Search

This paper presents an innovative approach to detect solar panel defects early, leveraging distinct datasets comprising aerial and electroluminescence (EL) images. The decision to employ separate datasets with different models signifies a strategic choice to harness the unique strengths of each imaging modality. Aerial images provide comprehensive surface-level insights, while electroluminescence images offer valuable information on internal defects. By using these datasets with specialized models, the study aims to improve defect detection accuracy and reliability. The research explores the effectiveness of modified deep learning models, including DenseNet121 and MobileNetV3, for analyzing aerial images, and introduces a customized architecture and EfficientNetV2B2 models for electroluminescence image analysis. Results indicate promising accuracies for DenseNet121 (93.75%), MobileNetV3 (93.26%), ELFaultNet (customized architecture) (91.62%), and EfficientNetV2B2 (81.36%). This study's significance lies in its potential to transform solar panel maintenance practices, enabling early defect identification and subsequent optimization of energy production. [ABSTRACT FROM AUTHOR]

This paper investigates hall sensor signal unbalancing faults in sensored Brushless Direct Current (BLDC) motor drives and presents a fault effect minimization scheme for implementation in motor controller without any modification in system architecture, or core commutation method. In the proposed scheme detection, classification, and estimation of fault extent are carried out separately at the start of controller itself for subsequent corrections without involving issue of repetitive error estimation and finding valid reference signal separately for correcting inverter switching mistiming, as required in classical methods. The categorization part of scheme maps the faults with corresponding hall sensors. The proposed scheme is validated in MATLAB/Simulink model. It is tested on experimental test bench of controller and 1 kW BLDC motor of an electric rickshaw, along with another technique based on least square method (LSM) for performance comparison. Results show reduction of peak-to-peak value by 30% and ripple content by 50% in phase currents, and peak-to-peak reduction of 47% with 29% lesser ripple content in DC link current by using the presented scheme. The observed increment in efficiency is 0.8% and 2% in nominal torque/ampere at 30% load. At 100% load, increase of 2.2% efficiency and 9% nominal torque/ampere are observed. The increased memory loading of controller is estimated to be 1.25 times as compared to normal run without any correction scheme. Approximately 24% of this additional loading is utilized for repetitive calculations as compared to 63% in the other LSM based scheme, resulting in lesser run time loading of controller. The transient response with sudden load change shows better response with implementation of the proposed scheme in controller. [ABSTRACT FROM AUTHOR]

Distribution system voltage profile management at each bus and fault detection and classification are often challenged by complex and changing network configurations. The distribution system voltage profile improvement issue is addressed by placing distributed generation (DG) units at different locations in the network. By placing the DG units at appropriate places in IEEE 33 bus radial distribution networks by a proposed reinforcement learning (RL) algorithm, the voltage profile of each node is improved and power loss in the network is minimized. There is a 69% reduction in active power losses compared to losses without DG. Furthermore, an innovative method for fault detection and classification is developed that uses a convolutional neural network (CNN) cascaded with a long short-term memory network (LSTM) and attention mechanisms (AMs). To extract dynamic information from the data, phasor measurement units (PMUs) placed on different buses are used as input for the CNN architecture. AM strengthens important information. A mapping weight and parameter learning approach allows AM to assign different weights to concentrate on LSTM characteristics and improve learning accuracy. Low and high impedance faults are tested as well as various non-faulty events. The scheme's performance is compared with that of other deep learning techniques through reliability analysis, and the time taken for fault detection (FD) is also determined. [ABSTRACT FROM AUTHOR]

This paper presents a comprehensive analysis of failures in low-voltage terminal connections within power transformers and proposes a fault classification methodology based on infrared thermography (IRT). Low-voltage terminal connections play a critical role in the reliable operation of power transformers, and their failures can lead to severe operational issues. In this study, we employ IRT as a noninvasive and efficient diagnostic tool to identify and classify various types of failures, including loose connections, overheating, and corrosion. The research involves the collection of infrared thermograms (IRT images) from the low-voltage terminals of power transformers under different operating conditions. The proposed methodology demonstrates its effectiveness in detecting and classifying low-voltage terminal connection failures, thereby enabling timely preventive maintenance and minimizing the risk of transformer malfunctions. This research contributes to enhancing the reliability and longevity of power transformers, reducing downtime, and optimizing maintenance practices in the power industry. [ABSTRACT FROM AUTHOR]

This paper proposes a novel unsupervised classification method to solve the problem of mechanical fault diagnosis under the condition of unknown number of fault types. The proposed method combining the three data processing stage. First, the deep encoding neural networks is used to complete the abstract signal feature representation under the unsupervised conditions. Second, the feature dimensionality reduction technique based on manifold learning is used to complete the low-dimensional mapping of the feature space. Third, the spatial clustering based on density criterion is introduced to classify the different fault samples. This paper uses two fault signals dataset to complete the performance verification experiment. The experimental results show that the DMDUC method respectively achieves the classification accuracy of 99.7 % and 100 % on the two datasets. [ABSTRACT FROM AUTHOR]

