Search results for "ENCODE"

showing 10 items of 91 documents

Data-driven Fault Diagnosis of Induction Motors Using a Stacked Autoencoder Network

2019

Current signatures from an induction motor are normally used to detect anomalies in the condition of the motor based on signal processing techniques. However, false alarms might occur if using signal processing analysis alone since missing frequencies associated with faults in spectral analyses does not guarantee that a motor is fully healthy. To enhance fault diagnosis performance, this paper proposes a machinelearning based method using in-built motor currents to detect common faults in induction motors, namely inter-turn stator winding-, bearing- and broken rotor bar faults. This approach utilizes single-phase current data, being pre-processed using Welch’s method for spectral density es…

010302 applied physicsSignal processingbusiness.industryRotor (electric)Computer science020208 electrical & electronic engineeringSpectral density estimationPattern recognition02 engineering and technologyFault (power engineering)01 natural sciencesAutoencoderlaw.inventionSupport vector machineStatistical classificationlaw0103 physical sciences0202 electrical engineering electronic engineering information engineeringArtificial intelligencebusinessInduction motor2019 22nd International Conference on Electrical Machines and Systems (ICEMS)
researchProduct

Multi-Component Fault Detection in Wind Turbine Pitch Systems Using Extended Park's Vector and Deep Autoencoder Feature Learning

2018

Pitch systems are among the wind turbine components with most frequent failures. This article presents a multicomponent fault detection for induction motors and planetary gearboxes of the electric pitch drives using only the three-phase motor line currents. A deep autoencoder is used to extract features from the extended Park's vector modulus of the motor three-phase currents and a support vector machine to classify faults. The methodology is validated in a laboratory setup of a scaled pitch drive, with four commonly occurring faults, namely, the motor stator turns fault, broken rotor bars fault, planetary gearbox bearing fault and planet gear faults, under varying load and speed conditions.

0209 industrial biotechnologyBearing (mechanical)StatorComputer scienceRotor (electric)02 engineering and technologyFault (power engineering)AutoencoderTurbineFault detection and isolationlaw.invention020901 industrial engineering & automationlawControl theory0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingInduction motor2018 21st International Conference on Electrical Machines and Systems (ICEMS)
researchProduct

Model-Free Sliding-Mode-Based Detection and Estimation of Backlash in Drives With Single Encoder

2021

Backlash is a frequently encountered problem for various drives, especially those equipped with a single encoder onside of the controlled actuator. This brief proposes a sliding-mode differentiator-based estimation of unknown backlash size while measuring the actuator displacement only. Neither actuator nor load dynamics are explicitly known, while a principal second-order actuator behavior is assumed. We make use of the different perturbation dynamics distinctive for different backlash modes and an unbounded impulse-type perturbation at impact. The latter leads to transient loss of the sliding-mode and allows for detecting an isolated time instant of the backlash occurrence. The proposed m…

0209 industrial biotechnologyComputer science020208 electrical & electronic engineeringPerturbation (astronomy)02 engineering and technologyResidualUpper and lower boundsSystem dynamicsDifferentiatorVDP::Teknologi: 500020901 industrial engineering & automationControl and Systems EngineeringControl theory0202 electrical engineering electronic engineering information engineeringElectrical and Electronic EngineeringActuatorEncoderBacklash
researchProduct

On Stability of Virtual Torsion Sensor for Control of Flexible Robotic Joints with Hysteresis

2019

Author's accepted manuscript (postprint). This article has been published in a revised form in Robotica, http://doi.org/10.1017/S0263574719001358. This version is free to view and download for private research and study only. Not for re-distribution or re-use. © 2019 Cambridge University Press. Available from 25/03/2020. Aim of the virtual torsion sensor (VTS) is in observing the nonlinear deflection in the flexible joints of robotic manipulators and, by its use, improving positioning control of the joint load. This model-based approach utilizes the motor-side sensing only and, therefore, replaces the load-side encoders at nearly zero hardware costs. For being applied in the closed control …

