Fault Classification Accuracy Research Articles

Fault detection, classification, and location for active distribution network based on neural network and phase angle analysis

ABSTRACTThe improved radial basis function (RBF) method utilizes an orthogonal regression matrix to produce an artificial neural network structure based on regularized least square. The phase angle and amplitude signal of fault voltage and current are extracted based on frequency domain analysis. The proposed method adopts the fault signal for fault diagnosis synchronously. The IEEE 13-bus active distribution network (ADN) simulation model is set up in Matlab. Test results demonstrate that accuracy of the fault diagnosis can reach 98.07% and the response time of the fault classification method is less than 0.04s. The wavelet neural network (WNN) model is developed to extract the maximum decomposition level and time series behavior. The WNN method can resist noise effects and improve the fault classification accuracy by 4.3%. The effect of fault type and fault resistance on the fault location method is researched. The fault simulation result shows that the proposed method can locate a fault precisely and synchronously. The improved RBF method can diagnose the fault section, classify the fault type and locate a fault accurately in ADN. The research is significant to maintain system stability against realistic fault and network restore.

Intelligent classification model for railway signal equipment fault based on SMOTE and ensemble learning

In this paper, we propose a novel intelligent classification model to classify the railway signal equipment fault based on SMOTE and ensemble learning. To tackle the imbalanced fault text data, the model uses SMOTE algorithm to generate the minority railway signal equipment fault class data randomly, making the data balanced. Then the model adopts the base classifier, such as Logistic Regression, Multinomial Naive Bayes, SVM and the ensemble classifier, such as GBDT, Random Forests to classify the data processed by SMOTE. To combine the advantages of various classifiers, the model integrates multiple classifiers by way of voting. Based on the experiment analysis of railway signal equipment fault text data from 2012 to 2016, the result shows that the model has a significant improvement in fault classification accuracy, recall rate and f-score.

A multi-task deep learning model for rolling element-bearing diagnostics

The rolling element bearing is the predominant source of failures in rotating machinery. Therefore, detecting the corresponding faults, predicting their locations and measuring their severity is of immense importance. Classical intelligent diagnostics approaches rely on feature extraction methods followed by a classification model. Recently, deep learning models improved the fault classification accuracy by learning a suitable representation directly from the raw sensor data. In this work, we present a novel multi-task deep convolutional neural network trained end-to-end on raw vibration data to learn a shared representation for fault isolation and fault size evaluation. The proposed model architecture is constructed by stacking blocks of convolution layers, pooling layers, and batch normalization layers followed by a regression head and a classification head. Extensive experiments show that the proposed approach produces a superior performance to other existing methods and generalizes well to fault sizes not present in the training set.

A deep Boltzmann machine and multi-grained scanning forest ensemble collaborative method and its application to industrial fault diagnosis

The essence of big data-based intelligent industrial fault diagnosis lies in the process of machine learning and feature engineering. Deep learning methods can discover the complex relationship between data and potential faults, and outperform the traditional machine learning methods. The gcForest is able to generate a deep forest ensemble, which allows gcForest to do representation learning and fault classification. At each node of the random tree, gcForest selects the one with the best gini value from candidates for splitting. However, most of the data acquired from industrial scene is with continuous and unstructured attributes, accordingly the node-splitting procedure will be generally intractable. We present a novel approach with the combination of deep Boltzmann machine and multi-grained scanning forest ensemble, to effectively deal with industrial fault diagnosis based on big data. At first, we use deep Boltzmann machine to turn all features of data to be processed by forests into binary, and then utilize multi-grained scanning forest ensemble to process them in every layer of deep Boltzmann machine. By means of the collaborative method, we can address the aforementioned issues. The experimental results and analysis on industrial fault diagnosis under different experimental conditions, show that the fault classification accuracy of the proposed approach is competitive to other popular deep learning algorithms, but also takes much less time than gcForest.