Purpose: The global interest of developing monitoring system is increasing due to the continuous challenges in reliability and accuracy. Automatic fault detection and diagnosis of rotating machinery play an important role for the high efficiency and reliability of modern industrial systems. The key point of having high accurate automatic model for fault detection and diagnosis is obtaining defect features and choosing a representative approach for the model. Methods: In this paper, a model is developed based on Mel Frequency Cepstral Coefficients (MFCC) and gammatone cepstral coefficients (GTCC) that are computed for the input signal frames. Additionally, two global representations (feature concatenation and feature statistics) are adopted to feed Support Vector Machine (SVM) and a temporal representation is used with Long Short-Term Memory (LSTM) and Echo State Network (ESN) classification models. To generalize the proposed model, the experiments are evaluated based on two different datasets (PHM09 and DDS), where the PHM09 contains samples of helical and spur gears while the DDS contains samples from parallel and plenary gearboxes. Results: The results show that the proposed SVM model based on feature concatenation can effectively detect faults from gears and outperforms the other existing methods in the state-of-the-art studies. Conclusion: Base on the result of this paper, a global representation by concatenating frame-based features outperforms global statistical and time-series feature representations. [ABSTRACT FROM AUTHOR]

Accurate bearing fault classification is essential for the safe and stable operation of rotating machinery. The success of Machine Learning (ML) in fault classification is mainly dependent on efficient features and the optimal pre-defined hyper-parameters. Various hyper-parameter optimization (HPO) methods have been proposed to tune the ML algorithms' hyper-parameters in low dimensions but ignore the hyper-parameters of Feature Engineering (FE). The hyper-parameter dimension is high because both FE and the ML algorithm contain many hyper-parameters. This paper proposed a new HPO method for high dimensions based on dimension reduction and partial dependencies. Firstly, the whole hyper-parameter space is separated into two subspaces of FE and the ML algorithm to reduce time consumption. Secondly, the sensitive intervals of hyperparameters can be recognized by partial dependencies due to the nonlinearity of the relationship between the hyperparameters. Then HPO is conducted in intervals to acquire more satisfactory accuracy. The proposed method is verified on three OpenML datasets and the CWRU bearing dataset. The results show that it can automatically construct efficient domain features and outperforms traditional HPO methods and famous ML algorithms. The proposed method is also very time efficient. [ABSTRACT FROM AUTHOR]

This paper presents an efficient approach to estimate the failures of various components in an induction motor using motor current signature analysis. Conventional sensor-based fault detection methods lead to huge manpower and require greater number of sensors. To overcome these drawbacks, current signature base fault detection is proposed. An advanced spectral analysis, namely discrete wavelet transform (DWT), is used for frequency domain analysis. This paper also presents fault severity estimation using feature extraction-based evaluation of DWT coefficients. As the DWT gives many coefficients at higher level decomposition which is essential for high resolution, fault classification and severity index become challenging. To address this issue, artificial neural network (ANN) algorithm is used after DWT decomposition. The fault severity is predicted by proposed fault indexing parameter of various features like energy, standard deviation, skewness, variance, RMS values. Conventional algorithms like support vector machine, k‐nearest neighbour, local mean decomposition-singular value decomposition and extreme learning machine have given maximum of 98–99% accuracy, Whereas the proposed DWT-based ANN has given 100% accuracy with tanh function. Moreover, the testing loss with this function is also very less. Experimental results have affirmed the accuracy of proposed fault detection of various faults in induction motor of rating 3—Phase, 1. 5KW, 440 V and 50 Hz. [ABSTRACT FROM AUTHOR]

Nowadays, solar photovoltaic plays as a major alternative non-conventional energy source to meet the increasing load demand. However, for the implementation of these solar plants in the field, the requirement of the land area is very large which reflects in the installation cost. In addition, the effective performance of SPV depends on atmospheric conditions such as temperature and wind speed. Thus, in recent literature, floating-based SPV plants are in the limelight where these plants are mounted on water bodies like reservoirs and irrigation channels instead of land. In this system, the generated power at the SPV plant is transferred to the offshore bank via direct current cable and finally connected to the grid. Moreover, the unavoidable low value of DC leakage current flow through the conductive buried infrastructure/metallic pipeline system can be negligible under normal condition. Nevertheless, under transient conditions, the flow of DC leakage current will be enhanced and it causes the corrosion of surrounding metallic structures such as pipelines. Further, it leads to serious problems on a long-term basis. Therefore, in this work, a fuzzy-based relaying technique is proposed to detect and classify the faults occurring at the grid side by estimating the DC leakage current at cables. To evaluate the performance of the proposed technique, the simulation tests are performed on a 25 kV grid-connected floating SPV system (100 kW and 300 V). The simulation results show the effectiveness of the proposed technique under various symmetrical and asymmetrical faults. [ABSTRACT FROM AUTHOR]

This work proposes a systematic approach to detect and classify bearing faults using vibration signals under varying speeds. The proposed approach consists of several steps, such as segmentation of signal consisting of maximum fault relevant information and extraction of features less influenced by varying speeds, and develop a machine learning model for online classification of bearing faults. Bearing when operating under time-varying speeds, the most critical and challenging step, is the demodulation of non-stationary and nonlinear vibration signals exhibiting severe modulations. The empirical wavelet transformation (EWT) algorithm has been used to decompose the raw signal into multiple mode functions (MFs), thereby detecting faults. However, these MFs contaminated by vestigial noise, when processed, mislead the detection of incipient bearing faults, thereby reducing EWT performance. Hence, this study addresses this by proposing the selection of the most impulsive MF for varying speed by estimating instantaneous frequency, which lies near bearing characteristic defect frequencies, thereby eliminating the possibility of vestigial noise being processed. Further, ten entropies, root-mean-square, and kurtosis are computed from the selected MF for statistical analysis. The results of the proposed approach are compared with the ensemble empirical mode decomposition to highlight the capabilities. Statistically significant fault discriminating features are identified using the Kruskal–Wallis test. These identified features are subsequently utilized by the Random Forest classifier. Thus, it has resulted in higher accuracy in detecting and classifying the different faults trapped by severe modulations. [ABSTRACT FROM AUTHOR]

