-shift multi-scale amplitude-aware permutation entropy for rolling bearing condition assessment and fault recognition

To avoid production interruptions and equipment damage caused by rolling bearing failure, this study presents a novel diagnosis scheme applicable to both condition monitoring and fault recognition. In detail, to fully exploit feature information, a modified Hierarchical Time-Shift Multi-scale Amplitude-Aware Permutation Entropy (MHTSMAAPE) is put forward to map the raw vibration signal into a high-dimensional vector space of features. This method is developed from the AAPE algorithm and integrates the time-shift procedure and modified hierarchical analysis, extracting more feature details while ensuring entropy stability. Afterwards, the averaged value of the feature vector is regarded as an indicator to assess the condition of rolling bearing, this indicator exceeds a specific value indicates the rolling bearing steps into faulty. Then, the Unsupervised Discriminative Feature Selection (UDFS) algorithm is first introduced to directly pick fault-sensitive features from the vector space, relieving the calculation burden of the fault recognition task. The fault identification algorithm is based on Harris Hawks Optimization-Joint Opposite Selection optimized for Support Vector Machine (HHO-JOS-SVM) to improve classification accuracy. Finally, the proposed scheme fused by MHTSMAAPE, UDFS, and HHO-JOS-SVM is validated in two different cases with four common evaluation metrics, respectively. The experimental results demonstrate its reliability and robustness in rolling bearing condition assessment and fault recognition.

Optimal Energy-efficient Resource Allocation and Fault Tolerance scheme for task offloading in IoT-FoG Computing Networks

Due to technology development in the recent past, it is observed that an exponential growth in the usage of high speed intelligent devices which includes smart objects, smart home, smart vehicles etc. Therefore, for the efficient transmission between different smart objects/devices situated across different regions, an effective communication is required and the corresponding technology is called as ‘Internet of Things (IoT)’. This leads to an issues in various aspects like, increase in complexity, low data rate & latency and security may reduce the performance of the existing technologies. Therefore, there is a huge requirement of advanced technology which may support ultra-low latency transmission for the task received from the devices. Fog computing (FC) is one of an emerging technology that can improve network performance and provide resource-constrained applications for the IoT devices. In this paper, the Optimal Energy-efficient Resource Allocation (OEeRA) algorithm is proposed based on Minimal Cost Resource Allocation (MCRA) and Fault Identification and Rectification (FIR) algorithms for effective task offloading of IoT-FoG computing networks. The MCRA algorithm is proposed to assign at least one FN and Resource Block (RB) for each device, and also it ensures that each FN is connected with one or more RBs and devices. The leftover RBs are collected and stored in the buffer to replace the faulty RBs, as proposed in the FIR algorithm, which achieves better processing and response time with higher fault detection accuracy. The energy efficiency (EE) of the proposed OEeRA algorithm is computed through MCRA and FIR algorithms by varying FN, RB, and IoT devices. The performance analysis shows that the proposed algorithm achieved the maximum EE of 6.12 × 109 bit/J, 5.69 × 1010 bit/J, and 3.019 × 1010 (bit/J) for varying RBs, IoTs, and FNs, respectively.

Fault identification and classification algorithm for high voltage transmission lines based on a fuzzy-neuro-fuzzy approach

ABSTRACT Traditional techniques are used for fault location detection in high-voltage transmission lines that mostly depend on traveling waves and impedance-based techniques suffer from large errors owing to the intricacy of fault modeling for various types of faults. Although single-line to ground faults are dominant in high-voltage transmission lines, fault resistance as well as fault inception angle might distort the current fault detection techniques. In addition, other types of faults exist and that raises the need to develop an accurate fault detection technique to minimize the recovery time. The current paper introduces a fuzzy and neuro-fuzzy algorithm to detect, analyze, and locate different faults taking place in high-voltage transmission lines. A MATLAB Simulink Model is used for analyzing different fault cases; fault detection and classification are done by the Fuzzy Interface System (FIS), while fault location detection is done using the Adaptive Neuro-Fuzzy Interface System (ANFIS). The introduced algorithm is evaluated via the Mean Square Error (MSE) technique. The results showed full success in detecting and identifying different fault types, with a 0.0042 validity performance factor for fault location detection using ANFIS.

