Search

This paper proposes a fast protection scheme of a hybrid AC/DC distribution network based on features extraction of the decomposed signals. The signal decomposition is achieved using discrete wavelets transform (DWT). The proposed scheme offers three main functions, fast fault detection for both network sides, AC fault classification with the ability to identify the faulted phase/ phases, and protection coordination between AC and DC sides. In addition, the scheme is based on local measurement so no need for extra-cost for communication infrastructure. The absence of communication reduces the overall cost and, as a most important feature, it reduces the fault clearing time. The system is thoroughly analyzed under many types of faults in both AC and DC sides. Also, different disturbance conditions are considered which used in threshold determination. The simulation results show that the proposed protection scheme was not only able to protect the system but also it offers a generalized fast acting communication-less approach. [ABSTRACT FROM AUTHOR]

The presented paper introduces an accurate approach for detecting and classifying parametric or soft faults that affect analog integrated circuits. This technique is based on the use of machine learning algorithm to improve the accuracy and the performance of fault classification process. To achieve this, the real and imaginary frequency responses of output voltage and supply current of the circuits under test (CUT) are used to extract features for both normal and faulty cases. These features are then exploited to train machine learning classifiers, from which the selected one among its equivalents is the quadratic discriminant classifier since it allowed the highest average accuracy score. The faults to be investigated are parametric ones affecting resistors and capacitors values. The proposed approach is validated using three filters circuits that are Sallen-Key band-pass filter, four op-amp biquad high-pass filter, and a leapfrog filter circuit. Obtained results indicate a high classification average accuracy for all circuits that are undergone testing. The proposed approach has provided a highest classification accuracy level comparing to other research works. [ABSTRACT FROM AUTHOR]

The photovoltaic (PV) array is the most sensible element in PV plants, which is subject to different type of faults and defects. Thus, to keep these plants working efficiently they should be monitored and protected carefully. Some faults if they are not detected and isolated promptly they may lead to hazardous risks. The diagnosis of PV systems is widely addressed and recently machine learning (ML) and deep leaning (DL) methods drawn the attention of many researchers. Most applications of ML methods are based on the use of the I–V curves measurement, as enough information and features can be extracted from the curves, to detect and classify faults. These methods showed their capability to classify some faults, like line to line, degradation, disconnected PV modules, partial shading effect, and bypass diode faults. Another approach is based on the use of thermal or electroluminescence images of PV modules/arrays to detect and identify defects, such as hot spot, snails crack, and others. In this paper, different ML and ensemble learning (EL) methods are evaluated for fault diagnosis of PV arrays. The focus is mainly on the detection and classification of some complex faults that may affect the PV arrays, i.e., multiple faults, and faults with similar I–V curves, that are not evaluated before. The results showed the ability of the methods developed to detect faults with very good accuracy (classification rate = number of classified instances/total instances), within 99%, while the classification faults is done with an acceptable accuracy, within 81.73%. Through this study it is shown when really ML and EL methods should be used, and some recommendations, challenges and future directions in this topic are presented. [ABSTRACT FROM AUTHOR]

In this paper, a procedure aimed at the automatic extraction of the features from polymer electrolyte membrane fuel cell impedance spectra is proposed. An artificial neural network that is trained by exploiting the similarity learning concept has been used. The network learns the features of the impedance spectra and maps each of them into the embedding space by clustering them accurately and by emphasising differences among spectra corresponding to different faults. The siamese network structure is optimised and the quality of the learnt representation is evaluated by analysing the clusters obtained in the features space. The dataset of experimental spectra has been augmented in two different ways and the results are compared. The clustering quality of the proposed siamese network is compared with the one of other state of the art approaches. [Display omitted] • A Siamese Neural Network is used to analyse the impedance spectra of a PEM fuel cell. • The SNN is able to extract the features corresponding to each faulty condition. • Two different data augmentation approaches are used to train the SNN and their performance is analysed. • The approach is tested on a set of noisy impedance spectra. [ABSTRACT FROM AUTHOR]

