Fault Classification Accuracy Research Articles

Category-aware dual adversarial domain adaptation model for rolling bearings fault diagnosis under variable conditions

The domain adaptation methods have good performance in solving the distribution discrepancy of vibration signals of rolling bearings under variable conditions, but without considering the alignment of different categories. To this end, a new dual adversarial domain adaptation (2ADA) mechanism for feature intra-category is proposed and a fault diagnosis model based on 2ADA is built in this paper. The method effectively uses category information to achieve category awareness, and avoids misclassification at the fuzzy decision boundary. In the training process, the multiple-kernel maximum mean discrepancy is used to reduce the discrepancy and perform a global alignment. The category-level alignment is performed when 2ADA is activated, which due to obtain more comprehensive domain adaptation performance and improve the accuracy of fault classification. The results of fault diagnosis experiments on the Case Western Reserve University (CWRU) bearing dataset and the rotating machinery fault platform dataset demonstrate that, the diagnosis accuracy of the proposed method is improved by up to 15.46% and 5.75% on tasks with high domain shift when compared with convolutional neural network method, which verifies the effectiveness of the method.

Speed adaptive gate: A novel auxiliary branch for enhancing deep learning-based rotating machinery fault classification under varying speed conditions

Rotating machines like wind turbines often work under varying speed conditions. Faults may occur in these machines as time goes on. It is important to detect faults early and classify the type and the severity of an occurred fault, so that timely maintenance could be scheduled. This paper attempts to improve the fault classification accuracy of existing deep learning models when they are used for the fault classification of rotating machinery that operates under varying speed conditions. To achieve this goal, we firstly investigate the effects of speed variation from the perspective of deep learning. We find that the fault information in vibration signals is imbalanced due to speed variation. The imbalance future deteriorates the fault classification accuracy of deep learning models. That is, the accuracy does not evenly distribute across speed but increases with speed. We then propose an auxiliary branch named speed adaptive gate (SAG) for existing deep learning models to address the speed induced fault information imbalance. The SAG takes the speed signal as the input and outputs speed adaptive gate values. The gate values control the information flow of deep learning models so that the effects of speed variation are mitigated. Case studies with two baseline models, i.e., a convolutional neural network (CNN) and a residual network (ResNet), over two experimental datasets, i.e., a planetary gearbox dataset and a fixed-shaft gearbox dataset, have validated the effectiveness of the proposed SAG and its superiority over existing approaches.

Research on Transformer Partial Discharge Feature Extraction Based on Empirical Wavelet Transform and Multiscale Permutation Entropy

Aiming to extract efficiently the fault features of partial discharge in the process of fault diagnosis of power transformer, a method of combining Empirical Wavelet Transform (EWT) with Multiscale Permutation Entropy (MPE) is advanced to extract fault features of transformers partial discharge. Firstly, four different partial discharge pulse signals are analyzed by EWT method, and the fault signal is decomposed according to different frequency domain characteristics of the signal to obtain the intrinsic mode function (IMF) of the signal. Then, the calculated multi-scale permutation entropy of different IMFs to complete the fault feature extraction. Finally, the multi-scale entropy of the fault semaphore is used as the eigenvector of the Support Vector Machine (SVM) for glitch diagnosis, and the accurate systematization of the partial discharge semaphore of the transformer is realized. semaphore Compared with the Continuous Wavelet Transform (CWT), Empirical Mode Decomposition (EMD), and Ensemble Empirical Mode Decomposition (EEMD) feature extraction way, it shows that the raised EWT-MPE is more valid and accurate in diagnosing and analyzing transformer partial discharge faults, and the accuracy of fault classification 96.43%.

Fault Diagnosis Method Based on CND-SMOTE and BA-SVM Algorithm

The problem of unbalanced data classification has gotten extensive attention in the past few years. Unbalanced sample data makes the fault diagnosis and classification accuracy rate low, and the capability to classify minority-class fault samples is restricted. To address the problem that the classification algorithm in machine learning has the insufficient capability to identify minority class samples for unbalanced sample data classification problems. Therefore, this paper proposes an improved support vector machine (SVM) classification method based on the synthetic minority over-sampling technique (SMOTE). For the sampler, an improved synthetic minority over-sampling technique based on the characteristics of neighborhood distribution (CND-SMOTE) algorithm is used to equilibrate the minority class samples and the majority class samples. For the classifier, the parameter optimization method of support vector machines based on the bat algorithm (BA-SVM) is used to solve the multi-classification problem of faulty samples. Finally, experimental results prove that the CND-SMOTE+BA-SVM algorithm can synthesize high-quality minority fault samples, increase the classification accuracy rate of fault samples, and decrease the time spent on the classification.