0209 industrial biotechnologyComputer scienceGeneral Mathematics020208 electrical & electronic engineeringPassivityTorsion (mechanics)02 engineering and technologyComputer Science ApplicationsRobot controlSystem dynamicsNonlinear systemVDP::Teknologi: 500020901 industrial engineering & automationControl and Systems EngineeringControl theoryControl systemJoint stiffness0202 electrical engineering electronic engineering information engineeringmedicinemedicine.symptomEncoderSoftware
researchProduct

Health Indicator for Low-Speed Axial Bearings Using Variational Autoencoders

2020

This paper proposes a method for calculating a health indicator (HI) for low-speed axial rolling element bearing (REB) health assessment by utilizing the latent representation obtained by variational inference using Variational Autoencoders (VAEs), trained on each speed reference in the dataset. Further, versatility is added by conditioning on the speed, extending the VAE to a conditional VAE (CVAE), thereby incorporating all speeds in a single model. Within the framework, the coefficients of autoregressive (AR) models are used as features. The dimensionality reduction inherent in the proposed method lowers the need of expert knowledge to design good condition indicators. Moreover, the sugg…

0209 industrial biotechnologyGeneral Computer Sciencegenerative modelsComputer sciencecondition monitoring02 engineering and technologyLatent variableunsupervised learningFault detection and isolationBearing fault detection020901 industrial engineering & automationVDP::Teknologi: 500::Maskinfag: 5700202 electrical engineering electronic engineering information engineeringGeneral Materials Sciencevariational autoencoderconditional variational autoencoderbusiness.industryDimensionality reduction020208 electrical & electronic engineeringGeneral EngineeringPattern recognitionData pointAutoregressive modelRolling-element bearingFalse alarmArtificial intelligencelcsh:Electrical engineering. Electronics. Nuclear engineeringbusinesslcsh:TK1-9971IEEE Access
researchProduct

Upgrading HepG2 cells with adenoviral vectors that encode drug-metabolizing enzymes: application for drug hepatotoxicity testing.

2016

Drug attrition rates due to hepatotoxicity are an important safety issue considered in drug development. The HepG2 hepatoma cell line is currently being used for drug-induced hepatotoxicity evaluations, but its expression of drug-metabolizing enzymes is poor compared with hepatocytes. Different approaches have been proposed to upgrade HepG2 cells for more reliable drug-induced liver injury predictions. Areas covered: We describe the advantages and limitations of HepG2 cells transduced with adenoviral vectors that encode drug-metabolizing enzymes for safety risk assessments of bioactivable compounds. Adenoviral transduction facilitates efficient and controlled delivery of multiple drug-metab…

0301 basic medicineDrugmedia_common.quotation_subjectGenetic VectorsBiologyPharmacologyToxicologyENCODERisk AssessmentAdenoviridae03 medical and health sciencesToxicity TestsmedicineAnimalsHumansmedia_commonPharmacologyLiver injurychemistry.chemical_classificationReproducibility of ResultsGeneral MedicineHep G2 Cellsmedicine.disease030104 developmental biologyEnzymemedicine.anatomical_structureDrug developmentchemistryPharmaceutical PreparationsHepg2 cellsHepatocyteDrug DesignCancer researchHepatocytesChemical and Drug Induced Liver InjuryDrug metabolismExpert opinion on drug metabolismtoxicology
researchProduct

Identification of control targets in Boolean molecular network models via computational algebra

2015

Motivation: Many problems in biomedicine and other areas of the life sciences can be characterized as control problems, with the goal of finding strategies to change a disease or otherwise undesirable state of a biological system into another, more desirable, state through an intervention, such as a drug or other therapeutic treatment. The identification of such strategies is typically based on a mathematical model of the process to be altered through targeted control inputs. This paper focuses on processes at the molecular level that determine the state of an individual cell, involving signaling or gene regulation. The mathematical model type considered is that of Boolean networks. The pot…