• A principal component analysis (PCA)-based supervised machine learning (SML) method is developed. • PCA-based SML is proposed to enhance fault detection and diagnosis (FDD) of photovoltaic (PV) systems. • The developed FDD approach uses feature extraction and selection, and fault classification tools. • The detection performance is studied using several PV system faults. • The results show good diagnosis efficiency and higher classification accuracy in PV systems. Fault detection and diagnosis (FDD) in the photovoltaic (PV) array has become a challenge due to the magnitudes of the faults, the presence of maximum power point trackers, non-linear PV characteristics, and the dependence on isolation efficiency. Thus, the aim of this paper is to develop an improved FDD technique of PV systems faults. The common FDD technique generally has two main steps: feature extraction and selection, and fault classification. Multivariate feature extraction and selection is very important for multivariate statistical systems monitoring. It can reduce the dimension of modeling data and improve the monitoring accuracy. Therefore, in the proposed FDD approach, the principal component analysis (PCA) technique is used for extracting and selecting the most relevant multivariate features and the supervised machine learning (SML) classifiers are applied for faults diagnosis. The FDD performance is established via different metrics using data extracted from different operating conditions of the grid-connected photovoltaic (GCPV) system. The obtained results confirm the feasibility and effectiveness of the proposed approaches for fault detection and diagnosis. [ABSTRACT FROM AUTHOR]

Stacked auto-encoder (SAE)-based deep learning has been introduced for fault classification in recent years, which has the potential to extract deep abstract features from the raw input data. However, SAE cannot ensure the relevance of deep features with the fault types due to its unsupervised self-reconstruction in the pretraining stage. To overcome this problem, a stacked supervised auto-encoder is proposed to pretrain the deep network and obtain deep fault-relevant features from raw input data. In each supervised auto-encoder, informative features are learned from the input data with the goal that they can largely distinguish different fault types. By stacking multiple supervised auto-encoders hierarchically, high-level fault-relevant features are gradually learned from raw input data, which can improve the classification accuracy of the classifiers. The proposed SSAE is tested on the Tennessee–Eastman (TE) benchmark process and a real industrial hydrocracking process. The results show the effectiveness and flexibility of SSAE. • A stacked supervised auto-encoder is proposed to pretrain deep network and obtain deep fault-relevant features. • In each supervised auto-encoder, informative features are learned from the input data with the goal that they can largely distinguish different fault types. • High-level fault-relevant features are gradually learned from raw input data by hierarchically stacking multiple supervised auto-encoders. • High classification performance of the proposed method is validated on TE process and an industrial hydrocracking process. [ABSTRACT FROM AUTHOR]

Bearing is one of the most critical parts used in rotary machines. Bearing faults break down the mechanism where it is located. Moreover, the faults may cause to malfunction by spreading to the entire system. Thus this may result in catastrophic failure eventually. Precise and decisive feature extraction from the raw vibration signal maintains to be one of the current topics explored for fault diagnosis in bearings. In this study, vibration signals are obtained from bearings which are formed with artificial faults of specific dimensions from a bearing test setup. Instead of employing traditional feature extraction methods found in the literature, a novel feature extraction method for bearing faults called one-dimensional ternary pattern (1D-TP) is applied. The proposed approach is a statistical method that uses patterns obtained from comparisons between neighbors of each value on vibration signals. The study aims to identify the size (mm) of the fault by determining the bearing part (inner ring, outer ring, ball) from which the faults in the bearings are caused. Several classification techniques were performed by using ternary patterns with RF (Random Forest), k-NN (k-nearest neighbor), SVM (Support Vector Machine), BayesNet, ANN (Artificial Neural Networks) models. As a result of analyzing the signals obtained from the experimental setup with the proposed model, 91.25% for dataset_1 (different speed), 100% for dataset_2 (fault type — inner ring, outer ring, ball) and 100% for dataset_3 (fault size (mm)) success rates are determined. • A novel approach is proposed to extraction of features from bearing signals. • One advantage is that this method uses all data points for feature extraction. • It is fast and can be use in real-time application. • High accuracies achieved for bearing fault classification. • Original data (Experimental setup of authors). [ABSTRACT FROM AUTHOR]

This paper presents a non-unit protection scheme for series capacitor compensated transmission lines (SCCTL) using discrete wavelet transform and k-nearest neighbor (k-NN) algorithm. All the protective relaying functions such as fault detection, fault classification, faulty phase identification and fault location estimation have been considered in this work. Such a comprehensive work providing all protective relaying functions for protection of double circuit SCCTL utilizing k-NN has not been reported so far. The signal processing and feature extraction are done using discrete wavelet transform due to its capability to differentiate between high and low frequency transient components. For fault detection and classification, only approximate wavelet coefficient of current signal up to level 1 has been used; while for k-NN location estimation, both voltage and current signals of the two circuits are decomposed up to level 3 have been used. Finally, the standard deviation of one cycle pre-fault and one cycle post-fault samples of the approximate wavelet coefficients are calculated to form the feature vector for the k-NN-based algorithm. The performance of the proposed technique is evaluated for large number of fault events with variation in fault type including inter-circuit faults, fault inception angle, fault location and fault resistance. The change in position of series capacitor and different degree of compensation has been discussed. The accuracy of the proposed k-NN-based fault detection and classification module is 100% for all the tested fault cases with a decision period of less than half cycle. The k-NN-based fault location scheme estimates the location of fault with ≤1% error for most of the tested fault cases, which is an exceptional attribute of the proposed scheme as compared with 10–15% error of conventional distance relaying scheme. [ABSTRACT FROM AUTHOR]