PrismPatNet: Novel prism pattern network for accurate fault classification using engine sound signals

AbstractEngines are prone to various types of faults, and it is crucial to detect and indeed classify them accurately. However, manual fault type detection is time‐consuming and error‐prone. Automated fault type detection promises to reduce inter‐ and intra‐observer variability while ensuring time invariant attention during the observation duration. We have proposed an automated fault‐type detection model based on sound signals to realize these advantageous properties. We have named the detection model prism pattern network (PrismPatNet) to reflect the fact that our design incorporates a novel feature extraction algorithm that was inspired by a 3D prism shape. Our prism pattern model achieves high accuracy with low‐computational complexity. It consists of three main phases: (i) prism pattern inspired multilevel feature generation and maximum pooling operator, (ii) feature ranking and feature selection using neighbourhood component analysis (NCA), and (iii) support vector machine (SVM) based classification. The maximum pooling operator decomposes the sound signal into six levels. The proposed prism pattern algorithm extracts parameter values from both the signal itself and its decompositions. The generated parameter values are merged and fed to the NCA algorithm, which extracts 512 features from that input. The resulting feature vectors are passed on to the SVM classifier, which labels the input as belonging to 1 of 27 classes. We have validated our model with a newly collected dataset containing the sound of (1) a normal engine and (2) 26 different types of engine faults. Our model reached an accuracy of 99.19% and 98.75% using 80:20 hold‐out validation and 10‐fold cross‐validation, respectively. Compared with previous studies, our model achieved the highest overall classification accuracy even though our model was tasked with identifying significantly more fault classes. This performance indicates that our PrismPatNet model is ready to be installed in real‐world applications.

A CNN-Architecture-Based Photovoltaic Cell Fault Classification Method Using Thermographic Images

Photovoltaic (PV) cells are a major part of solar power stations, and the inevitable faults of a cell affect its work efficiency and the safety of the power station. During manufacturing and service, it is necessary to carry out fault detection and classification. A convolutional-neural-network (CNN)-architecture-based PV cell fault classification method is proposed and trained on an infrared image data set. In order to overcome the problem of the original dataset’s scarcity, an offline data augmentation method is adopted to improve the generalization ability of the network. During the experiment, the effectiveness of the proposed model is evaluated by quantifying the obtained results with four deep learning models through evaluation indicators. The fault classification accuracy of the CNN model proposed here has been drawn by the experiment and reaches 97.42%, and it is superior to that of the models of AlexNet, VGG 16, ResNet 18 and existing models. In addition, the proposed model has faster calculation, prediction speed and the highest accuracy. This method can well-identify and classify PV cell faults and has high application potential in automatic fault identification and classification.

Circuit Breaker Fault Diagnosis Method Based on Coil Current Time Sequence Phase Trajectory Characteristics

The traditional circuit breaker fault diagnosis method suffers from insufficient feature information extraction and is easily affected by abnormal signal acquisition. To address this, this paper introduces the phase space reconstruction algorithm to reconstruct the current signal for fault diagnosis based on phase trajectory features. The proposed method uses a first-order forward differencing method and mutual information method to process abnormal data and select the parameters of the reconstruction, then extract overall and local inflection point features to construct a fault feature set. The support vector machine algorithm-based model is trained and tested using actual samples, and the results show that the proposed method can adaptively sample anomalous signals, exhibit strong robustness, and significantly improve the accuracy of fault classification.

