6,333 Hits in 5.3 sec

An application of numerical differentiation formulas to discontinuity curve detection from irregularly sampled data [article]

Cesare Bracco, Oleg Davydov, Carlotta Giannelli, Alessandra Sestini
2019 arXiv   pre-print
We present a method to detect discontinuity curves, usually called faults, from a set of scattered data. The scheme first extracts from the data set a subset of points close to the faults.  ...  The shape of the faults is reconstructed through local computations of regression lines and quadratic least squares approximations.  ...  formulas, which are the mathematical tool used for our direct fault detection approach from scattered data.  ... 
arXiv:1812.07399v2 fatcat:eumhwls7g5dndkg5gh5djhcodi

Fisher Discriminative Sparse Representation Based on DBN for Fault Diagnosis of Complex System

Qiu Tang, Yi Chai, Jianfeng Qu, Hao Ren
2018 Applied Sciences  
model using the extracted features for fault detection and diagnosis.  ...  Fault detection and diagnosis in the chemical industry is a challenging task due to the large number of measured variables and complex interactions among them.  ...  fault detection and diagnosis.  ... 
doi:10.3390/app8050795 fatcat:wo7vxkumkrb2jezjfg5e4shdbe

A Generative Adversarial Network-Based Fault Detection Approach for Photovoltaic Panel

Fangfang Lu, Ran Niu, Zhihao Zhang, Lingling Guo, Jingjing Chen
2022 Applied Sciences  
So, the model can filter out the fault PV panel by checking the error value between the original image and its reconstructed image.  ...  Since the abnormal PV panel data do not obey the data distribution learned by the generator, the difference between the original image and its reconstructed image exceeds the given threshold.  ...  Acknowledgments: We acknowledge a photovoltaic power plant located in Zhejiang province for providing data for our experiment. Appl. Sci. 2022, 12, 1789  ... 
doi:10.3390/app12041789 fatcat:hy6ltzr7lbdzthp6roc6yjcwiu

Determination of composition, residual stress and stacking fault depth profiles in expanded austenite with energy-dispersive diffraction

S. Jegou, T.L. Christiansen, M. Klaus, Ch. Genzel, M.A.J. Somers
2013 Thin Solid Films  
The proposed method is applied to an expanded austenite layer on stainless steel and allows the separation of stress, composition and stacking fault density gradients.  ...  SOMERS -Determination of composition, residual stress and stacking fault depth profiles in expanded austenite with energy-dispersive diffraction -Thin Solid A methodology is proposed combining the scattering  ...  Acknowledgements Financial support from the Danish Research Council for Technology and Production Sciences under grant no. 274-07-0344 is gratefully acknowledged.  ... 
doi:10.1016/j.tsf.2012.06.029 fatcat:u3ijayr2lbaw3axmx6sjbm2hgq

Deep Convolutional Clustering-Based Time Series Anomaly Detection

Gavneet Singh Chadha, Intekhab Islam, Andreas Schwung, Steven X. Ding
2021 Sensors  
As a core novelty, we split the autoencoder latent space in discriminative and reconstructive latent features and introduce an auxiliary loss based on k-means clustering for the discriminatory latent variables  ...  The system solely relies on unlabeled data and employs a 1D-convolutional neural network-based deep autoencoder architecture.  ...  However, the clustering features receive the update gradient from reconstruction and the clustering errors.  ... 
doi:10.3390/s21165488 pmid:34450930 pmcid:PMC8400863 fatcat:6bk4djhthnd2bbx7kvb4gnxyxa

Fault Diagnosis for Rolling Bearing under Variable Conditions Based on Image Recognition

Bo Zhou, Yujie Cheng
2016 Shock and Vibration  
Next, a popular feature extraction method which has been widely used in the image field, scale invariant feature transform (SIFT), is employed to extract fault features from the two-dimensional RP and  ...  Recently, a large amount of fault diagnosis studies for rolling bearing based on vibration data has been reported.  ...  Finally, the PNN is used as a classifier to diagnose the fault classification using data from one of the conditions to train the neural network and using data from the other conditions to test the proposed  ... 
doi:10.1155/2016/1948029 fatcat:bw64vj5l2vgnhbfn35n4w6mlgq

Anomaly Detection for Partial Discharge in Gas-Insulated Switchgears Using Autoencoder

Ngoc-Diem Tran Thi, The-Duong Do, Jae-Ryong Jung, Hyangeun Jo, Yong-Hwa Kim
2020 IEEE Access  
Then, the reconstruction error was used as a fault indicator, and the threshold was determined using the partial discharge data.  ...  Based on the one-class classification scenario, in which the training data exploited the noise data only, the proposed autoencoder learned the low-dimensional latent information from the high-dimensional  ...  From these histograms, most noise samples are not detected falsely as fault data, whereas in some fault data, the reconstruction loss is higher than the threshold.  ... 
doi:10.1109/access.2020.3017226 fatcat:eghvgn2cvjfgbcylcan4a35naa

Componential coding in the condition monitoring of electrical machines Part 1: Principles and illustrations using simulated typical faults