Several methods for the location and classification of faults in power transmission lines using computational intelligence and digital signal processing techniques have been described in literature. Artificial neural networks (ANNs) and wavelet transform (WT) have drawn significant attention lately, but they present some drawbacks when dealing with power systems faults where data are often contaminated by noise. This paper proposes an approach by combining independent component analysis (ICA) with travelling wave (TW) theory and support vector machine (SVM). The approach is adequate to locate and recognize faults in high-voltage (HV) transmission lines, while the acquired signals are noisy. Experiments performed for distinct types and locations of faults in a real transmission line model have shown that the proposed combined methods are able to provide excellent performance in fault location. The obtained errors are lower than 1% and accuracy is 100% for the classification of fault signals with noise. It can be stated that this method presents better performance than those regarding the main conventional techniques such as wavelets and neural networks in the presence of noise. [ABSTRACT FROM AUTHOR]

• A hybrid data-scaling method combining Min-max and Box-Cox transformation was proposed. • It yields accurate fault classification for unbalanced and multi-domain data in industrial fields. • The health index evaluates classification difficulty before generating complex classification models. • Various scaling methods were compared using box plots and t-SNE for selected feature values. • Various classification models (SVM, RF, KNN, and XGBoost) were compared. Fault diagnosis of compressors in air conditioners is challenging owing to the imbalance and nonlinearity of the vibration data because of the contrasting failure modes. This study proposes a hybrid data-scaling method combining Min-Max normalization and Box-Cox transform methods. The Min-Max normalization method was employed to scale the multi-domain data with different failure modes whereas the Box-Cox transformation method transformed the nonlinear distributions of features into normal distributions, thereby rendering the classification of unbalanced and insufficient data easier. The primary features for fault diagnosis were extracted using an embedded feature extraction method and were consequently used to generate fault classification models such as support vector machine (SVM), K-nearest neighbor (KNN), random forest (RF), and extreme gradient boosting (XGBoost) to classify refrigerant deficiencies and motor demagnetization defects. The proposed hybrid data-scaling demonstrates the most accurate and robust classification performance relative to conventional data-scaling methods, regardless of the types of classification models. [ABSTRACT FROM AUTHOR]

Since industrial process data often presents strong correlations, high complexity, and nonlinear patterns, a proficient deep learning model is required for the fault classification task. Recent researches have shown that deep learning models like stacked autoencoder (SAE) are able to learn deep abstract features from complex process data. Nevertheless, a traditional SAE cannot extract the informative fault-relevant features and data distribution features from industrial process data, which are necessary for effective fault classification in industrial processes. Thus, this study proposes a semi-supervised Inter-Relational Mahalanobis SAE (IRM-SAE) model to learn inter-relational distribution and fault-relevant dynamic features of process data for fault classification. First, the Inter-Relational Mahalanobis loss is introduced into the original objective function of SAE to learn meaningful inter-relational distribution features within the data. Then, an active time frame technique is developed to preprocess the input data to capture the dynamic features of the data. Furthermore, to fully utilize both labeled and unlabeled data in industrial processes, the semi-supervised strategy is introduced to learn fault-related features for better fault classification. To validate the performance of the proposed model, it is applied on the Tennessee–Eastman process and a real-world industrial hydrocracking process. The experimental results show that the proposed model has higher fault classification performance compared to other deep learning models. • A novel semi-supervised Inter-Relational Mahalanobis SAE (IRM-SAE) model is proposed to learn inter-relational distribution and fault-relevant dynamic features of process data. • An active time frame technique is developed to preprocess the process data to capture the dynamic features of the data. • To fully utilize both labeled and unlabeled data in industrial processes, the semi-supervised strategy is introduced to learn fault-related features for better fault classification. • The experimental results on two industrial processes show that the proposed model has higher fault classification performance compared to other deep learning models. [ABSTRACT FROM AUTHOR]