Fault detection and classification in DC microgrid clusters

With the rising popularity of DC microgrids, clusters of such grids are beginning to emerge as a practical and economical option. Short circuit problems in a DC microgrid clusters can cause overcurrent damage to power electronic devices. Protecting DC lines from large fault currents is essential. This paper presents a novel localized fault detection and classification technique for the protection of DC microgrid clusters. In this paper, a variational mode decomposition (VMD) and artificial neural network (ANN) based technique is proposed for accurate and effective fault detection and classification. This research aims to train an ANN that can detect and classify faults in DC microgrid clusters with multiple sources and loads by applying VMD to extract features of current signals. Different types of short circuit faults such as Pole to Pole and Pole to ground faults are considered under various grid operating conditions. The proposed method is capable of real-time fault detection and diagnosis, which can help prevent system failures and minimize downtime. The results indicate that the proposed approach is efficient and effective in detecting/classifying faults in DC microgrid clusters improving the reliability and system safety. The performance evaluation is carried out through rigorous case studies in MATLAB/Simulink environment to prove the efficacy of the proposed method. The VMD-ANN approach is shown to outperform other traditional signal processing techniques in terms of accuracy and robustness. Moreover, the proposed method is applicable to a wide range of DC microgrid clusters, making it a versatile and valuable tool for future research and development.

An intelligent protection scheme for series-compensated transmission lines connecting large-scale wind farms

Series-compensated transmission lines (SCTLs) are increasingly preferred for transmitting bulk amounts of electricity generated from the present-day large-scale wind farm to the utility grid due to several technical and economic benefits. However, when a fault occurs in such a wind farm-integrated SCTL, the impedance across the metal oxide varistor (MOV)-protected series capacitor varies non-linearly. Also, the fault current contributed from the wind farm side is quite different compared to the grid side. Consequently, the widely used fixed impedance-based distance relaying schemes showed limitations when used for protecting such crucial TLs. In this paper, the impacts of series compensation and wind farm integration on distance relay are investigated, and this paper proposes an intelligent relaying scheme using only the current measurements. In the proposed scheme, the fault detection task is performed using the signs of the half-cycle magnitude differences of the line end positive-sequence currents, and the fault classification task is performed using only the local current measurements processed through the Fourier–Bessel series expansion (FBSE) bagging ensemble (BE) classifier. The non-stationary components present in the current signal at the initiation of a fault are captured by calculating FBSE coefficients, and the singular value decomposition is applied for dimensionality reduction of the feature set. Finally, the extracted features are used by the BE classifier for fault classification. The method is evaluated in MATLAB/Simulink® on numerous fault and non-fault data simulated in two-bus systems and also validated through the OPAL-RT (OP4510) manufactured real-time digital simulation platform. The obtained results (response time for fault detection and classification <10 ms), including the comparative assessment results (fault detection accuracy =100% and fault classification accuracy =99.37%), justify the effectiveness of the proposed relaying scheme in protecting the wind farm-integrated SCTLs.

Fault diagnosis of EHA with few-shot data augmentation technique

As an emerging object in aerospace actuators, electro-hydrostatic actuator (EHA) has the advantages of heavy load capacity and high reliability. An EHA fault diagnosis method based on a few-shot data augmentation technique is proposed to diagnose and isolate possible faults. The sensitive parameters of typical failure modes are demonstrated based on the mathematical model of EHA. By converting multi-dimensional experimental data into two-dimensional grayscale data and extracting local features, the time series characteristics and correlation between different signals can be highlighted. The Wasserstein deep convolutional generative adversarial network (WDCGAN) is used to enhance the EHA small sample data. The diagnostic model WDCGAN-stacked denoised auto encoder (SDAE) combined with WDCGAN and SDAE is proposed to differentiate between multiple types of EHA failures. Compared with the five commonly used fault classification methods, the proposed method can effectively identify the typical fault modes of EHA, with the highest accuracy of fault classification and strong feature extraction ability.