This paper covers the basics of fault diagnosis in wireless sensor networks, as well as fault diagnosis terminology, sensor fault classification, causes and effects, and fault diagnosis performance metrics. In recent years, it has been observed that a large variety of fault diagnosis techniques have been proposed by researchers. The existing fault diagnosis methods for sensor networks can be divided into three categories: centralised, distributed, and hybrid approach. This paper gives a detailed review of state-of-the-art wireless sensor network fault diagnosis approaches. It specifically discusses some existing automated fault detection and diagnosis approaches in wireless sensor networks, as well as their benefits and drawbacks. [ABSTRACT FROM AUTHOR]

In condition monitoring, accurate fault identification is an essential task for designing a proper maintenance strategy. Misalignment is one of the main faults in rotary machinery, because 70% of the failure occurs due to misalignment. Conventionally, the diagnosis of misalignment is carried out through vibration measurements. Especially, the presence of strong 2x vibration peak is generally accepted. Both angular and parallel misalignment shows peak at 2x, therefore, distinguishing misalignment type by using vibration signals alone is a difficult activity. This paper discusses classification of misalignment i.e., angular and parallel by using a diagnostic medium such as the acoustic emission and the rotor vibration signal. Vibro-acoustic sensors are used to collect data from the misaligned rotor system at two different loading, three different speed and three defect severity conditions. Time domain features are extracted and graded according to their significance using t test (One-way ANOVA) technique. Extracted features are used to train different algorithms. The outcome obtained using support vector machine (SVM) is 100% accurate. Vibro-acoustic sensor data fusion technique is employed to classify various forms of misalignment under different operating conditions. This work also intended to explore using a small amount of training data using different algorithms. The proposed method outperforms fault classification using vibration signal and acoustic signal separately. [ABSTRACT FROM AUTHOR]

Copyright of Frontiers of Information Technology & Electronic Engineering is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Background: Misalignment is one of the major reasons for rotating machinery breakdown. Conventionally, misalignment diagnosis is done by the occurrence of a strong peak at 2x running speed is widely accepted. Purpose: Both angular and parallel misalignment type display peak at 2x running speed, so it is difficult to discern the form of misalignment by using vibrational signal alone. This study addresses classification of misalignment faults (parallel, angular, and combined) by using a diagnostic medium by vibration signal and acoustic emission. Methods: The vibro-acoustic sensors are utilized to capture data with different speed and defect intensity conditions for misaligned rotor system. Time domain features are extracted, and features are ranked using t test (One-way ANOVA). Ranked features are used to train different machine learning algorithms. Results: The investigation shows the vibro-acoustic sensor data fusion as an efficacious tool for misalignment fault classification. This work also intended to carry out fault classification using a small amount of training data by employing different algorithms. Conclusion: The proposed method of misalignment fault classification provides better and reliable results than fault segregation using vibration and acoustic signals separately. [ABSTRACT FROM AUTHOR]

Purpose: To improve the recognition accuracy of the existing fuzzy entropy method for bearing fault signals, a novel processing method by combining improved refined composite hierarchical fuzzy entropy (IRCHFE) and least square support vector machine (LSSVM) is proposed. Methods: In this method, an improved refined composite hierarchical analysis applies to solve the problems of incomplete extraction of the existing multi-scale fuzzy entropy (MFE) fault information, inaccurate estimation of the entropy value of the hierarchical fuzzy entropy (HFE), and the inability of the hierarchical analysis to handle arbitrary data lengths. First, the IRCHFE method applies to extract fault information from the vibration signal. Then, LSSVM effectively recognizes and classifies the extracted fault information. Furthermore, the application of PSO to adjust the parameters of LSSVM increase classification accuracy. Results: The superiority of the IRCHFE-LSSVM method is verified by the bearing experimental data of Case Western Reserve University and Paderborn University. The experimental results show that the IRCHFE-LSSVM has a fault recognition accuracy of 100%. The comparative experiment results display that the proposed IRCHFELSSVM method is superior to MFE-LSSVM and HFE-LSSVM in identifying bearing fault types. Conclusions: The combined method of IRCHFE and LSSVM for fault diagnosis can provide certain guidance for the engineering application of fault diagnosis. [ABSTRACT FROM AUTHOR]

Overhead transmission lines are the most vulnerable components in electrical power systems. Therefore, to improve the electrical system availability and reliability, fault location should be performed as quickly and accurately as possible. This procedure consists of several steps, including fault detection and classification, which are essential to successfully locate the fault. Due to the importance of these two steps in protection schemes, different approaches have been proposed recently, such as algorithms based on Fourier Transform, Wavelet Transform, Statistical and Artificial Intelligence Techniques. Although they are all promising, they require complex formulations or high computational efforts. This paper proposes a method based on the Euclidean distance measure to perform the fault detection and classification functions, only by using voltage signals from the transmission line ends. The proposed method is simple and robust, not requiring complex formulation or significant computational effort. A large number of tests were performed, considering the power system under different operational conditions and fault characteristics such as fault resistance and fault inception angle, among others. The observed results showed that the proposed method is capable of accurately detecting and classifying faults, regardless of the power system condition or fault characteristic. The comprehensiveness and applicability of the proposed method was confirmed by means of two different transmission lines (line parameters, voltage level, and AC equivalent systems). [ABSTRACT FROM AUTHOR]