• A new deep learning method called Sparse Probabilistic Dynamic Network (SPDN) is proposed, which is based on Gaussian-Bernoulli Restricted Boltzmann Machine and the Long-Short Term Memory. • The proposed method takes into account the nonlinear and dynamic characteristics in process data, and deeply extracts the potential information in it. • The proposed method can obviously improve the classification accuracy in the case study. The dynamic and nonlinear characteristics of process data have become the major issue in data-driven process monitoring. Traditional data-driven methods are often only able to extract a single feature in process data. Therefore, how to effectively extract multi-dimensional features has become the focus of current research. Sparse probabilistic dynamic network (SPDN) is a deep learning model proposed in this paper for the purpose of fault classification. The method mainly takes the advantages of the sparse Gaussian-Bernoulli Restricted Boltzmann Machine (GRBM) and the recurrent neural network (RNN) with long-short term memory (LSTM) units. First, the sparse GRBM is used for nonlinear feature extraction in an unsupervised way. Then, LSTM is introduced to realize the modeling of sequence data which can effectively handle the dynamic feature of the data. In the Tennessee-Eastman benchmark process, the classification accuracies of the proposed method are proved to be far superior to MLP, RNN and PDN. Meanwhile, in order to prove the influence of the data dynamics and the internal parameters of the structure on the fault classification results, two additional experiments were carried out. [Display omitted] [ABSTRACT FROM AUTHOR]

Diagnosis aims at predicting the health status of components and systems. In photovoltaic systems, it is vital to guarantee energy production and extend the useful life of photovoltaic power plants. Multiple prediction and classification algorithms have been proposed for this purpose in the literature. The accuracy of these algorithms depends directly on the quality of the data and the features with which they are tuned or trained. In this paper, an innovative approach for predicting the health status of photovoltaic systems is proposed, which includes a feature selection stage. This approach first discriminates severely affected photovoltaic panels using basic electrical features. In a second step, it discriminates the other faulty panels using more elaborated time–frequency features and selecting the most relevant features through correlation and variance analysis. Finally, the approach predicts the health status of photovoltaic panels using a nonlinear regression method named partial least squares. This later is then combined with linear discriminant analysis and compared. The approach is validated with real current data from a photovoltaic plant composed of twelve photovoltaic panels with power between 205 and 240 Wp in three health states, namely broken glass, healthy, and big snail trails. The results obtained show that the proposed approach efficiently predicts the three health states. It determines the level of degradation of the panels, which indicates priorities to corrective and predictive maintenance actions. Furthermore, it is cost-effective since it uses only electrical measurements that are already available in standard photovoltaic data acquisition systems. Above all, the approach is generic and it can be easily extrapolated to other diagnosis problems in other domains. [ABSTRACT FROM AUTHOR]

• A novel accommodative random weighted fusion algorithm is proposed. • More feature information can be retained by using BB-1D-TP feature extraction. • A new gear fault diagnosis method is constructed with high accuracy. As an essential component of a gearbox, gears can damage a structure or even an entire gear transmission system in case of failures. As a result, advanced fault diagnosis methods are crucial to system's operation. Currently, single-signal-driven gear fault diagnosis techniques have been applied in many fields, but multipath noise and single-sensor sampling errors inevitably affected the accuracy of diagnosis. This paper proposes a gear fault diagnosis method based on a novel accommodative random weighting theory and a balanced binary one dimension ternary pattern (BB-1D-TP) model. It can accurately diagnose the types of gear failures under the circumstances of multiple channels and strong background noise. The novel accommodative random weighting algorithm reduces the total mean-square error (MSE) by adaptively adjusting the proportional connection between a measured value at a present state and a historical state. Then the balanced binary algorithm extracts texture features of fault signals for signal enhancement. In the end, the classification is done by using Support Vector Machine (SVM) method. The result of experiments demonstrated that the method in this article effectively improves accuracy and efficiency of gear fault identification. [ABSTRACT FROM AUTHOR]

Highlights: [•] A new method for multi-damage extraction and classification of gear system is proposed. [•] Using PCA and KPCA to extracte the signal feature of gear system. [•] Five kinds of fault signal are analyzed under 300rpm, 900rpm, 1200rpm and 1500rpm. [•] Proposed method can be used to identify various faults (multi-fault) and damage level. [Copyright &y& Elsevier]

Highlights: [•] We present a fault diagnosis expert system for newly assembled auto transmission. [•] Synchronous data acquisition algorithm of the vibration signal and the speed signal. [•] Improved FFT algorithm which is used for spectral transformation after a lot of tests. [•] Knowledge representation and knowledge renew algorithm for transmission. [•] Improved genetic algorithm for feature selection and fault classification with BP network. [Copyright &y& Elsevier]