A fault diagnosis method for building electrical systems based on the combination of variational modal decomposition and new mutual dimensionless

The fault diagnosis of building electrical systems are of great significance to the safe and stable operation of modern intelligent buildings. In this paper, it has many problems, such as various fault types, inconspicuous fault characteristics, uncertainty of fault type and mode, irregularity, unstable signal, large gap between fault data classes, small gap between classes and nonlinearity, etc. A method of building electrical system fault diagnosis based on the combination of variational mode decomposition and mutual dimensionless indictor (VMD-MDI) and quantum genetic algorithm-support vector machine (QGA-SVM) is proposed. Firstly, the method decomposes the original signal through variational modal decomposition to obtain the optimal number of Intrinsic Mode Function(IMF) containing fault feature information. Secondly, extracts the mutual dimensionless indicator for each IMF. Thirdly, the optimal penalty coefficient C of the support vector machine and the parameter gamma (gamma) in the radial basis kernel function are selected by the quantum genetic algorithm. Finally, SVM optimized by the QGA is used to identify and classify the faults. By applying the proposed method to the experimental platform data of building electrical system, and compared with the traditional feature extraction method Empirical Mode Decomposition (EMD), Singular Value Decomposition(SVD), Local Mean Decomposition(LMD). And compared with traditional SVM, Genetic Algorithm optimized Support Vector Machine (GA-SVM), One-Dimensional Convolutional Neural Network (1DCNN) for fault classification methods. The experimental results show that the method has better effect and higher accuracy in fault diagnosis and classification of building electrical system. Its average test accuracy can reach 91.67%.

A Novel Opposition-Based Border Collie Optimization Approach for Fault Detection in Solar Photovoltaic Array

Solar photovoltaic systems installed in outdoor environments are susceptible to faults and partial shading, which leads to reduction in the production of maximum power. The conventional protection units are unable to detect the types of faults due to non-linear characteristics and they result in fire hazards and reduced system efficiency. In this paper, a fault detection method based on Multiclass Support Vector Machine (MSVM) is proposed to detect different faults like line-ground (L-G), line-line (L-L), and partial shading. The array voltage, array current and irradiance are used to detect the line-line and partial shading under different irradiation conditions. The novel Opposition-based Border Collie Optimization (OBCO) algorithm is used to improve the accuracy of fault classification by optimizing the hyper-parameters of MSVM. A 1.6 kW, 4 × 4 solar photovoltaic array is developed, and the fault conditions are experimentally tested to validate the proposed algorithm. The experimental results show that the proposed MSVM-OBCO fault detection algorithm has higher accuracy compared to that of the existing classification algorithms such as k-nearest neighbor, Naïve Bayes, Decision Tree and Random Forest.

Research on an Improved Convolutional Neural Network Fault Diagnosis Method for Exciter System

ABSTRACT At present, China’s power grid has entered a new stage of ultra-high voltage, long-distance, large-capacity, large-unit, AC and DC hybrid interconnection grid, and the generator excitation system has an important impact on the stability of the power system. As the core component of the excitation system, the exciter plays a vital role in the safe operation of the excitation system. In view of the above problems, this paper proposes an improved CNN exciter fault diagnosis research method. To be able to learn more abundant fault features, this article first builds a dilated convolutions which is types of deep convolutional neural network (DCNN) to expand the receptive field of the convolution kernel. Then build the Pythagorean Spatial Pyramid Pooling Layer (PTSPP) to further enhance the feature information of the extracted samples. Finally, this article will generate two-dimensional matrix samples from the collected excitation voltage and excitation current signals for model training. The experimental results show that the proposed PTSPP-DCNN method has high classification accuracy in the fault diagnosis of the exciter system. The comparison results show that the fault classification accuracy of the proposed method is higher than other deep learning methods.

On-Line Fault Identification, Location, and Seamless Service Restoration using Transfer Learning-Based Convolution Neural Network for Low-Voltage DC Microgrid

DC microgrid over the last decade has gained a global paradigm in the power system field. Through the effective integration of distributed energy resources, significant researchers have improved its advantages over conventional power systems. The new state-of-the-art infrastructure despite its numerous advantages possess challenges in implementing an appropriate protection system. Impact of selecting a definite threshold for voltage and current compromises with the accuracy and speed of detection in conventional fault detection methods. Although many machine learning methods are successful in fault detection and classification for DC microgrid they still suffer from overfitting problems and exhaustively time-consuming. This article intends to provide an Online fault protection method for a LVDC microgrid system based on a transfer learning-based convolution neural network (TCNN). With the help of transient voltages and currents at different buses, image data for faults at different buses serves as input to the convolution neural network layer. First, the pre-trained Alex-Net CNN initializes the weights and biases for the targeted offline CNN’s. Secondly, the transferred layers from the offline CNN’s, initializes the online convolution neural network for real-time fault detection and classification. This work aims to accurately identify and locate the faults without complex dataset and multiple thresholds while improving accuracy of fault detection and classification. To ensure reliability of the system the recognized faulty bus reconnects to the healthy bus via sectionalizing circuit breakers through the detected signals. The proposed TCNN framework has an accuracy of 99.78%. The proposed method results when compared with state-of-the-art machine learning techniques such as SVM, LSTM, RNN, multilayer perceptron, and wavelet-based ANN showed better results in terms of accuracy and has significantly reduced data abundance.

