Search results for "Prognostics"

showing 10 items of 15 documents

Novel Threshold Calculations for Remaining Useful Lifetime Estimation of Rolling Element Bearings

2018

The prognostics objective is to avoid sudden machinery breakdowns and to estimate the remaining useful life after initial degradation. Typically, physical health indicators are derived from available sensor data, and a mathematical model is tuned to fit them. The time it takes for the model to reach a failure threshold is the estimated remaining useful life. The failure threshold may be determined from historical failure data, but that is not always readily available. ISO standard 10816–3 defines permissible velocity vibration levels for machines that may be used as a failure threshold. However, velocity vibration is not suitable for bearing prognostics due to the effect of integration from…

0209 industrial biotechnologyBearing (mechanical)Computer science020208 electrical & electronic engineeringCondition monitoring02 engineering and technologyAccelerometerlaw.inventionVibrationAcceleration020901 industrial engineering & automationControl theorylaw0202 electrical engineering electronic engineering information engineeringPrognosticsProbability distributionDegradation (telecommunications)2018 XIII International Conference on Electrical Machines (ICEM)
researchProduct

A review of diagnostics and prognostics of low-speed machinery towards wind turbine farm-level health management

2016

Abstract Large wind farms are gaining prominence due to increasing dependence on renewable energy. In order to operate these wind farms reliably and efficiently, advanced maintenance strategies such as condition based maintenance are necessary. However, wind turbines pose unique challenges in terms of irregular load patterns, intermittent operation and harsh weather conditions, which have deterring effects on life of rotating machinery. This paper reviews the state-of-the-art in the area of diagnostics and prognostics pertaining to two critical failure prone components of wind turbines, namely, low-speed bearings and planetary gearboxes. The survey evaluates those methods that are applicabl…

0209 industrial biotechnologyEngineeringGearbox020209 energy02 engineering and technologyTurbineBearings; Diagnostics; Gearbox; Health management; Prognostics; Reliability centered maintenance; Wind turbines; Renewable Energy Sustainability and the Environment020901 industrial engineering & automationWind turbines0202 electrical engineering electronic engineering information engineeringForensic engineeringRenewable EnergyDiagnosticsPrognosticsReliability (statistics)Wind powerHealth management systemSustainability and the EnvironmentRenewable Energy Sustainability and the Environmentbusiness.industryCondition-based maintenanceReliability centered maintenanceRenewable energyReliability engineeringLow speedHealth managementPrognosticsbusinessBearings
researchProduct

Reliable diagnostics using wireless sensor networks

2019

International audience; Monitoring activities in industry may require the use of wireless sensor networks, for instance due to difficult access or hostile environment. But it is well known that this type of networks has various limitations like the amount of disposable energy. Indeed, once a sensor node exhausts its resources, it will be dropped from the network, stopping so to forward information about maybe relevant features towards the sink. This will result in broken links and data loss which impacts the diagnostic accuracy at the sink level. It is therefore important to keep the network's monitoring service as long as possible by preserving the energy held by the nodes. As packet trans…

0209 industrial biotechnologyGeneral Computer ScienceComputer science[INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS]02 engineering and technologyData loss[INFO.INFO-SE]Computer Science [cs]/Software Engineering [cs.SE]Network topology[SPI.AUTO]Engineering Sciences [physics]/Automatic[INFO.INFO-IU]Computer Science [cs]/Ubiquitous ComputingPrognostics and health management[INFO.INFO-CR]Computer Science [cs]/Cryptography and Security [cs.CR]020901 industrial engineering & automation0202 electrical engineering electronic engineering information engineeringAdaBoostElectroniquebusiness.industryNetwork packetGeneral Engineering[INFO.INFO-MO]Computer Science [cs]/Modeling and SimulationWireless sensor networksRandom forest[SPI.TRON]Engineering Sciences [physics]/Electronics[INFO.INFO-MA]Computer Science [cs]/Multiagent Systems [cs.MA]Sensor node020201 artificial intelligence & image processing[INFO.INFO-ET]Computer Science [cs]/Emerging Technologies [cs.ET]Gradient boosting[INFO.INFO-DC]Computer Science [cs]/Distributed Parallel and Cluster Computing [cs.DC]businessWireless sensor networkComputer networkComputers in Industry
researchProduct

Impact of decision horizon on post-prognostics maintenance and missions scheduling: a railways case study

2021

International audience; In this paper, we propose a study of the decision horizon duration for rolling stock mission assignment and maintenance planning in a prognostics and health management (PHM) context. The aim is to determine the best decision horizon duration that allows the con- struction of a suitable schedule that assigns railway vehicles to missions and integrates required maintenance operations accord- ing to the current and future health of the vehicles. A genetic algorithm is used to minimize the overall cost of the joint schedule as a function of the decision horizon. The results are compared to three proposed heuristics to study the influence of the resolution method on the d…

050210 logistics & transportation0209 industrial biotechnologyScheduleOperations researchHorizon (archaeology)Computer science05 social sciences[INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS]TransportationContext (language use)02 engineering and technologyScheduling (computing)[SPI.AUTO]Engineering Sciences [physics]/Automatic020901 industrial engineering & automationMechanics of Materials0502 economics and businessAutomotive EngineeringGenetic algorithmPrognosticsDuration (project management)Heuristics
researchProduct

Autoencoders and Recurrent Neural Networks Based Algorithm for Prognosis of Bearing Life

2018

Bearings are one of the most critical components in electric motors, gearboxes and wind turbines. Therefore, bearing fault detection and prognosis of remaining useful life are important to prevent productivity losses. In this study, a novel method is proposed for prognosis of bearing life using an autoencoder and recurrent neural networks-based prediction algorithm. Promising results have been obtained from the experimental data. A monotonic upward trend of the produced health indicator is obtained for all test cases, being one of critical indicators of a proper prognosis. The remaining useful life estimation is moderately accurate under a limited data.