Abstract: This article studies if machine faults can be effectively determined in a reduced dimensional space. When faults occur in machines, machine vibration signals will deviate from its normal signal pattern. Such changes can be reflected in the features constructed from the machine signals. In this article, 13-dimension feature data set is constructed to represent different health conditions of machines, and unsupervised learning algorithms are introduced to deal with feature data sets for feature extraction and fault classification. A weighted local and global regressive mapping (WLGRM) algorithm is proposed for machine fault classification. Two synthetic fault data sets and two experimental data sets are employed to validate the effectiveness of the proposed approach. Comparative analysis with other unsupervised learning algorithms, such as local and global regressive mapping, locality preserving projection, Isomap, principal component analysis, and Sammon mapping, are reported. The results show that different machine faults can be classified, the degree of fault severity can be captured, and WLGRM can achieve better performance than other algorithms in most cases of machine fault classification. [Copyright &y& Elsevier]

Worm gearboxes (WG) are frequently used in many areas of the industry. WG is different from other gearbox types and due to their working principles they are under high risk of wear and fault. Therefore, detection of faults that may occur in WG and taking measures accordingly are especially important for systems and facilities that require uninterrupted operation. This paper introduces an intelligent feature selection and classification method for fault diagnosis of WGs under different working conditions. The novelty of the study lies in the selection of feature sources and different loading and speed conditions for condition monitoring studies of WGs experimentally. Fault detection and classification were performed based on vibration, sound and thermal images data which were acquired and processed from the healthy and the faulty WG. Apart from classical studies, time and frequency domain features and thermal images features were extracted and evaluated singularly, dual or triple forms with ANN (Artificial Neural Network) and SVM (Support Vector Machines) classifiers. Reasonable classification performances for fault detection were observed when the features of all three sources used (99.2% with ANN and 98.7% with SVM). ANN and SVM classification performances are almost equal for fault classification (98.9% with SVM and 98.6% with ANN). The findings of the study would be a possible means for online condition monitoring of industrial plants, conveyors, elevators, etc. [ABSTRACT FROM AUTHOR]

The Open Circuit (OC) faults occurring in switches of Multilevel Converters (MLC) may lead to undesirable operation of the converter. Therefore, fault detection and its localization in minimum time are necessary. This paper focuses on the fast fault detection algorithm based on the two samples technique and the fault localization algorithm using the Entropy of Wavelet Packets (EWP) as a feature. The EWP feature is used to classify and localize the OC faults in Insulated Gate Bipolar Transistors (IGBTs) of three-phase, three-level inverter using Support Vector Machine (SVM) based fault classification algorithm. The proposed technique can detect the fault in single IGBT and multiple IGBTs in a lesser time range of microseconds to 0.33 ms. It gives better performance and accuracy (99.70%) than previously proposed SVM algorithms, as the EWP-based feature extraction process used in this paper is simple and accurate with a less computational burden. [Display omitted] • An observer-based algorithm is proposed using two samples-based technique. • The Entropy of Wavelet Packets (EWP-SVM) technique is used for fault diagnosis. • The proposed algorithm can detect the faults in a single IGBT and multiple IGBTs. • The technique is faster and accurate than techniques available in the literature. • The comparison of detection time of different techniques is also discussed. [ABSTRACT FROM AUTHOR]

This work deals with robust dynamic probabilistic modeling and fault classification for process data. In dynamic processes, observed variables can be numerous in amount and correlated with each other in both variable-wise and time-wise. While multivariate statistical analysis methods such as principle component analysis (PCA) are widely used to handle variable-wise correlations and also for dimension reduction purpose, the time-wise correlation among process data is typically addressed by constructing dynamical models, e.g. time-series data model, state space model, etc. In this paper, the robust probabilistic principle component analysis (RPPCA) model is introduced for feature extraction from contaminated process data, suffered from outliers, disturbances, heave noises, etc. A dynamic Bayesian network (DBN) is then constructed, with incorporation of a mixture of Gaussian components for approximation of the non-Gaussian characteristics of latent variables. Based on the developed robust dynamic Bayesian network model, a fault classification scheme is proposed. To validate the effectiveness and feasibility of the new method, two well-known benchmark case studies are carried out. Simulation results show that robust dynamic method performs better in outlier contaminated situations, where the performance has been improved by 10%–20% in most cases. [ABSTRACT FROM AUTHOR]