C J S Webber, B S Payne, F Gu, A D Ball
2003 Proceedings of the Institution of mechanical engineers. Part C, journal of mechanical engineering science  
The companion paper (Part 2), which follows, assesses componential coding in its application to real data recorded from a known machine and an entirely unseen machine (a conventional induction motor and  ...  This is because componential coding is an unsupervised technique that derives the features of the data during training, and so requires neither labelling of known faults nor pre-processing to enhance known  ...  D ifferentiating a 'monitored' data-set in this way from a healthy, validation data-set is the basis of the algorithm's fault detection capability, and differentiating different faulty data-sets from one  ... 
doi:10.1243/095440603322310431 fatcat:izv4auq7izcilkaxwta5ofg3ea

A Novel Multimode Fault Classification Method Based on Deep Learning

Funa Zhou, Yulin Gao, Chenglin Wen
2017 Journal of Control Science and Engineering  
The data feature involved in the observation often varies with mode changing. Mode partition is a fundamental step before fault classification.  ...  with different fault severity.  ...  U1604158, U1509203, and Journal of Control Science and Engineering  ... 
doi:10.1155/2017/3583610 fatcat:oiubsnf5vjhlrc36dww3lgwiom

An Abnormal Data Processing Method Based on An Ensemble Algorithm for Early Warning of Wind Turbine Failure

Qiang Zhao, Kunkun Bao, Zhenfan Wei, Yinghua Han, Jinkuan Wang
2021 IEEE Access  
The manual selection of modeling data according to fault records is time-consuming and makes it difficult to guarantee the high quality of the data because of inconsistencies, errors, and losses of records  ...  of normal and abnormal operational data.  ...  data processing algorithm first detected the fault at the 405th data point, and then the fault was detected again at the 474th data point.  ... 
doi:10.1109/access.2021.3062865 fatcat:zhmbm3ebf5hwtbh3toei4yi3hi

Approximation of surfaces with fault(s) and/or rapidly varying data, using a segmentation process, D m -splines and the finite element method

C. Gout, C. Le Guyader, L. Romani, A.-G. Saint-Guirons
2008 Numerical Algorithms  
To perform the segmentation step, we propose a quasi-automatic algorithm that uses a level set method to obtain from the given (gridded or scattered) Lagrange data several patches delimited by large gradients  ...  Approximation of surfaces with fault(s) and/or rapidly varying data, using a segmentation process, D m -splines and the finite element method Numerical Algorithms, to appear 2008.  ...  and improved version of the paper.  ... 
doi:10.1007/s11075-008-9177-8 fatcat:gk52mpt4nnfctforjphwcgdhsa

Hybrid deep fault detection and isolation: Combining deep neural networks and system performance models [article]

Manuel Arias Chao, Chetan Kulkarni, Kai Goebel, Olga Fink
2019 arXiv   pre-print
With the increased availability of condition monitoring data and the increased complexity of explicit system physics-based models, the application of data-driven approaches for fault detection and isolation  ...  improvement when applied within the hybrid fault detection and diagnostics framework.  ...  model combining data from all the operating conditions provide unsatisfactory performance for fault detection and isolation.  ... 
arXiv:1908.01529v2 fatcat:ftmxwwawcvdepd77onfhqazkke

Abnormal Detection for Running State of Linear Motor Feeding System Based on Deep Neural Networks

Zeqing Yang, Wenbo Zhang, Wei Cui, Lingxiao Gao, Yingshu Chen, Qiang Wei, Libing Liu
2022 Energies  
The method constructs an encoding-decoding-reconstructed encoding network model.  ...  Compared with other classical methods such as GANomaly and GAN-AE, the average AUROC index of this method is improved by 17.5% and 9.3%, the average accuracy is enhanced by 11.6% and 15.5%, and the detection  ...  On the other hand, LSTM can avoid gradient disappearance and gradient explosion when training time-series data.  ... 
doi:10.3390/en15155671 fatcat:h2amluqsyfde7ivmibyckvdqme

Towards zero-configuration condition monitoring based on dictionary learning

Sergio Martin-del-Campo, Fredrik Sandin
2015 2015 23rd European Signal Processing Conference (EUSIPCO)  
We study how the feature vectors learned from a vibration signal evolve over time when a fault develops within a ball bearing of a rotating machine.  ...  Online condition monitoring systems are customized to each type of machine and need to be reconfigured when conditions change, which is costly and requires expert knowledge.  ...  The requirements on the methods employed to achieve that go beyond fault detection, in particular in terms of prediction of faults [1] and detection of abnormal operational conditions.  ... 
doi:10.1109/eusipco.2015.7362595 dblp:conf/eusipco/CampoS15 fatcat:36l5vrimpvbb7f7qwldmd3k22u

Towards Zero-Configuration Condition Monitoring Based On Dictionary Learning

Sergio Martin-del-Campo, Fredrik Sandin
2015 Zenodo  
The requirements on the methods employed to achieve that go beyond fault detection, in particular in terms of prediction of faults [1] and detection of abnormal operational conditions.  ...  CHARACTERIZATION OF ROTATING MACHINE WITH FAULT IN ROLLING ELEMENT BEARING We apply the MP with dictionary learning approach to vibration data from a rotating machine at the bearing data center at Case  ... 
doi:10.5281/zenodo.35895 fatcat:lzocaort6nb2baajau2lidwisq
« Previous Showing results 1 — 15 out of 6,333 results