On the Assessment of Sampling Rate Impacts on Responses of Digital Protective Relays

Power systems (including industrial and commercial power systems) widely utilize digital protective relays for component and system protection. These protective devices have shown numerous operational advantages over conventional electromagnetic protective devices. Such operational advantages include the accuracy, reliability, response speed, interoperability, weight, and size. Performance and operational advantages of digital protective relays are typically dependent on the resolution of their input data, as well as their algorithms for fault detection and identification. This paper assesses the performance of time-based, frequency-based, and time-frequency-based digital protective relays, when operated at different sampling rates. Tested sampling rates include low, medium, and high sampling rates that range from 16 to 288 samples per cycle. In this paper, the three digital protective relays are tested when deployed as the digital 87 T transformer digital protection. Performance of the time-based, frequency-based, and time-frequency-based digital protective relays is assessed in terms of their accuracy and response speed. Test results show that low sampling rates can deteriorate the accuracy and response speed of the three tested digital protective relays. Obtained performance results also reveal that medium and high sampling rates can effectively improve the accuracy and response speed of the time-based, frequency-based, and time-frequency-based digital protective relays.

Probabilistic neural network-based diagnosis of blockage faults in air conditioning and refrigeration units

Abstract The refrigeration unit is a core component of the air conditioner, and its typical faults are pipe scaling and blockage, which can cause refrigerant leakage in serious cases, and these faults can affect the cooling effect of the air conditioner and even affect the safety of using the air conditioner in serious cases. Therefore, it is necessary to study the fault diagnosis system of the refrigeration unit. The traditional fault diagnosis system for refrigeration units, which generally uses wireless sensor networks to transmit data, is a challenge because of its slow diagnosis speed and the low accuracy rate of fault diagnosis for refrigeration units. This paper uses a probabilistic neural network (PNN) to debug a blockage fault diagnosis algorithm system for simulated fault training. The system successfully achieves four levels of pre-warning for blockage faults: “uncertainty, micro-blockage, blockage, and severe blockage”, with the fastest pre-warning time of “uncertainty, micro-blockage” being less than 2 seconds. The experimental results of this paper show that the PNN system can take timely measures against blockage faults, and the fault diagnosis accuracy of the model reaches 97.97%, which is 13.34% higher than the traditional fault identification algorithm. The PNN model can pinpoint the blockage faults of the refrigeration unit, which enables the working state of the refrigeration unit to be continuously optimized, and the air conditioner to maintain energy-efficient operation. The fault simulation of the air conditioning refrigeration unit in automatic control mode verifies the blockage fault diagnosis’s accuracy and the algorithm’s feasibility, providing reference and learning for the development of fault diagnosis algorithms.

A Fault Diagnosis Method of Four-Mass Vibration MEMS Gyroscope Based on ResNeXt-50 with Attention Mechanism and Improved EWT Algorithm.

In this paper, a fault identification algorithm combining a signal processing algorithm and machine learning algorithm is proposed, using a four-mass vibration MEMS gyroscope (FMVMG) for signal acquisition work, constructing a gyroscope fault dataset, and performing the model training task based on this dataset. Combining the improved EWT algorithm with SEResNeXt-50 reduces the impact of white noise in the signal on the identification task and significantly improves the accuracy of fault identification. The EWT algorithm is a wavelet analysis algorithm with adaptive wavelet analysis, which can significantly reduce the impact of boundary effects, and has a good effect on decomposition of signal segments with short length, but a reconstruction method is needed to effectively separate the noise signal and effective signal, and so this paper uses multiscale permutation entropy for calculation. For the reason that the neural network has a better ability to characterize high-dimensional signals, the one-dimensional signal is reconstructed into a two-dimensional image signal and the signal features are extracted. Then, the constructed image signals are fed into the SEResNeXt-50 network, and the characterization ability of the model is further improved in the network with the addition of the Squeeze-and-Excitation module. Finally, the proposed model is applied to the FMVMG fault dataset and compared with other models. In terms of recognition accuracy, the proposed method improves about 30.25% over the BP neural network and about 1.85% over ResNeXt-50, proving the effectiveness of the proposed method.

Development of an algorithm for identifying single-phase ground fault conditions in cable and overhead lines in the networks with isolated neutral

The paper addresses the issue of identification of the type of single-phase ground fault in medium voltage networks operating mainly with an isolated neutral. By analyzing the published research, the most promising methods for detection of a single-phase ground fault were selected. Further, using the selected parameters, algorithms were designed to determine the parameters, process them, and use them to identify the type of a single-phase ground fault. The algorithm developed by the authors was formalized for the application on the basis of microprocessor-based protection systems using digital signal processors. The operation process was modeled using real oscillograms of single-phase ground fault. The use of high-frequency zero-sequence current and voltage components, as well as the root-mean-square value of the zero-sequence voltage, made it possible to design an algorithm that identifies any of the possible single-phase ground fault types (bolted, arc, or contact resistance ones). The first part of the article gives an overview of the state-of-the-art of research in the field of detection and identification of single-phase-to-earth faults. In the second part, the parameters of emergency operating conditions are analyzed and the key parameters are determined based on them. The third part contains a description of the single-phase fault identification algorithm developed by the authors and the output oscillograms. The fourth part makes conclusions on the applicability of the algorithm.