Data-Mining Techniques Based Relaying Support for Symmetric-Monopolar-Multi-Terminal VSC-HVDC System

Considering the advantage of the ability of data-mining techniques (DMTs) to detect and classify patterns, this paper explores their applicability for the protection of voltage source converter-based high voltage direct current (VSC-HVDC) transmission systems. In spite of the location of fault occurring points such as external/internal, rectifier-substation/inverter-substation, and positive/negative pole of the DC line, the stated approach is capable of accurate fault detection, classification, and location. Initially, the local voltage and current measurements at one end of the HVDC system are used in this work to extract the feature vector. Once the feature vector is retrieved, the DMTs are trained and tested to identify the fault types (internal DC faults, external AC faults, and external DC faults) and fault location in the particular feeder. In the data-mining framework, several state-of-the-art machine learning (ML) models along with one advanced deep learning (DL) model are used for training and testing. The proposed VSC-HVDC relaying system is comprehensively tested on a symmetric-monopolar-multi-terminal VSC-HVDC system and presents heartening results in diverse operating conditions. The results show that the studied deep belief network (DBN) based DL model performs better compared with other ML models in both fault classification and location. The accuracy of fault classification of the DBN is found to be 98.9% in the noiseless condition and 91.8% in the 20 dB noisy condition. Similarly, the DBN-based DMT is found to be effective in fault locations in the HVDC system with a smaller percentage of errors as MSE: 2.116, RMSE: 1.4531, and MAPE: 2.7047. This approach can be used as an effective low-cost relaying support tool for the VSC-HVDC system, as it does not necessitate a communication channel.

Accurate Identification of Transformer Faults From Dissolved Gas Data Using Recursive Feature Elimination Method

Dissolved gas analysis (DGA) of insulating oils is one of the most popular methods to detect incipient faults in power transformers. However, appropriate feature selection is crucial for accurately detecting incipient faults using DGA data. Another issue is the unavailability of a balanced DGA dataset, which can hamper the fault classification accuracy. Considering these two issues, this article proposes a novel and accurate fault classification framework using gas ratios as features obtained from the DGA data of power transformers. The obtained unbalanced DGA data was initially balanced using the synthetic minority oversampling technique (SMOTE) in the data pre-processing stage. Following this, an efficient feature selection algorithm, namely, recursive feature elimination (RFE) was used to select the best possible features prior to the fault classification using three benchmark machine learning (ML) classifiers, namely, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula> -nearest neighbor (KNN), multiclass support vector machines (SVMs), and extreme gradient boost (XGBoost). The proposed classification model was tested on the DGA data obtained from the local power utility and on the benchmark IEC TC-10 database. Investigations revealed that the proposed classification model delivered detection accuracy of 98.84% and 97.43%, respectively. The proposed method may be reliably used to diagnose incipient faults in power transformers.

Trend Feature Consistency Guided Deep Learning Method for Minor Fault Diagnosis

Deep learning can be applied in the field of fault diagnosis without an accurate mechanism model. However, the accurate diagnosis of minor faults using deep learning is limited by the training sample size. In the case that only a small number of noise-polluted samples is available, it is crucial to design a new learning mechanism for the training of deep neural networks to make it more powerful in feature representation. The new learning mechanism for deep neural networks model is accomplished by designing a new loss function such that accurate feature representation driven by consistency of trend features and accurate fault classification driven by consistency of fault direction both can be secured. In such a way, a more robust and more reliable fault diagnosis model using deep neural networks can be established to effectively discriminate those faults with equal or similar membership values of fault classifiers, which is unavailable for traditional methods. Validation for gearbox fault diagnosis shows that 100 training samples polluted with strong noise are adequate for the proposed method to successfully train deep neural networks to achieve satisfactory fault diagnosis accuracy, while more than 1500 training samples are required for traditional methods to achieve comparative fault diagnosis accuracy.