In the outdoor erected overhead transmission lines, the probability of occurrence of a fault is high and it might lead to unstable operation of the power system and interrupt the continuity of power supply. This work has proposed a methodology to detect and classify such transmission line faults based on the signs of computed reactive power. The sign of reactive powers at both ends of the transmission line is computed through the extracted fundamental components of voltage and current obtained through the DFT algorithm. The discrimination of fault and normal operating conditions is achieved based on the signs of reactive power at both ends of the transmission line. Further, a transmission line fault classification strategy has been developed with the signs of computed reactive power. The method developed has been tested on the designed two-machine transmission test system and modified WSCC-9 bus test system in the PSCAD/EMTDC and MATLAB tools for all types of short circuit faults at various locations on the transmission line, with and without fault resistance, sudden change in load, with noisy input signal, CT saturation conditions, etc. In all the cases, the proposed method ensures the accuracy of detecting and classifying transmission line faults. [ABSTRACT FROM AUTHOR]

A transmission line fault classification scheme is proposed in this article using Poincaré-based correlation analysis of three-phase fault currents. The method segments each fault signal into two equal time-split components and computes correlation coefficient between these two time-split signals. The fault current signals of the directly affected line(s) observe an abrupt monotonic rise, compared to the indirectly affected phases. This sudden rise in magnitude is expressed with correlation coefficients between the two almost consecutive time-split components of signal, time shifted by delay index. This method emphasizes this monotonic nature of increment of the fault current, enabling prompt fault detection. Further analysis of three phases of fault signals independently yields a set of correlation coefficients for ten different fault prototypes, which are used to develop fault classifier signatures for direct classification. The proposed method yields high classification accuracy of 99.76% using only (1/6)th of the post-fault noisy signal with fault resistance varying from 0.01 to 100Ω. Besides, analysis of only one end single discards the requirement of time synchronous signal acquisition from both ends. Finally, use of simple analysis reduces the computational burden compared to several contemporary methods. [ABSTRACT FROM AUTHOR]

Overhead energy transmission lines are highly susceptible to failure. To deal with this problem, some researchers have proposed different preprocessing stages, which comprise mainly feature extraction, selection, and dimension reduction for fault classification in transmission lines. The common techniques applied in the preprocessing stage are the wavelet and Fourier transforms. For the classification stage, the most used method is artificial neural network. This work aims to show the use of random forest method with a simple preprocessing step based on notch filter to classify faults in transmission lines. The performance of the model was compared with that obtained by a neural network to show its efficiency. Using k-fold cross-validation to train, test, and compare the models, it was obtained the mean accuracy of 89.59% for the neural network and 91.96% for the random forest for testing data. In the validation process, it was obtained accuracy of 96.49% and 91.49% for neural network and random forest models, respectively. Although the neural network model has shown better generalization capacity, the random forest model performed about eight times faster than the neural network. [ABSTRACT FROM AUTHOR]

In this article, a long short-term memory based protection scheme for power transmission lines is presented. A fault detection framework is developed that uses voltage and current signals’ RMS values as input. The proposed work is established for various shunt faults, both low-impedance and high-impedance faults which are tested on a standard IEEE 14 bus system and an existing real transmission network. Results confirm the detection and classification of faults with accuracy and precision higher than 99%. The impact of non-faulty events such as load switching, capacitor switching, noisy data, and load variation conditions is also studied to analyze the model’s performance. The efficacy of the proposed method is confirmed by comparing it with different methods in the literature. Results indicate the aptness of the proposed scheme for the protection of power transmission lines. [ABSTRACT FROM AUTHOR]

This paper presents a data-driven approach to classify and locate the faults occurring in underground distribution cables using a CNN-LSTM-based deep learning architecture. A sliding window method is adopted, using the current and voltage signal patches as inputs. The combination of various system parameters is considered to generalize the performance. Additionally, Gaussian noise is added to resemble and extend the approach to practical scenarios. The trained model is evaluated with the data from a new simulation, and the results confirm the generalizability of the adopted method. A comparison is made with other feasible approaches, which show that the adopted method is preferable to achieve better performance. Further, to ease the extension of the proposed method for different systems with similar configurations, parameters of the trained deep learning networks are exploited with the help of transfer learning. [ABSTRACT FROM AUTHOR]

In machinery fault detection and identification (FDI), decomposing vibration signals into corresponding intrinsic mode functions (IMFs) reduces the intricacy in extracting weak fault features at the early failure state. However, selecting a suitable IMF for fault information extraction is a challenging task. Analyzing the non-Gaussian IMFs allows extracting effective fault-related information rather than the entire signal or other IMFs because the vibration signals are random in nature. In this study, we present an IMF selection method based on the maximum kurtosis value of each IMF. A kurtosis computation method named autogram is used. It considers the autocovariance function to characterize the 2nd order cyclostationary. We deploy the AdaBoost algorithm with a decision tree classifier to gain a better performance compared with other tree-based classifiers. The proposed FDI framework can effectively detect and classify multiple fault features at the incipient failure stage. [ABSTRACT FROM AUTHOR]