Compound gear-bearing fault feature extraction using statistical features based on time-frequency method

A small incipient fault in gear and bearing causes multiple faults in gear-bearing system leading to catastrophic failure. The purpose of present study is to explore more complex situation of compound gear-bearing fault. The compound faults such as a fault in the inner and outer race of bearing along with two teeth of gear having corner damage or three teeth of gear having corner damage, etc. are investigated using experimentation. To improve the effectiveness of diagnosis, vibration measurement is done at different speed and load condition. This paper proposes new compound fault features, extracted from continuous and discrete wavelet transform of vibration signal. The methodology consist of proposing the features in time–frequency domain and comparison of its diagnostic potential with respect to the features extracted from time and frequency domain for compound fault identification using three different classifiers. The fault classification accuracy of these features is found to be better than the conventional time and frequency domain parameters.

Transient- and probabilistic neural network-based fault classification in EHV three-terminal lines

This paper presents a fast and accurate fault classifier for three-terminal transmission circuits. Traditional phasor-based methods fail to meet the high speed requirements of modern power grids and necessitate alternative solutions. The transient-based schemes use advanced signal processing techniques to achieve fast and accurate fault classification. As the three-terminal lines experience very pronounced transients during faults, the proposed method makes use of the fault-generated transients to quickly and correctly classify the fault. Many transient-based schemes fail to give the required accuracy since the transient patterns with relay-measured signals are highly influenced by fault conditions. Therefore, a thorough analysis of transient patterns is carried out in this paper, and based on the typical patterns revealed by the analysis of fault-generated transients an effective classification algorithm is developed. For high-speed classification, only a quarter-cycle of postfault voltage signals measured at the relay points will be processed for feature extraction using wavelet transform. The algorithm includes a hybrid procedure based on a probabilistic neural network for tackling the effects of fault inception angle and fault resistance in transient variations. Particularly, it is designed to overcome the problem with double-line-to-ground fault classification. The technique is simple and extensive simulation studies and comparison substantiate the efficacy of the proposed method under different fault conditions.

A new fault detection and fault location method for multi-terminal high voltage direct current of offshore wind farm

This paper proposes a novel protection scheme for multi-terminal High Voltage Direct Current (MTDC) systems incorporating offshore wind farm based on high-frequency components detected from the fault current signal. This method can accurately detect the fault on each line and classify the fault types. Using the post-fault current time series, both single-ended measurements (detection and classification) and double-end measurements (location), the frequency spectrum is generated to measure the gaps between the contiguous peak frequencies giving a robust and comprehensive scheme. Unlike the previous travelling wave based methods, which must identify the travelling wavefront and require a high sampling rate, the new gap-based approach is able to give accurate fault detection and fault location using any appropriate range of post-fault signals. Furthermore, the proposed method is fault resistance independent and thus even a very high fault impedance has no effect on the fault location detection. By immediately tripping the faults, the fault-caused disturbance to the offshore wind farm is minimized. A three-terminal voltage sourced converter HVDC (VSC-HVDC) system connection of offshore wind farm is modelled in PSCAD/EMTDC (Power Systems Computer Aided Design/Electro-Magnetic Transients including DC) software, which is used for obtaining the fault current data for the transmission line terminal. The algorithm is verified by studying a range of cases, by varying the fault resistance fault locations and also including external faults. The results show that the proposed method gives an accurate and reliable fault detection, classification and location on the test MTDC system.

Artificial intelligence-based machine learning considering flow and temperature of the pipeline for leak early detection using acoustic emission

The application of the high-frequency Acoustic Emission (AE) system for condition monitoring of the pipeline has been increasing. But the noise of AE signal is essential to reduce the noise and redundant signal due to the high sensitivity transducer. Genetic Algorithm (GA) for feature selection and Principle Component Analysis (PCA) for preprocessing to improve fault classification accuracy are estimated by Artificial Intelligence (AI) based machine learning using Support Vector Machine (SVM). In order to diagnose efficiently leak early detection for pipeline system. In addition, the different critical condition for exciting sources of the tube for heat exchanger of fuel cell are occurred considering crack, temperature and flow of fluid. For preprocessing, envelope analysis is a powerful method for detecting faults of the bearing system, but envelope analysis is not proper for use in the pipeline. Therefore, in this paper, Intensified Envelope Analysis (IEA) for a signal-preprocessing method consisting of envelope analysis and discrete wavelet transform (DWT) is applied. Moreover, a novel mother function optimized for the AE signal. Therefore, preprocessing and feature selection and extraction are estimated for early detection considering the condition of the pipeline through the comparison with them. As the result of classification using SVM one of the machine learning, the performance of GA for feature selection and IEA are more improved than PCA and envelope analysis. This study is focused on the condition of the pipeline to discriminate the condition of crack, temperature and the flow of fluid using AE signal.