0301 basic medicineTheoretical computer scienceComputer scienceProcess (engineering)Molecular Networks (q-bio.MN)Systems biologySystem of polynomial equationsENCODEBoolean networksSet (abstract data type)03 medical and health sciences0302 clinical medicineStructural BiologyModelling and SimulationQuantitative Biology - Molecular NetworksMolecular BiologyEdge deletionsApplied MathematicsComputer Science ApplicationsNetwork controlIdentification (information)030104 developmental biologyBoolean networkBlocking transitionsFOS: Biological sciencesModeling and SimulationAlgebraic controlState (computer science)030217 neurology & neurosurgeryResearch ArticleBMC Systems Biology
researchProduct

An optimal population code for global motion estimation in local direction-selective cells

2021

AbstractNervous systems allocate computational resources to match stimulus statistics. However, the physical information that needs to be processed depends on the animal’s own behavior. For example, visual motion patterns induced by self-motion provide essential information for navigation. How behavioral constraints affect neural processing is not known. Here we show that, at the population level, local direction-selective T4/T5 neurons in Drosophila represent optic flow fields generated by self-motion, reminiscent to a population code in retinal ganglion cells in vertebrates. Whereas in vertebrates four different cell types encode different optic flow fields, the four uniformly tuned T4/T5…

0303 health scienceseducation.field_of_studyMatching (graph theory)Computer sciencebusiness.industryPopulationPattern recognitionENCODERetinal ganglion03 medical and health sciences0302 clinical medicineFlow (mathematics)Physical informationMotion estimationArtificial intelligenceeducationbusiness030217 neurology & neurosurgery030304 developmental biologyCoding (social sciences)
researchProduct

Related haloarchaeal pleomorphic viruses contain different genome types

2012

Archaeal viruses have been the subject of recent interest due to the diversity discovered in their virion architectures. Recently, a new group of haloarchaeal pleomorphic viruses has been discovered. It is distinctive in terms of the virion morphology and different genome types (ssDNA/dsDNA) harboured by rather closely related representatives. To date there are seven isolated viruses belonging to this group. Most of these share a cluster of five conserved genes, two of which encode major structural proteins. Putative proviruses and proviral remnants containing homologues of the conserved gene cluster were also identified suggesting a long-standing relationship of these viruses with their ho…

Archaeal VirusesGenes ViralviruseseducationMolecular Sequence DataGenomicsGenome ViralBiologyENCODEGenome03 medical and health sciencesViral ProteinsGene clusterGeneticsNucleotide MotifsGene1183 Plant biology microbiology virologyChromatography High Pressure Liquid030304 developmental biologyGenomic organizationGenetics0303 health sciencesBase Sequence030306 microbiologyNucleosidesArchaeal VirusesGenomicsViral replicationvirus haloarchaea genomicsDNA ViralNucleic Acids Research
researchProduct

Combining Auto-Encoder with LSTM for WiFi-Based Fingerprint Positioning

2021

Although indoor positioning has long been investigated by various means, its accuracy remains concern. Several recent studies have applied machine learning algorithms to explore wireless fidelity (WiFi)-based positioning. In this paper, we propose a novel deep learning model which concatenates an auto-encoder with a long short term memory (LSTM) network for the purpose of WiFi fingerprint positioning. We first employ an auto-encoder to extract representative latent codes of fingerprints. Such an extraction is proven to be more reliable than simply using a deep neural network to extract representative features since a latent code can be reverted back to its original input. Then, a sequence o…

Artificial neural networkbusiness.industryComputer scienceDeep learningFeature extractionFingerprint (computing)WirelessPattern recognitionArtificial intelligenceFingerprint recognitionbusinessAutoencoderData modeling2021 International Conference on Computer Communications and Networks (ICCCN)
researchProduct