The simple and robust construction, less weight, wide operating speed range, and higher fault tolerance capability of switched reluctance (SR) motor make it a viable contender for the conventional dc and ac machines. The faults at the rotor, winding, stator converters, and sensors lead to overcurrent, increase torque ripples, and sudden breakdown of the system. Thus, it is an urgent requirement to recognize and classify the faults that exist in switched reluctance motors, thereby the reliability, robustness, and widespread utilization of SR motors can be increased. The phases of the SR Motor are excited by using an asymmetric bridgeless resonance converter. This paper proposes an automatic diagnosis and classification of faults using radial basis function neural network (RBFNN). A mathematical model of the SR motor is established to determine the state of the art of fault condition of SR motors. The speed data of SR motor are utilized by RBFNN to generate fault information. Gabor filter is used for preprocessing the input data, and segmentation is achieved using high accurate DCT-DOST transformation. A gray-level co-occurrence matrix optimized with a genetic algorithm is used to extract the features in the speed signal of the motor. A test setup was developed in MATLAB to measure the performances of the RBFNN classifier in real-time. The effectiveness of the simulated fault classification model is verified by comparing the results of the conventional PI controller with several optimized algorithm-based tuned PI controllers. [ABSTRACT FROM AUTHOR]

In this paper, a fault diagnosis scheme is proposed in the transmission line, by which the faults can be classified and located correctly and rapidly using voltage amplitudes and support vector machine. A high voltage power system transmission line is simulated by MATLAB to produce a fault data set. The three-phase fault voltages are obtained at one terminal point of the line. The amplitudes of the three-phase fault voltages will be applied as the fault features to train the support vector classification (SVC) and realize fault classification after the three-phase fault voltages pass through a low-pass filter to remove the noise. After knowing the fault type, the voltage amplitude of the phase where the fault occurs will be used as the fault feature to train the support vector regression (SVR) and realize the fault location. Compared with other fault classification and fault location schemes, the proposed fault diagnosis scheme needs less information to provide one hundred percent classification accuracy and high accurate estimations of fault location. Simulations and comparisons show the proposed scheme is better than other schemes. [ABSTRACT FROM AUTHOR]

The protection of mutually coupled series capacitor-compensated (SCC) parallel transmission lines is a more complicated task than uncompensated lines due to the effect of mutual coupling, inter-circuit faults, and non-linearity of effective impedance of SCC line. A method that can overcome these issues and still work efficiently is a supervised learning-based method which is an adaptive technique. Hence, in this work, various supervised learning-based intelligent schemes like artificial neural network (ANN), support vector machines (SVM), and decision tree (DT) are employed to find a suitable method for the protection of series capacitor-compensated lines. Discrete wavelet transform has been used to process the three-phase current signals of the parallel lines measured at one terminal only. A moving window of 20 samples is selected, and approximate wavelet coefficient is calculated up to level 1 using DB-4 mother wavelet. The resultant is then given as input to the intelligent schemes (ANN, SVM, and DT). The proposed intelligent schemes have been tested with variety of fault conditions such as inter-circuit faults, cross-country faults, transforming faults, single-circuit operation, and high resistance faults. A large number of fault simulation studies corroborate that DT-based fault classification method is better than ANN and SVM. The accuracy of faulty phase and ground identification scheme is 100% for all the tested fault cases. Hence, the proposed supervised learning-based intelligent method can be implemented in real power system network effectively. [ABSTRACT FROM AUTHOR]

Rotary machines are key equipment in many industrial sectors, from mining operations to advanced manufacturing. Among the critical components of these machines are bearings, gearboxes, rotors, among others. These components tend to present failures, which can be catastrophic, with economic, safety and/or environmental consequences. Among the most established methods for classifying bearing faults, the envelope method has been widely used, with relative success, for several years. However, this method and its variations are difficult to automate and require extensive experience on the part of the analyst. We report that, while traditional methods (e.g., envelope) successfully classified bearing failures less than 45% of the time, machine learning methods were successful more than 62% of the time, and in some cases reaching 67%. This work differs from others in the sense that it uses all the available measurements from a well-known database, not just a subset. In addition, the measurements are taken at the motor base, which are more difficult to classify, and avoid using different segments of the same signal in both training and validation, thus reducing the possibility of overfitting. As a consequence, the results obtained are apparently inferior to those reported elsewhere, but probably closer to what one might expect in practical applications. [ABSTRACT FROM AUTHOR]

The prominence of incorporating the renewable energy resources in a power system via microgrids has increased in the recent years, which impose a caution on conventional protection schemes. Protection schemes proposed earlier use local measurements, but fault classification for selective phase tripping using wide area measurements for microgrid has not been reported so far. This paper presents a wide area monitoring and protection of microgrid with distributed generations (DGs) using modular artificial neural networks (MANNs) for the fault detection and classification without affecting the relays in non-faulty or healthy sections of the microgrid. The distinct characteristics of the microgrid sort the proposed methodology into two stages. In stage 1, ANN 1 is developed to identify the operating mode of microgrid, whether it is operating in grid-connected mode (GCM) or islanded mode (IM). In stage 2, there are two MANNs corresponding to GCM and IM. Each MANNs consists of three separate ANNs for fault detection, classification, and section identification. A standard IEC 61850-7-420 microgrid with DGs (wind and photovoltaic) penetration is modeled in MATLAB/Simulink. The three-phase voltages and currents are measured with time synchronization considering the microphasor measurement units located at each bus. The extensive study includes different simulation scenarios such as shunt faults, high impedance fault, and dynamic situations like connection/disconnection of DGs/distribution lines. The results confirm the efficacy of the proposed methodology. [ABSTRACT FROM AUTHOR]