Fault Diagnosis of Diesel Engine Valve Clearance Based on Wavelet Packet Decomposition and Neural Networks

In order to improve the accuracy of engine valve clearance fault diagnosis, in this study, a fault identification algorithm based on wavelet packet decomposition and an artificial neural network is proposed. Firstly, the vibration signals of the engine cylinder head were collected, and different levels of noise were superimposed on the extended data sets. Then, the test data were decomposed into wavelet packets, and the power spectrum of the sub-band signal was analyzed using the autoregressive power spectrum density estimation method. A group of values were obtained from the power spectrum integration to form the fault eigenvalue. Finally, a neural network model was designed to classify the fault eigenvalues. In the training process, the test data set was divided into three parts, the training set, the verification set, and the test set, and the dropout layer was added to avoid the overfitting phenomenon of the neural network. The experimental results show that the wavelet packet neural network model in this paper has a good diagnostic accuracy for data with different levels of noise.

Protection Algorithm for Fault Identification and Isolation in DC Microgrid

In renewable energy dominated distributed ring configuration direct current (DC) networks, the protection philosophy is one of the critical challenging task. It is due to the existence of power electronic converters and erratic attributes of distributed energy sources. Consequently, conventional current direction based as well as over current protection strategies is not applicable for DC microgrids. In this paper, protection algorithm for fault recognition and isolation of faulty line is presented based on the polarity of change in inductance immediately after fault inception. The voltage and current sample information is used to determine the parameter by employing the least square estimation (LSE) technique. The efficiency of the proposed method is tested for internal and external faults, the impact of fault resistance and fault location, different system configurations, and load change conditions in MATLAB/Simulink simulation. It is noted that proposed method would categorize internal and external faults perfectly. The operating time of the proposed protection method is comparatively less than the existing methods. It also improves selectivity, security, and reliability under above mentioned abnormal cases.

Selection of fault selection jump identification algorithms for high-speed railway traction networks

High-speed railways have become a new business card for China. When power supply faults occur in the electrical traction network of high-speed railways, the practice of sacrificing selectivity to ensure the reliability of the relay protection system often occurs, and a more effective relay protection scheme must be adopted if the reliability and selectivity of the protection system are to be taken into account. Fast and accurate identification of fault types and their removal from the traction network is of great significance for the stable operation of railway power supply systems. Therefore, it is particularly important to identify and locate fault solutions. This paper analyses the commonly used fault identification and location algorithms, determines the fault signal processing principles for fully parallel AT lines, determines which algorithms are used to identify and locate faults, and helps to improve the fault detection efficiency of railway power lines.

Multi-Sensor Fault Diagnosis Based on Time Series in an Intelligent Mechanical System

Intelligent mechanical systems are a focused area nowadays. One of the requirements of intelligent mechanical systems is to achieve intelligent fault diagnosis through the real-time acquisition and analysis of data from various sensors installed on mechanical components. In this paper, a new fault diagnosis method is proposed to solve the problems of difficulty in integrating the fault diagnosis algorithm and locating fault parts due to the complexity of modern mechanical systems. The complexity of modern industrial intelligent systems is due to the fact that the systems are composed of multiple components and there are various connections between them. Common fault diagnosis is to design specialized fault identification algorithms for the physical characteristics of each component, and the integration of different algorithms is a major challenge for system performance. Therefore, this paper investigates a general algorithm for the fault diagnosis of complex systems using the timing characteristics of sensors and transfer entropy. The fault diagnosis algorithm is based on the prediction of multi-dimensional long time series using Autoformer, and fault identification is performed based on the deviation of the predicted value from the actual value. After fault identification, a root cause analysis method of faults based on transfer entropy is proposed. The method can locate the component where the fault occurs more accurately based on the analysis of the cause-effect relationship of each component and help maintenance personnel to troubleshoot the fault.

Data Driven Transformer Thermal Model for Condition Monitoring

Condition monitoring of power transformers, which are key components of electrical power systems, is essential to identify incipient faults and avoid catastrophic failures. In this paper machine learning algorithms, i.e., nonlinear autoregressive neural networks and support vector machines, are proposed to model the transformer thermal behavior for the purpose of monitoring. The thermal models are developed based on the historical measurements from nine transformers comprised of two 180-MVA units, four 240-MVA units and three 1000-MVA units. The data consist of load profile, tap position, winding indicator temperature (WTI) measurement, ambient temperature, wind speed and solar radiation. The results are validated against field measurements, and it is clearly demonstrated that the alternative algorithms surpass the IEEE Annex G thermal model. An incipient thermal fault identification algorithm is then proposed and successfully used to identify an issue using measurements taken in the field. This algorithm could be used to alert the operator and plan intervention accordingly.