A hybrid wavelet–APSO–ANN-based protection scheme for six-phase transmission line with real-time validation

The ever-increasing load demand motivates the adoption of the six-phase transmission system as a viable alternative to the conventional three-phase double-circuit line because of its enhanced power transfer capability. However, the acceptance of six-phase transmission is highly dependent on its protection scheme, which is a challenging task due to the large number of possible faults. In this regard, this paper describes a novel concept based on the hybridization of wavelet transform, adaptive particle swarm optimization (APSO) and ANN for fault classification and location in the six-phase transmission line. The proposed scheme overcomes the difficulties associated with existing ANN-based protection schemes related to the selection of architecture and convergence to the non-global optimal set of weight vectors and biases post-training. From the features/attributes extracted using wavelet transform, the hybrid algorithm utilizes the strong exploration and mapping capability of APSO and ANN, respectively, for input–output mapping. It significantly increases the probability of global convergence for ANN training, thereby improving the performance of the protection scheme in terms of fault detection, classification and location estimation accuracy. The proposed scheme has been extensively tested for wide variation in different fault attributes. In addition to the offline simulations, the effectiveness of the proposed scheme has been validated in real-time environment by carrying out hardware in loop simulations using OPAL-RT digital simulator.

A New Harmony Search Approach for Optimal Wavelets Applied to Fault Classification

This paper presents a novel approach based on the harmony search algorithm to optimally determine suitable wavelet functions and wavelet decomposition levels for accurate fault classification in transmission lines, unlike previous works in which only one arbitrary wavelet function is used. Discrete wavelet transform is used to extract the features in the voltage and/or current signals using the identified wavelet functions. Machine learning classifiers are then used to build a proper classification model to automate the fault classification process. The results of applying the proposed approach are presented and discussed, and conclusions are drawn.

Design and development of fault classification algorithm based on relevance vector machine for power transformer

Identification of faults within power transformers is the means of ensuring unit transformer protection. Existing relay maloperates during abnormalities such as magnetising inrush, CT saturation and high resistance internal fault condition. Therefore, it is essential to categorise the internal fault and external abnormality/fault in case of transformer protection. This study presents a new scheme, based on relevance vector machine (RVM) as a fault classifier. The developed algorithm is assessed by simulating various disorders on 345 MVA, 400/220 kV transformer in PSCAD/EMTDC software and also on prototype model with 2 kVA, 230/110 V multi-tapping transformer. One cycle post fault current signals are captured from primary and secondary to form feature vectors. These feature vectors are used as an input to RVM for classification of various test cases. Wide variation in system parameters and fault conditions are considered for test data generation and validation. The proposed scheme is compared with the support vector machine (SVM) and probabilistic neural network (PNN)-based techniques. The proposed scheme successfully discriminates various types of internal faults and external abnormalities in power transformer within a short time. The fault classification accuracy obtained by proposed RVM technique is more than 99% in comparison to SVM and PNN-based schemes.

Understanding the importance of process alarms based on the analysis of deep recurrent neural networks trained for fault isolation

AbstractThe identification of process faults is a complex and challenging task due to the high amount of alarms and warnings of control systems. To extract information about the relationships between these discrete events, we utilise multitemporal sequences of alarm and warning signals as inputs of a recurrent neural network–based classifier and visualise the network by principal component analysis. The similarity of the events and their applicability in fault isolation can be evaluated based on the linear embedding layer of the network, which maps the input signals into a continuous‐valued vector space. The method is demonstrated in a simulated vinyl acetate production technology. The results illustrate that with the application of recurrent neural network–based sequence learning not only accurate fault classification solutions can be developed, but the visualisation of the model can give useful hints for hazard analysis.