The inherent uncertainty of software gives a vague and imprecise solution when it is solved by human judgment. As the project expands, the issues of missing data values, outlier detection, feature subset selection and prediction of faultiness behaviour should be addressed. The feature selection process may lead to the production of high-dimensional data sets that may contribute to many irrelevant or redundant features. In this paper, we focussed on the optimal feature subset selection and fault prediction at the early stage of a project. We propose the novel approach of grey relational analysis (GRA) from grey system theory by optimizing the grey relational grade function using biogeography optimization referred to as B-GRA. The proposed algorithm gives resilience to users to select features for both continuous and categorical attributes. The issues such as feature subset selection, heterogeneity of data sets, outlier analysis and fault prediction are addressed, and then, B-GRA and GRA approaches on five publically available data sets are evaluated using statistical and machine learning techniques. Experimental results show significant results indicating that the proposed methodology can be used for the prediction of faults and produce conceivable results when compared with the GRA feature selection approach. [ABSTRACT FROM AUTHOR]

In modern diagnostic approaches, the key step consists in generating the features related to fault type and severity. In fact, the generated features should be able to help the classifier to determine the health condition of the monitored system based on the measured signal. In this paper, in order to make an effective diagnosis about the rolling-element bearing failure, novel generated features that can maintain the physical meaning of the extracted vibration signal, while identifying its relationship to rolling bearing damage, are proposed using a wrapper model. For this purpose, based only on the Most Impulsive Frequency Bands (MIFBs) of the measured vibration signals for many bearing conditions, 33 feature parameters are proposed. Using a wrapper scheme, these parameters can be reduced until a set of them are found improving the efficiency of the diagnostic approach. The effectiveness of the proposed predictive features is analyzed by comparing it with some related works using many testing data for several bearing conditions. The experimental results reveal that the proposed procedure has obtained a high level of accuracy of 99.83%. [ABSTRACT FROM AUTHOR]

Condition monitoring of piston pumps has great significance to ensure the reliability and security of hydraulic systems. However, the complex working conditions of the integrated electromechanical systems make the fault mechanism unclear which is difficult for fault diagnosis by feature matching techniques. In this paper, a novel minimum entropy deconvolution (MED)-based convolutional neural network (CNN) is presented to classify faults in axial piston pumps. Firstly, the collected raw signals are preprocessed using the MED technique. Then, the filtered signals are used to construct training samples and testing samples. Finally, the constructed samples are fed into the CNN to classify the multi-faults of axial piston pumps. With the convolution and subsampling operations, the present model can automatically obtain data features via iterative learning processes, which is suitable for the unknown fault mechanism problems. The learned features are visualized by t-distributed stochastic neighbor embedding technique. A benchmark data simulation of mechanical transmission systems and an experimental data investigation of an axial piston pump are performed to manifest the superiority of the present method by comparing with the traditional CNN. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Today's modern industry has accepted condition monitoring based on intelligent fault diagnosis of rotating machinery systems to provide precision and sustainability. The conventional signal processing methods are less productive due to the involvement of various noises from different sources in the vibration signal, and therefore, recently fault diagnosis approaches use the artificial intelligent techniques along with the signal processing methods. Thus, motivated by the kurtogram and convolutional neural network (CNN), a novel efficient method for the fault classification of rotating machines is proposed in this paper. Kurtogram is a measure of dispersion for time–frequency energy density which provides additional frequency contents information and as an effect represents a pattern of each fault uniquely. Thus, it inspires to utilize the kurtogram as an input feature vector, and it helps in reducing the task of identifying dominant features to represent the different faults. Hence, this 2D distinct feature vector presented to CNN for fault classification. The various levels of kurtogram are examined by tuning different hyperparameters of CNN to achieve a good feature set for decent performance. The experimental results demonstrate that the proposed method effectively classifies the bearing faults under different operating conditions in comparison to other methods. [ABSTRACT FROM AUTHOR]

This work investigates an improved protection solution based on the use of artificial neural network on the 330 kV Nigerian network modeled using MATLAB R2014a. Measured fault voltages and currents signals decomposed using the discrete Fourier transform implemented via fast Fourier transform are fed as inputs to the neural network. The output plots of the neural network shows its successful application to fault diagnosis (fault detection, fault classification and fault location). Unlike conventional protection schemes, the neural network can be adapted to distances which can cover the entire length of the protected line. Numerical assessment carried out on the neural network fault locator shows a reduced time of operation of 5.15 ms as compared to the 0.350 s with the use of ordinary numerical relays. This work also investigates the adaptive auto-reclosure scheme implemented using artificial neural network. The adaptive reclosure scheme has been adapted for use in the Nigerian network successfully to distinguish transient and permanent faults. Simulation results prove that the adaptive reclosure scheme was able to detect a line-to-ground transient fault and clear this fault in 0.1 s while the line-to-ground permanent fault is cleared after 0.14 s. The fault diagnostic algorithm designed using artificial neural network (ANN) for the 330 kV network was tested on a 132 kV network. Results show and prove that the algorithm is flexible and can be adopted to other networks. [ABSTRACT FROM AUTHOR]