Research Based on Improved CNN-SVM Fault Diagnosis of V2G Charging Pile

With the increasing number of electric vehicles, V2G (vehicle to grid) charging piles which can realize the two-way flow of vehicle and electricity have been put into the market on a large scale, and the fault maintenance of charging piles has gradually become a problem. Aiming at the problems that convolutional neural networks (CNN) are easy to overfit and the low localization accuracy in fault diagnosis of V2G charging piles, an improved fault classification model based on convolutional neural networks (CNN-SVM) is proposed. Firstly, the hardware adaptation optimization is carried out for the CNN structure, the wavelet packet transformation is used to extract the fault current signal feature information into the CNN, and the CNN-SVM model is constructed by SVM (Support Vector Machine) instead of the SoftMax classifier in the CNN. The PSO (particle swarm algorithm) is used to optimize the parameters of the SVM model to obtain the optimal model. Finally, the superiority of the proposed method is verified by multi-working cases. The experimental results show that the fault classification accuracy of the CNN-SVM model is far higher than that of the traditional deep learning network and has practical significance for fault diagnosis of the switch module of the charging pile.

Bearing Fault Diagnosis Using a Hybrid Fuzzy V-Structure Fault Estimator Scheme.

Bearings are critical components of motors. However, they can cause several issues. Proper and timely detection of faults in the bearings can play a decisive role in reducing damage to the entire system, thereby reducing economic losses. In this study, a hybrid fuzzy V-structure fuzzy fault estimator was used for fault diagnosis and crack size identification in the bearing using vibration signals. The estimator was designed based on the combination of a fuzzy algorithm and a V-structure approach to reduce the oscillation and improve the unknown condition's estimation and prediction in using the V-structure method. The V-structure surface is developed by the proposed fuzzy algorithm, which reduces the vibrations and improves the stability. In addition, the parallel fuzzy method is used to improve the robustness and stability of the V-structure algorithm. For data modeling, the proposed combination of an external autoregression error, a Laguerre filter, and a support vector regression algorithm was employed. Finally, the support vector machine algorithm was used for data classification and crack size detection. The effectiveness of the proposed approach was evaluated by leveraging the vibration signals provided in the Case Western Reserve University bearing dataset. The dataset consists of four conditions: normal, ball failure, inner fault, and outer fault. The results showed that the average accuracy of fault classification and crack size identification using the hybrid fuzzy V-structure fuzzy fault estimation algorithm was 98.75% and 98%, respectively.

A feasibility study of multi-mode intelligent fusion medical data transmission technology of industrial Internet of Things combined with medical Internet of Things

As a branch of the Internet of Things (IoT) dedicated to medical care industry, the Internet of Medical Things (IoMT) includes networking devices and applications for medical and health information technology applications. The IoMT still has many shortcomings, such as unstable information transmission, low accuracy of fault diagnosis and classification, and lack of anomaly detection capability. Therefore, this paper first comprehensively describes some relatively new research and popular background technologies of the Industrial Internet of Things (IIoT) and IoMT, and then, according to the functional requirements analysis of the intelligent data transmission system based on IoMT, we discuss in detail the problems of fault diagnosis and resource allocation faced in the IoMT model. An intelligent data transmission model is proposed to apply the wireless communication transmission technology of the industrial Internet of Things to the Internet of Medical Things scene. This model has the ability of high-quality data transmission, high accuracy accident diagnosis classification and real-time anomaly monitoring, which makes up for the shortcomings of traditional IoMT models. In particular, for the accident diagnosis and classification functions in this model, we innovatively adopt the multi-mode data fusion CNN algorithm. The experimental results show that the classification accuracy of the accident diagnosis results is effectively improved. Compared with other algorithms, this model with multi-mode data fusion CNN algorithm improves the data transmission rate, reduces the average data delay, and improves the real-time anomaly monitoring capability of IoMT without increasing the signal leakage rate, thus further improving the overall stability of IoMT.