Fault Detection and Classification Based on Co-training of Semisupervised Machine Learning

This paper presents a semisupervised machine learning approach based on co-training of two classifiers for fault classification in both the transmission and the distribution systems with consideration of microgrids. Unlike previous work in which only labeled data are treated using supervised machine learning approaches, this study uses a semisupervised machine learning approach to handle both labeled and unlabeled data. In order to extract the hidden features in the current and voltage waveforms, the discrete wavelet transform is applied, while the harmony search algorithm is utilized to identify the optimal parameters of the wavelets. The performance of the proposed method was examined on both transmission and distribution test systems in a simulation environment, and also using experimental hardware. The results have shown that the proposed approach provides flexibility and adaptability in dealing with various system conditions/configurations with high accuracy. The results also have demonstrated that the proposed semisupervised approach can improve the fault classification accuracy compared to that obtained using other machine learning approaches (i.e., supervised and unsupervised) in the case of utilizing unlabeled data to build and train the classifier's model.

A New Fault Classifier in Transmission Lines Using Intrinsic Time Decomposition

As nonstationarity exists in fault signals of transmission lines, their classification and quantification remain a challenging issue. This paper presents a new scheme for feature extraction in an attempt to achieve high fault classification accuracy. The proposed scheme consists of three steps: first, the proper rotation components (PRCs) matrix of current signals captured from one end of the protected line is constructed using the intrinsic time decomposition, a fast time-domain signal processing tool with no need for sensitive tuning parameters. Second, the singular value decomposition and nonnegative matrix factorization are employed to decompose the PRCs into its significant components. Finally, eight new normalized features extracted from the output of the data processing techniques are fed into the probabilistic neural network classifier. The data processing techniques employed for classification substantially improve the overall quality of the input patterns classified and increase the generalization capability of the trained classifiers. The proposed scheme is evaluated through two simulated sample systems in the PSCAD/EMTDC software and field fault data. Moreover, the effects of the current transformer saturation, decaying dc component, and noisy conditions are evaluated. The comparison results and discussion regarding the different aspects of the problem confirm the efficacy of the proposed scheme.

Kernel Entropy-Based Classification Approach for Superbuck Converter Circuit Fault Diagnosis

How to extract the fault feature and how to design the classification algorithm are the two most critical problems in power electronic circuits (PECs) fault diagnosis. Based on a kernel entropy component analysis theory, combining an extreme learning machine classification algorithm, this paper explores the feasibility of applying an ensemble approach, called KECA-ELM, to deal with the hard fault and soft fault diagnosis in a superbuck converter circuit (SCC). This approach can reduce the influence of the complex correlation between the data on the accuracy of fault classification. Furthermore, it can compress the feature dimension of the data while maintaining the feature discriminating power and reduce the computation in the classification stage. We record the signal from the output of the circuit, analyze their static and dynamic electrical performance, and then select the representative feature parameters. These feature parameters are combined into feature vectors which can reflect the health status of the PECs. Finally, simulation and physical experiment are presented in the SCC to demonstrate the fault classification ability of the proposed approach.

Texture analysis based feature extraction using Gabor filter and SVD for reliable fault diagnosis of an induction motor

This paper presents a texture analysis based feature extraction method using a Gabor filter and singular value decomposition (SVD) for reliable fault diagnosis of an induction motor. This method first converts one-dimensional (1D) vibration signal to a two-dimensional (2D) grey-level texture image for each fault signal. Then, the 2D Gabor filter with optimal frequency and orientation values is used to extract a filtered image with distinctive texture information, and SVD is utilised to decompose the Gabor filtered image and select finer singular values of SVD as discriminative features for multi-fault diagnosis. Finally, one-against-all multiclass support vector machines (OAA-MCSVMs) are used as classifiers. In this study, multiple induction motor faults with different noisy conditions are used to validate the proposed fault diagnosis methodology. The experimental results indicate that the proposed method achieves an average classification accuracy of 99.86% and outperforms conventional fault diagnosis algorithms in the fault classification accuracy.

Reliable Fault Diagnosis of Rotary Machine Bearings Using a Stacked Sparse Autoencoder‐Based Deep Neural Network

Due to enhanced safety, cost‐effectiveness, and reliability requirements, fault diagnosis of bearings using vibration acceleration signals has been a key area of research over the past several decades. Many fault diagnosis algorithms have been developed that can efficiently classify faults under constant speed conditions. However, the performances of these traditional algorithms deteriorate with fluctuations of the shaft speed. In the past couple of years, deep learning algorithms have not only improved the classification performance in various disciplines (e.g., in image processing and natural language processing), but also reduced the complexity of feature extraction and selection processes. In this study, using complex envelope spectra and stacked sparse autoencoder‐ (SSAE‐) based deep neural networks (DNNs), a fault diagnosis scheme is developed that can overcome fluctuations of the shaft speed. The complex envelope spectrum made the frequency components associated with each fault type vibrant, hence helping the autoencoders to learn the characteristic features from the given input signals more readily. Moreover, the implementation of SSAE‐DNN for bearing fault diagnosis has avoided the need of handcrafted features that are used in traditional fault diagnosis schemes. The experimental results demonstrate that the proposed scheme outperforms conventional fault diagnosis algorithms in terms of fault classification accuracy when tested with variable shaft speed data.