Electric motor021103 operations researchBearing (mechanical)Computer science020208 electrical & electronic engineeringFeature extraction0211 other engineering and technologies02 engineering and technologyBearing fault detectionAutoencoderlaw.inventionRecurrent neural networkTest caselaw0202 electrical engineering electronic engineering information engineeringPrognosticsAlgorithm2018 21st International Conference on Electrical Machines and Systems (ICEMS)
researchProduct

Rotor-bar breakage mechanism and prognosis in an induction motor

2015

© 1982-2012 IEEE. This paper proposes a condition-based maintenance and prognostics and health management (CBM/PHM) procedure for a rotor bar in an induction motor. The methodology is based on the results of a fatigue test intended to reproduce in the most natural way a bar breakage in order to carry out a comparison between transient and stationary diagnosis methods for incipient fault detection. Newly developed techniques in stator-current transient analysis have allowed tracking the developing fault during the last part of the test, identifying the failure mechanism, and establishing a physical model of the process. This nonlinear failure model is integrated in a particle filtering algor…

EngineeringFailure analysisBar (music)particle filtersremaining life assessmentFault (power engineering)Fault detection and isolationlaw.inventionlawspectrograminduction motorsElectrical and Electronic EngineeringSpectrogramFatigueFault diagnosisbusiness.industryRotor (electric)prognostics and health management (PHM)Prognostics and health management (PHM)Structural engineeringfault diagnosisfrequency-domain analysisrotorsInduction motorsControl and Systems EngineeringRotorsPrognosticsRemaining life assessmentINGENIERIA ELECTRICAfatigueTransient (oscillation)Particle filtersbusinessParticle filterInduction motor
researchProduct

UiA Accelerated Life Time Bearing Test Rig – Test 1, 250 rpm

2020

Vibration data from an accelerated lifetime test of a bearing. Contains raw vibration data and shaft position data. The mean shaft speed is 250 rpm. Can be used for fault diagnosis and remaining useful lifetime estimation. Please see "00_ReadMe.pdf" file for more details. Update - 3 January 2022: This dataset is now updated to use floating point values for shaft position data, which gives a much more accurate description of the shaft position.

Prognostics and health managementEngineeringComputer and Information ScienceRotating machinesVibration measurementBall bearingsFault diagnosis
researchProduct

UiA Accelerated Life Time Bearing Test Rig – Test 3, Variable speed around 50rpm

2021

Vibration data from an accelerated lifetime test of a bearing. Contains raw vibration data and shaft position data. The mean shaft speed is 50rpm with a variation +- 40 rpm. Can be used for fault diagnosis and remaining useful lifetime estimation. Please see "00_ReadMe.pdf" file for more details.

Prognostics and health managementEngineeringComputer and Information ScienceRotating machinesVibration measurementVariable speed drivesBall bearingsFault diagnosis
researchProduct

Integrated Production and Predictive Maintenance Planning based on Prognostic Information

2019

International audience; This paper address the problem of scheduling production and maintenance operation in predictive maintenance context. It proposes a contribution in the decision making phase of the prognostic and health management framework. Theprognostics and decision processes are merged and an ant colony optimization approach for finding the sequence of decisions that optimizes the benefits of a production system is developed. A case study on a single machine composed of several components where machine can have several usage profiles. The results show thatour approach surpasses classical condition based maintenance policy.

Remaining UsefulLife0209 industrial biotechnology021103 operations researchHealth management systemOperations researchComputer scienceCondition-based maintenanceAnt colony optimization algorithms[INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS]0211 other engineering and technologiesScheduling (production processes)02 engineering and technologyPredictive maintenanceAnt Colony Optimization[SPI.AUTO]Engineering Sciences [physics]/Automatic020901 industrial engineering & automationPrognostic InformationProduction and Maintenance SchedulingPrognosticsIntegrated productionDecision processPredic-tive Maintenance
researchProduct

On the Use of Prognostics and Health Management to Jointly Schedule Production and Maintenance on a Single Multi-purpose Machine

2020

This paper address the problem of using prognostic information in the decision-making process of a single multi-purpose machine. The prognostics and health management method is compared to condition-based maintenance combined with a genetic algorithm to determine the joint schedule of maintenance and production. The paper presents a methodology to select the adequate strategy while considering several factors that influence the functioning of the machine. The results show that operational and conditions variability influence the choice of the suitable methods. In the presented case, we show configurations where prognostic information is useless or useful.

ScheduleComputer scienceProcess (engineering)Ant colony optimization algorithmsCondition-based maintenanceGenetic algorithmPrognosticsProduction (economics)Reliability engineering2020 Prognostics and Health Management Conference (PHM-Besançon)
researchProduct