A fault identification method based on an ensemble deep neural network and a correlation coefficient

An intelligent fault identification algorithm based on ensemble deep neural networks and correlation coefficients is proposed for rotating machinery fault detection. In this algorithm, three deep neural networks (DNNs) are arranged to initially identify faults in the frequency domain, wavelet domain and envelope spectrum angle, respectively. Then, correlation coefficients are adopted to evaluate the recognition results of the DNNs. The reliabilities of the DNNs’ recognition results are divided into 6 levels according to the outputs of the DNNs and the correlation coefficients. Finally, the evaluation results of the three DNNs are put through fusion processing to generate more reliable recognition results. This algorithm identifies fault signals from multiple angles and combines the correlation coefficients to make a comprehensive judgment, which is beneficial for fault identification. Tests on some public bearing data sets show that the proposed algorithm can improve the reliability of fault identification.

Automated fault detection in the Arabian Basin

In recent years, there has been a rapid development of the computer-aided interpretation of seismic data to reduce the otherwise intensive manual labor. A variety of seed detection algorithms for horizon and fault identification are integrated into popular seismic software packages. Recently, there has been an increasing focus on using neural networks for fully automatic fault detection without manually seeding each fault. These networks are usually trained with synthetic fault data sets. These data sets can be used across multiple seismic data sets; however, they are not as accurate as real seismic data, particularly in structurally complex regions associated with several generations of faults. The approach taken here is to combine the accuracy of manual fault identification in certain parts of the data set with a convolutional neural network that can then sweep through the entire data set to identify faults. We have implemented our method using 3D seismic data acquired from the Arabian Basin in Saudi Arabia covering an area of 1051 km2. The network is trained, validated, and tested with samples that included a seismic cube and fault images that are labeled manually corresponding to the seismic cube. The model successfully identifies faults with an accuracy of 96% and an error rate of 0.12 on the training data set. To achieve a robust model, we further enhance the prediction results using postprocessing by linking discontinued segments of the same fault line, thus reducing the number of detected faults. The postprocessing improves the prediction results from the test data set by 77.5%. In addition, we introduce an efficient framework to correlate the predictions and the ground truth by measuring their average distance value. Furthermore, tests using this approach also have been conducted on the F3 Netherlands survey with complex fault geometries and find promising results. As a result, fault detection and diagnosis are achieved efficiently with structures similar to the trained data set.

Multi-Sensor GA-BP Algorithm Based Gearbox Fault Diagnosis

To address the problem of the low recognition rate of time-frequency domain methods gearbox fault identification, a method featuring decision-level fusion of DS evidence theory and GA-BP algorithm was proposed in the present study. Firstly, the fault data of each state of the gearbox was classified, based on which the time-frequency domain features were extracted and 19 significant features have been selected. Secondly, the accuracy of the traditional BP algorithm was compared with that of the GA-BP algorithm. On this basis, it has been concluded that the GA-BP algorithm is highly accurate, and the local diagnostic results obtained by the GA-BP algorithm have been used as the basic probability. Finally, the DS evidence theory is currently used to fuses with the GA. In addition, the final fault identification of the gearbox can be achieved by using the DS evidence theory and the multi-sensor local diagnosis results obtained by the GA-BP algorithm for decision fusion. The results of the simulations and experiments showed that the method proposed has improved accuracy over a single algorithm for fault identification of gearboxes, respectively.

Integrity monitoring of Global Navigation Satellite System/Inertial Navigation System integrated navigation system based on dynamic fading filter optimisation

In the application of integrity monitoring of Global Navigation Satellite System (GNSS)/Inertial Navigation System integrated navigation system in complex environments, such as vegetation covered areas, the Kalman filtering (KF) has the disadvantages of low positioning precision, poor performance of fault identification and error bounds. This study proposes an integrity monitoring method based on dynamic fading filter optimisation. According to the real-time updates of filtering innovation, a fading filtering algorithm is designed, which can adjust the fading factor dynamically. The dynamic fading filtering algorithm is then combined with the fault identification algorithm, which integrates chi-square and multiple solution separation. An optimisation strategy of setting a fading period to speed up the filter convergence is proposed. The simulation results show that compared with the KF, the dynamic fading filtering reduces the standard deviations of positioning errors by 26%, 39%, and 26%, respectively, in the east, north and up directions. By reducing the filter convergence period, the proposed dynamic fading filtering can enhance the accuracy of the identification results when the subsequent GNSS fault is minor. It can shorten the identification time to about 20% when the subsequent fault is large. The dynamic fading filtering can also limit the state errors below the bounds correctly.