Multiple Feature Vectors Based Fault Classification for WSN Integrated Bearing of Rolling Mill

For rolling mill machines, the operation status of bearing has a close relationship with process safety and production effectiveness. Therefore, reliable fault diagnosis and classification are indispensable. Traditional methods always characterize fault feature using a single fault vector, which may fail to reveal whole fault influences caused by complex process disturbances. Besides, it may also lead to poor fault classification accuracy. To solve the above-mentioned problems, a fault extraction method is put forward to extract multiple feature vectors and then a classification model is developed. First, to collect sufficient data, a data acquisition system based on wireless sensor network is constructed to replace the traditional wired system which may bring dangers during production. Second, the measured signal is filtered by a morphological average filtering algorithm to remove process noise and then the empirical mode decomposition method is applied to extract the intrinsic mode function (IMF) which contains the fault information. On the basis of the IMFs, a time domain index (energy) and a frequency index (singular values) are proposed through Hilbert envelope analysis. From the above analysis, the energy index and the singular value matrix are used for fault classification modeling based on the enhanced extreme learning machine (ELM), which is optimized by the bat algorithm to adjust the input weights and threshold of hidden layer node. In comparison with the fault classification methods based on SVM and ELM, the experimental results show that the proposed method has higher classification accuracy and better generalization ability.

Fault Diagnosis of a Reconfigurable Crawling–Rolling Robot Based on Support Vector Machines

As robots begin to perform jobs autonomously, with minimal or no human intervention, a new challenge arises: robots also need to autonomously detect errors and recover from faults. In this paper, we present a Support Vector Machine (SVM)-based fault diagnosis system for a bio-inspired reconfigurable robot named Scorpio. The diagnosis system needs to detect and classify faults while Scorpio uses its crawling and rolling locomotion modes. Specifically, we classify between faulty and non-faulty conditions by analyzing onboard Inertial Measurement Unit (IMU) sensor data. The data capture nine different locomotion gaits, which include rolling and crawling modes, at three different speeds. Statistical methods are applied to extract features and to reduce the dimensionality of original IMU sensor data features. These statistical features were given as inputs for training and testing. Additionally, the c-Support Vector Classification (c-SVC) and nu-SVC models of SVM, and their fault classification accuracies, were compared. The results show that the proposed SVM approach can be used to autonomously diagnose locomotion gait faults while the reconfigurable robot is in operation.

Unsupervised Fault Diagnosis of a Gear Transmission Chain Using a Deep Belief Network.

Artificial intelligence (AI) techniques, which can effectively analyze massive amounts of fault data and automatically provide accurate diagnosis results, have been widely applied to fault diagnosis of rotating machinery. Conventional AI methods are applied using features selected by a human operator, which are manually extracted based on diagnostic techniques and field expertise. However, developing robust features for each diagnostic purpose is often labour-intensive and time-consuming, and the features extracted for one specific task may be unsuitable for others. In this paper, a novel AI method based on a deep belief network (DBN) is proposed for the unsupervised fault diagnosis of a gear transmission chain, and the genetic algorithm is used to optimize the structural parameters of the network. Compared to the conventional AI methods, the proposed method can adaptively exploit robust features related to the faults by unsupervised feature learning, thus requires less prior knowledge about signal processing techniques and diagnostic expertise. Besides, it is more powerful at modelling complex structured data. The effectiveness of the proposed method is validated using datasets from rolling bearings and gearbox. To show the superiority of the proposed method, its performance is compared with two well-known classifiers, i.e., back propagation neural network (BPNN) and support vector machine (SVM). The fault classification accuracies are 99.26% for rolling bearings and 100% for gearbox when using the proposed method, which are much higher than that of the other two methods.