Faults frequently occur in transmission lines and become a major issue in power system engineering. It is an unavoidable incident and leads to many problems such as failure of equipment, instability in power flow and economical losses. Protection relay is a device installed in transmission lines to perform detection, classification and estimation of fault. The task must be performed accurately and fast to isolate the faulted phase and protect the system from the harmful effects of the fault. Fault classification involves the process of identifying the type of fault in the transmission lines. The presence of ground fault in three-phase faults has caused difficulty in identifying the fault types. This is due to the input signals that only contain three-phase currents/voltages and influenced by noise. Recent studies show that ANNs are powerful tools for fault classification. However, most studies utilized single ANN to classify all the faults, even though not all fault classes are equally difficult. This paper proposes a robust fault classification scheme using wavelet transform (WT) and 2-Tier multilayer perceptron (MLP) network. The first-Tier MLP network (MLP 1) is used to classify the three-phase fault (A, B and C), and the second-Tier MLP network (MLP 2) is used to identify the presence of ground fault. A new WT-based feature that properly describe the presence of ground fault called class-dependent feature (CDF) is formulated. The CDF is determined from the correlation between the output of MLP 1, wavelet mean and energy features. The CDF is fed into the MLP 2 and used to determine the presence of ground fault. Comparison performance with different MLP network structures indicated that the proposed method showed good classification accuracy. The average accuracy of CDF and 2-Tier MLP network for three different datasets, ideal (no noise), 20 and 30 dB, shows the highest with 99.36% as compared to other structures. [ABSTRACT FROM AUTHOR]

Computational grids are established with the intention of providing shared access to hardware and software based resources with special reference to increased computational capabilities. Fault tolerance is one of the most important issues faced by the computational grids. The main contribution of this survey is the creation of an extended classification of problems that incur in the computational grid environments. The proposed classification will help researchers, developers, and maintainers of grids to understand the types of issues to be anticipated. Moreover, different types of problems, such as omission, interaction, and timing related have been identified that need to be handled on various layers of the computational grid. In this survey, an analysis and examination is also performed pertaining to the fault tolerance and fault detection mechanisms. Our conclusion is that a dependable and reliable grid can only be established when more emphasis is on fault identification. Moreover, our survey reveals that adaptive and intelligent fault identification, and tolerance techniques can improve the dependability of grid working environments. [ABSTRACT FROM AUTHOR]

This paper presents a new approach to address both fault classification and location in double-circuit power transmission lines. Fault diagnosis is achieved by using an algorithm based on the successive geometric segmentation approach. The proposed technique is able to generate both the topology and the weighting of neural networks. The input parameters are the magnitudes of phase voltages and currents measured in only one bus of a double-end fed transmission line. In order to validate the methodology, a comprehensive dataset of cross-country faults was simulated using a mathematical model. The results indicate high accuracy rate to fault diagnosis in double-circuit transmission lines compared to other ANN-based approaches found in the literature. [ABSTRACT FROM AUTHOR]

This paper addresses the multi-fault diagnosis problem of thrusters and sensors for autonomous underwater vehicles (AUVs). Traditional support vector domain description (SVDD) has low classification accuracy in the process of AUV multi-fault pattern classification because of the effect of sample sparse density and the uneven distribution of samples, and so on. Thus, a fuzzy weighted support vector domain description (FWSVDD) method based on positive and negative class samples is proposed. In this method, the negative class sample is introduced during classifier training, and the local density and the class weight are introduced for each sample. To improve the multi-fault pattern classifier training speed and fault diagnosis accuracy of FWSVDD, a multi-fault mode classification method based on a hierarchical strategy is proposed. This method adds fault contain detection surface for each thruster and sensor to isolate fault components during fault diagnosis. By considering the problem of pattern classification for a fuzzy sample, which may be located in the overlapping area of hyper-spheres or may not belong to any hyper-sphere in the process of multi-fault classification based on FWSVDD, a relative distance judgment method is given. The effectiveness of the proposed multi-fault diagnosis approach is demonstrated through water tank experiments with an experimental AUV prototype. [ABSTRACT FROM AUTHOR]

This paper introduces a new fault diagnosis strategy for analog circuits based on conic optimization and ellipsoidal classifiers. Ellipsoidal classifiers are trained for efficient and accurate fault classification of the circuit under test (CUT). In the testing phase, the output of the ellipsoidal classifiers is used to isolate the actual CUT fault. The constructed classifiers exhibit high classification rate with competitive computational complexity even if the CUT has overlapping faults. Experimental results demonstrate the superior performance of the ellipsoidal classifiers in analog fault diagnosis. [ABSTRACT FROM AUTHOR]

This article describes a proposed work-sequence to generate accurate reservoir-architecture models, describing the geometry of bounding surfaces (i.e., fault locations and extents), of a structurally complex geologic setting in the Jeffara Basin (South East Tunisia) by means of geostatistical modeling. This uses the variogram as the main tool to measure the spatial variability of the studied geologic medium before making any estimation or simulation. However, it is not always easy to fit complex experimental variograms to theoretical models. Thus, our primary purpose was to establish a relationship between the geology and the components of the variograms to fit a mathematically consistent and geologically interpretable variogram model for improved predictions of surface geometries. We used a three-step approach based on available well data and seismic information. First, we determined the structural framework: a seismo-tectonic data analysis was carried out, and we showed that the study area is cut mainly by NW-SE-trending normal faults, which were classified according to geometric criteria (strike, throw magnitude, dip, and dip direction). We showed that these normal faults are at the origin of a large-scale trend structure (surfaces tilted toward the north-east). At a smaller scale, the normal faults create a distinct compartmentalization of the reservoirs. Then, a model of the reservoir system architecture was built by geostatistical methods. An efficient methodology was developed, to estimate the bounding faulted surfaces of the reservoir units. Emphasis was placed on (i) elaborating a methodology for variogram interpretation and modeling, whereby the importance of each variogram component is assessed in terms of probably geologic factor controlling the behavior of each structure; (ii) integrating the relevant fault characteristics, which were deduced from the previous fault classification analysis, as constraints in the kriging estimation of bounding surfaces to best reflect the geologic structure of the study area. Finally, the estimated bounding surfaces together with seismic data and variogram interpretations were used to obtain further insights into the tectonic evolution of the study area that has induced the current reservoirs configuration. [ABSTRACT FROM AUTHOR]

This paper presents a new method for fault classification in series-compensated transmission line using multiclass support vector machine (MCSVM) and multi class extreme learning machine (MCELM). These methods use the information obtained from the wavelet decomposition of fault current signals for fault classification. Using MATLAB simulink, data set has been generated with different types of fault and system variables, which include the fault resistance, fault distance, load angle and fault inception angle. The proposed method has been tested on a 400-kV, 300-km transmission line under variety of fault conditions. The performance of MCSVM and MCELM is compared in terms of training time and classification accuracy. The comparisons have been made for both One-Versus-One and One-Versus-Rest methods of SVMs and ELMs. Results show that MCELMs need less training time compared to MCSVMs, and the classification accuracy of MCELMs is more or less similar to MCSVMs. The feasibility of the proposed methods is also tested on a practical 220-kV series-compensated transmission line, and the results obtained are quite promising. [ABSTRACT FROM AUTHOR]

This paper presents the expectation–maximization (EM) variant of probabilistic neural network (PNN) as a step toward creating an autonomous and deterministic PNN. In the real world, faulty reading sensors can happen and will create input vectors with missing features yet they should not be discarded. To overcome this, regularized EM is put in place as a preprocessing step to impute the missing values. The problem faced by users when using random initialization is that they have to define the number of clusters through trial and error, which makes it stochastic in nature. Global k-means is used to autonomously find the number of clusters using a selection criterion and deterministically provide the number of clusters needed to train the model. In addition, fast Global k-means will be tested as an alternative to Global k-means to help reduce computational time. Tests are conducted on both homoscedastic and heteroscedastic PNNs. Benchmark medical datasets and also vibration data collected from a US Navy CH-46E helicopter aft gearbox known as Westland were used. The tests’ results fully support the usage of fast Global k-means and regularized EM as preprocessing steps to aid the EM-trained PNN. [ABSTRACT FROM AUTHOR]

This paper proposes an integrated system for motor bearing diagnosis that combines the cepstrum coefficient method for feature extraction from motor vibration signals and artificial neural network (ANN) models. We divide the motor vibration signal, obtain the corresponding cepstrum coefficients, and classify the motor systems through ANN models. Utilizing the proposed method, one can identify the characteristics hiding inside a vibration signal and classify the signal, as well as diagnose the abnormalities. To evaluate this method, several tests for the normal and abnormal conditions were performed in the laboratory. The results show the effectiveness of cepstrum and ANN in detecting the bearing condition. The proposed method successfully extracted the corresponding feature vectors, distinguished the difference, and classified bearing faults correctly. [ABSTRACT FROM AUTHOR]

A new on-line fault detection and isolation (FDI) scheme proposed for engines using an adaptive neural network classifier is evaluated for a wide range of operational modes to check the robustness of the scheme in this paper. The neural classifier is adaptive to cope with the significant parameter uncertainty, disturbances, and environment changes. The developed scheme is capable of diagnosing faults in on-line mode and can be directly implemented in an on-board diagnosis system (hardware). The robustness of the FDI for the closed-loop system with crankshaft speed feedback is investigated by testing it for a wide range of operational modes including robustness against fixed and sinusoidal throttle angle inputs, change in load, change in an engine parameter, and all these changes occurring at the same time. The evaluations are performed using a mean value engine model (MVEM), which is a widely used benchmark model for engine control system and FDI system design. The simulation results confirm the robustness of the proposed method for various uncertainties and disturbances. [ABSTRACT FROM AUTHOR]

This paper proposes a condition classification system using wavelet transform, feature evaluation and artificial neural networks to detect faulty products on the production line of reciprocating compressors for refrigerators. The stationary features of vibration signals are extracted from statistical cumulants of the discrete wavelet coefficients and root mean square values of band-pass frequencies. The neural networks are trained by the sample data, including healthy or faulty compressors. Based on training, the proposed system can be used on the automatic mass production line to classify product quality instead of people inspection. The validity of this system is demonstrated by the on-site test at LG Electronics, Inc. for reciprocating compressors. According to different products, this system after some modification may be useful to increase productivity in different types of production lines. [ABSTRACT FROM AUTHOR]

A new neural network-based fault classification strategy for hard multiple faults in analog circuits is proposed. The magnitude of the harmonics of the Fourier components of the circuit response at different test nodes due to a sinusoidal input signal are first measured or simulated. A selection criterion for determining the best components that describe the circuit behaviour under fault-free (nominal) and fault situations is presented. An algorithm that estimates the overlap between different faults in the measurement space is also introduced. The learning vector quantization neural network is then effectively trained to classify circuit faults. Performance measures reveal very high classification accuracy in both training and testing stages. Two different examples, which demonstrate the proposed strategy, are described. [ABSTRACT FROM AUTHOR]

This is an experimental study to investigate the feasibility of employing fuzzysets theory in an integrated machine-fault diagnostic system. This system consists of modules for data acquisition, data processing, features extraction, fault clustering and fault assignment. Among these tasks, fault clustering and fault assignment are accomplished using fuzzy-sets-based procedures. The theoretical foundation of this study is discussed, with case studies. [ABSTRACT FROM AUTHOR]